385 pubblicazioni classificate nel seguente modo:

Impact of sampling frequency and signal quantization on myoelectric-based hand gesture recognition
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Autore/i: Verdini, F.; Tigrini, A.; Scattolini, M.; Mobarak, R.; Fioretti, S.; Burattini, L.; Mengarelli, A.
Classificazione: 1 Contributo su Rivista
Abstract: The rapid advancement of wearable technologies has facilitated the acquisition of myoelectric signals, which are increasingly used as input for machine learning (ML) architectures to recognize human motion. However, the technical specifications of sensors and the experimental setup can significantly affect signal quality, potentially reducing the reliability of motor command recognition. This study investigates how signal quantization (ADC resolution) and sampling frequency influence the performance of myoelectric hand gesture recognition. Surface EMG was recorded with an armband during 20 gestures performed by 10 healthy subjects. Three acquisition settings were tested: 8-bit/500 Hz, 8-bit/1000 Hz, and 12-bit/500 Hz. A time-domain feature set was extracted and used to train three classifiers: linear discriminant analysis (LDA), linear support vector machine (SVM), and quadratic SVM (SVMQ). Results show that higher sampling frequency consistently improved classification accuracy, both with the full armband configuration and with a reduced sensor setup (4 channels). The linear SVM trained with the complete feature set achieved the best performance, with accuracy up to 90% using all sensors and around 80% with the minimal configuration. Even when trained with a single feature, such as mean absolute value or waveform length, the full configuration yielded accuracy above 80% across conditions. In contrast, ADC resolution had only a marginal impact on performance. Overall, the findings indicate that appropriate feature selection and sensor configuration can mitigate the effects of lower sampling rates, offering practical trade-offs between recognition accuracy and computational efficiency in wearable EMG-based systems.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/350652

AI-assisted methodology for robust digital measurements by Raman spectroscopy: Quantification of inorganic pollutants in water
MEASUREMENT
Autore/i: Nocera, A.; Luciani, L.; Ciattaglia, G.; Raimondi, M.; Burattini, L.; Spinsante, S.; Gambi, E.; Galassi, R.
Classificazione: 1 Contributo su Rivista
Abstract: Raman spectroscopy is a versatile analytical tool, yet it often struggles with low sensitivity, hardware noise, and environmental interference. To address these limitations, this study presents an automated, Artificial Intelligence (AI)-assisted methodology to convert noisy optical signals into robust digital measurements. The process involves acquiring high-dimensional, noisy spectral data from analyte solutions. A grid search across various algorithms identifies the optimal pre-processing pipeline to minimize noise variance and ensure metrological repeatability. Instead of relying on raw sensor feeds, the method fits a Gaussian curve combined with a polynomial baseline to the data, extracting precise measurements from the peak of this mathematical model. Supported by AI, the method successfully separates multiple optical signals and their shifts originating from interactions among analytes, proving itself capable to compensate also for possible hardware misalignment and thermal drift. As such, it can be used to quantify the concentration of selected inorganic pollutants in a mixture of analytes. The primary application addressed in this work is quantifying inorganic pollutants in water, to enable in situ analysis without continuous expert supervision. Tests on binary and ternary mixtures of inorganic pollutants in pure water demonstrated that the Mean Absolute Percentage Error (MAPE) for nitrate was consistently below 10% in the concentration range between 0 mg/L to more than 15 000 mg/L, dropping to under 5% for concentrations exceeding 1000 mg/L. For concentrations below 1000 mg/L, the Mean Absolute Error (MAE) values were 67 mg/L for nitrate, 1475 mg/L for sulfate, and 736 mg/L for nitrite, respectively.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/352632

Assessment of the Psycho-Emotional State Induced by Open-Skill Sport Activity: An Electroencephalography-Based Study
SENSORS
Autore/i: Iammarino, Erica; Marcantoni, Ilaria; Grillo, Sebastiano; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Electroencephalography (EEG) is an effective tool for monitoring the psycho-emotional state induced by open-skill sport activities characterized by dynamic environments and unpredictable situations, offering objective insights into mental engagement. This study aims to characterize the psycho-emotional state induced by table tennis sport activity by exploiting EEG-derived biomarkers. The ‘Real World Table Tennis’ database was analyzed, which includes EEG signals of 25 subjects acquired before, during and after playing table tennis. After preprocessing, 30-s EEG epochs were recursively extracted every 5 s. For each epoch, EEG rhythms were extracted and combined to obtain 37 engagement indexes, defined as ratios of two or more EEG rhythm powers. Median trends of each index were obtained for five cortical regions, and the Wilcoxon signed-rank test was applied to assess significant temporal changes. Results show that engagement indexes can effectively characterize psycho-emotional dynamics during table tennis, capturing the transition from resting to game phase in all cortical regions and exhibiting an increasing trend when having beta/alpha in their definition, and a decreasing trend when having high-frequency rhythms in the denominator. Our findings demonstrate the feasibility of using engagement indexes to monitor psycho-emotional states induced by open-skill sports and provide a framework for investigating mental engagement over time.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354879

Heart Sound Classification for Early Detection of Cardiovascular Diseases Using XGBoost and Engineered Acoustic Features
SENSORS
Autore/i: Karthikeya, P. P. Satya; Rohith, P.; Karthikeya, B.; Reddy, M. Karthik; V M, Akhil; Tigrini, Andrea; Sbrollini, Agnese; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Heart sound-based detection of cardiovascular diseases is a critical task in clinical diagnostics, where early and accurate identification can significantly improve patient outcomes. In this study, we investigate the effectiveness of combining traditional acoustic features and transformer-based Wav2Vec embeddings with advanced machine learning models for multi-class classification of five heart sound categories. Ten engineered acoustic features, i.e., Log Mel, MFCC, delta, delta-delta, chroma, discrete wavelet transform, zero-crossing rate, energy, spectral centroid, and temporal flatness, were extracted as regular features. Four model configurations were evaluated: a hybrid CNN + LSTM and XGBoost trained with either regular features or Wav2Vec embeddings. Models were assessed using a held-out test set with hyperparameter tuning and cross-validation. Results demonstrate that models trained on regular features consistently outperform Wav2Vec-based models, with XGBoost achieving the highest accuracy of 99%, surpassing the hybrid model at 98%. These findings highlight the importance of domain-specific feature engineering and the effectiveness of ensemble learning with XGBoost for robust and accurate heart sound classification, offering a promising approach for early detection and intervention in cardiovascular diseases.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/352944

Residual Functional Connectivity in Split-Brain Patients: the Cerebellar Contribution
21st National Congress of the Italian Society for Neuroscience, Congress Book
Autore/i: Fabri, Mara; Marcantoni, Ilaria; Iammarino, Erica; Polonara, Gabriele; Reversi, Luca; Piccolantonio, Giusi; Burattini, Laura
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354952

Electroencephalographic response to music: Characterization using involvement indexes
Convegno Nazionale di Bioingegneria
Autore/i: Iammarino, E.; Marcantoni, I.; D'Agostino, C.; Dell'Orletta, A.; Frezzotti, S.; Burattini, L.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Electroencephalogram (EEG) can be used to assess music-induced emotional responses evoked in listeners. To date, few EEG-derived indexes of involvement have been examined in this field. Thus, this study aims to investigate the use of EEG-derived involvement indexes as objective evidence of music-listening emotional effects, also comparing them with emotional states not affected by music. To do so, we have characterized and compared EEG-derived involvement indexes of a population under two different conditions: at rest without any auditory stimulus, and while listening to music. EEG data was acquired from 10 healthy subjects, as part of a freely available dataset on OpenNeuro, named “An EEG dataset recorded during affective music listening”. EEG recordings were processed using EEGLAB software. Preprocessing involved 0.5-70 Hz band-pass filtering, average re-referencing, and artifact removal via independent component analysis. Then, EEG rhythms were extracted, and 37 involvement indexes were derived as ratios of the spectral powers of two or more EEG rhythms. The Wilcoxon rank-sum test was applied to identify the most significant indexes for distinguishing between conditions. Results showed that 5 involvement indexes and 3 EEG channels, specifically O2, F8, and O1, were statistically significant in distinguishing between music listening and resting state. In addition, most of the indexes, if computed on specific scalp regions, were found to distinguish even among the different induced emotions (previously assessed by a Likert questionnaire). Our results, although preliminary, highlight the potential of EEG-based involvement indexes in distinguishing emotional conditions while listening to music and without music. This pilot study contributes to the field of affective computing and music therapy, supporting the development of EEG-based tools for emotion recognition and therapeutic interventions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354941

Evaluation of ChatGPT and Gemini Large Language Models for Generating Pharmacokinetic Models with SimBiology
Conference Proceedings - 2025 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2025
Autore/i: Del Giudice, L. L.; Piersanti, A.; Morelli, A.; Gobl, C.; Burattini, L.; Tura, A.; Morettini, M.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Generative Artificial Intelligence (AI) chatbots like ChatGPT or Gemini rely on Large Language Models (LLMs), which are deep-learning algorithms capable of recognizing, generating, summarizing, translating, and predicting content using large data sets. They are yielding a strong boost to technological innovation in all fields, including drug discovery and development, in which in-silico models are often used to describe the behavior of biological systems and study their pharmacokinetic/pharmacodynamic (PK/PD) properties. This study aimed to evaluate how Generative AI tools, such as ChatGPT and Gemini, among the widely accessible LLMs, can support the PK/PD modeling process. It evaluated the potential of these LLMs in generating instructions within SimBiology, a MATLAB tool dedicated to modeling, simulation and analysis of biological systems. Four case studies were considered, the first two aimed at teaching SimBiology fundamentals and at providing basic model examples, and the second two directly related to the creation of a PK/PD model. Each output was evaluated based on the instructions provided, the differences between the two LLMs' answers, the errors made, and the ability of the tool to correct them. The results showed that ChatGPT offered greater accuracy and flexibility in code generation than Gemini, since it is able to better correct its errors, although both presented structural and syntactic errors, limiting the fully automated modeling tasks. In conclusion, ChatGPT and Gemini are promising tools for building in-silico models, especially in the early stages of model development, but at present, they require human supervision and expertise to correct errors and improve reliability.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354979

Prognostic Role of Electrocardiographic Alternans in Heart Failure Patients with Implanted Cardioverter Defibrillator: Comparison of Machine Learning Methods
Computing in Cardiology
Autore/i: Marcantoni, Ilaria; Iammarino, Erica; Sbrollini, Agnese; A. Swenne, Cees; Burattini, Laura
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Implantable cardioverter defibrillator (ICD) is often indicated for the primary prevention of sudden cardiac death in heart-failure (HF) patients, but sometimes, the device remains always inactive, highlighting that the implantation criterium is not specific. The aim of this study is to assess if electrocardiographic alternans (ECGA; an index of cardiac instability) can have a useful prognostic role in improving the identification of HF patients who will experience serious ventricular arrhythmias and truly benefit from the ICD. We analyzed the Leiden University Medical Center database of primary prevention ICD patients by computing ECGA using the enhanced adaptive matched filter (EAMF) method. Patients were categorized into those who needed ICD therapy (40 cases) and those who did not (82 controls) based on their follow-up. ECGA features were used to train and test five machine learning methods (i.e., Decision Tree-DT, Logistic Regression-LR, Naïve Bayes-NB, Linear Discriminant Analysis-LDA, Support Vector Machine-SVM), whose performance was assessed by computing sensitivity (SE), specificity (SP), F1 score (F1) and accuracy (ACC). Results indicated that SVM was the most suitable algorithm (SE=98%; SP=83%; F1=96%; ACC=94%), followed by DT and LR, and ECGA appeared to be a potentially useful tool to improve identification of patients benefiting from ICD.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354885

Robustness of Symbolic Analysis for Estimating Heart-Rate Variability during Sport
Convegno Nazionale di Bioingegneria
Autore/i: Rinaldi, S.; Gjika, M.; Mortada, M. J.; Burattini, L.; Sbrollini, A.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Stress plays a crucial role in sports, influencing both physiological and psychological responses, specifically during competitions. Understanding the stress-response dynamics is critical for developing strategies to optimize performance and avoid adverse events, such as injury or death. Wearable sensors have revolutionized the real-time monitoring of athletes, being non-invasive and allowing the continuous collection of biomedical data during both training and competition. Heart rate variability (HRV), a key index of autonomic nervous system activity, has become an invaluable tool for assessing stress and recovery. Among various HRV analysis methods, symbolic analysis, which represents HRV data as discrete symbols based on signal amplitude or direction, seems to be robust in real-world conditions. The study aimed to evaluate the reliability and robustness of symbolic analysis in assessing stress induced by sports activities. Data was collected from 10 sprint athletes using portable sensors, recording 30-s electrocardiograms during various phases of training and competition. The symbolic analysis was applied to extract its symbolic patterns (0V, 1V, 2LV, 2UV) from RR-interval series at different times, that are rest, post-warm-up, end of short-distance running (eSDR), and recovery phases at 5-, 10-, and 15-minutes post-exercise, and from the same series by applying one-beat and two-beat delays. Statistical analysis revealed minimal significant differences between the different RR-interval series in terms of symbolic patterns, confirming the robustness of symbolic analysis to temporal variations. The strong correlation (ρ > 0.93) between the trends of symbolic patterns over time-related to the different RR-interval series supports the reliability of this technique in tracking autonomic regulation over time. These findings demonstrate the potential of symbolic analysis as a robust, real-time method for assessing stress in athletes, with practical implications for optimizing training and recovery strategies. Despite promising results, the study is limited in terms of sample size and variety of sports disciplines.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354882

Electrocardiographic alternans as an additional criterion for cardioverter defibrillator implantation in primary prevention of sudden cardiac death
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Autore/i: Marcantoni, Ilaria; Iammarino, Erica; Sbrollini, Agnese; Morettini, Micaela; Swenne, Cees A.; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: The current Guidelines recommend implantable cardioverter defibrillator (ICD) for primary prevention of sudden cardiac death (SCD) when left ventricular ejection fraction (LVEF) is reduced. Nevertheless, LVEF lacks sensitivity and specificity as a risk index, meaning that additional risk indexes are needed. Electrocardiographic alternans (ECGA) is the every-other-beat morphology oscillation in either ECG wave: P-wave/QRS-complex/T-wave alternans (PWA/QRSA/TWA, respectively). This study aims to investigate ECGA as an additional criterion to decide for ICD implantation for primary prevention of SCD. ECGs were acquired during a bicycle-ergometer test in a heart-failure population having ICDs for primary prevention. During follow-up, patients were classified into cases, if device therapy was administered, and controls, if no device therapy occurred. Resting and exercise ECGs were analyzed using the enhanced adaptive matched filter method (EAMFM) to identify ECGA. Unlike the exercise condition, the resting condition showed a statistically significant difference in PWA and QRSA between cases and controls. Thus, to classify them, rest-related ECGA features were used to feed a support vector machine (SVM), validated by a leave-one-out cross-validation algorithm. SVM yielded a sensitivity, specificity, and F1 score of 98.49%, 83.33%, and 95.61%, respectively. These results suggest that EAMFM-derived ECGA may act as a further useful feature to stratify the arrhythmia risk, overcoming the insufficient sensitivity and specificity of LVEF only. Thus, the main contribution of this study is the proposal of an additional ECGA-based criterion for identifying patients who may benefit from primary prevention ICD implantation paving the way for a conceivable revision of the current Guidelines.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/346673

MyoPose: position-limb-robust neuromechanical features for enhanced hand gesture recognition in colocated sEMG–pFMG armbands
JOURNAL OF NEURAL ENGINEERING
Autore/i: Mobarak, Rami; Zhang, Shen; Zhou, Hao; Mengarelli, Alessandro; Verdini, Federica; Burattini, Laura; Tigrini, Andrea; Alici, Gursel
Classificazione: 1 Contributo su Rivista
Abstract: Objective. Surface electromyography (sEMG) and pressure-based force myography (pFMG) are two complementary modalities adopted in hand gesture recognition due to their ability to capture muscle electrical and mechanical activity, respectively. While sEMG carries rich neural information about the intended gestures and has long been established as the primary control signal in myoelectric interfaces, pFMG has recently emerged as a stable modality that is less sensitive to sweat and can indicate motion onset earlier than sEMG, making their fusion promising for robust pattern recognition. However, gesture classification systems based on these signals often suffer from performance degradation due to limb position changes, which affect signal characteristics. Approach. To address this, we introduce MyoPose, a novel and lightweight spatial synergy-based feature set for enhancing neuromechanical control. MyoPose works on effectively decoding colocated sEMG-pFMG information to improve hand gesture recognition under limb position variability while remaining computationally efficient for resource-constrained hardware. Main results. The proposed MyoPose feature combined with linear discriminant analysis, achieved 87.7% accuracy (ACC) in a nine-hand gesture recognition task, outperforming standard myoelectric feature sets and comparable to a state-of-the-art decision-level multimodal fusion parallel convolutional neural network. Notably, MyoPose maintained computational efficiency, achieving real-time feasibility with an estimated controller delay of 110.62 ms, well within the operational requirement of 100-125 ms, as well as ultra-light memory requirement of 0.011 KB. Significance. The novelty of this study lies in providing an effective feature set for multimodal driven hand gesture recognition, handling limb position variations with robust ACC, and showing potential for real-time feasibility for human-machine interfaces without the need for deep learning.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/346812

Variability of the Skin Temperature from Wrist-Worn Device for Definition of Novel Digital Biomarkers of Glycemia
SENSORS
Autore/i: Piersanti, Agnese; Littero, Martina; Del Giudice, Libera Lucia; Marcantoni, Ilaria; Burattini, Laura; Tura, Andrea; Morettini, Micaela
Classificazione: 1 Contributo su Rivista
Abstract: This study exploited the skin temperature signal derived from a wrist-worn wearable device to define potential digital biomarkers for glycemia levels. Characterization of the skin temperature signal measured through the Empatica E4 device was obtained in 16 subjects (data taken from a dataset freely available on PhysioNet) by deriving standard metrics and a set of novel metrics describing both the current and the retrospective behavior of the signal. For each subject and for each metric, values that correspond to when glycemia was inside the tight range (70–140 mg/dL) were compared through the Wilcoxon rank-sum test against those above or below the range. For hypoglycemia characterization (below range), retrospective behavior of skin temperature described by the metric CVT SD (standard deviation of the series of coefficient of variation) proved to be the most effective both in daytime and nighttime (100% and 50% of the analyzed subjects, respectively). On the other side, for hyperglycemia characterization (above range), differences were observed between daytime and nighttime, with current behavior of skin temperature, described by M2T (deviation from the reference value of 32 °C), being the most informative during daytime, whereas retrospective behavior, described by SDT hhmm (standard deviation of the series of means), showed the highest effectiveness during nighttime. Proposed variability features outperformed standard metrics, and in future studies, their integration with other digital biomarkers of glycemia could improve the performance of applications devoted to non-invasive detection of glycemic events.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/345972

Myoelectric and Inertial Data Fusion Through a Novel Attention-Based Spatiotemporal Feature Extraction for Transhumeral Prosthetic Control: An Offline Analysis
SENSORS
Autore/i: Tigrini, Andrea; Mengarelli, Alessandro; Al-Timemy, Ali H.; Khushaba, Rami N.; Mobarak, Rami; Scattolini, Mara; Sharba, Gaith K.; Verdini, Federica; Gambi, Ennio; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: This study proposes a feature extraction scheme that fuses accelerometric (ACC) and electromyographic (EMG) data to improve shoulder movement identification in individuals with transhumeral amputation, in whom the clinical need for intuitive control strategies enabling reliable activation of full-arm prostheses is underinvestigated. A novel spatiotemporal warping feature extraction architecture was employed to realize EMG and ACC information fusion at the feature level. EMG and ACC data were collected from six participants with intact limbs and four participants with transhumeral amputation using an NI USB-6009 device at 1000 Hz to support the proposed feature extraction scheme. For each participant, a leave-one-trial-out (LOTO) training and testing approach was used for developing pattern recognition models for both the intact-limb (IL) and amputee (AMP) groups. The analysis revealed that the introduction of ACC information has a positive impact when using windows of length (WLs) lower than 150 ms. A linear discriminant analysis (LDA) classifier was able to exceed the accuracy of 90% in each WL condition and for each group. Similar results were observed for an extreme learning machine (ELM), whereas k-nearest neighbors (kNN) and an autonomous learning multi-model classifier showed a mean accuracy of less than 87% for both IL and AMP groups at different WLs, guaranteeing applicability over a large set of shallow pattern-recognition models that can be used in real scenarios. The present work lays the groundwork for future studies involving real-time validation of the proposed methodology on a larger population, acknowledging the current limitation of offline analysis.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/348432

Myoelectric Temporal Patching: Future Prosthetics Shall Effectively Leverage sEMG Temporal Patterns
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Mobarak, R.; Khushaba, R.; Mengarelli, A.; Al-Timemy, A. H.; Verdini, F.; Samuel, O. W.; Fioretti, S.; Burattini, L.; Tigrini, A.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Robust myoelectric control is essential for advancing lower limbs active assistive devices and prosthetics. Feature extraction from surface Electromyographic (sEMG) signals serves as a fundamental component influencing the performance of such controllers. While deep learning models, such as Long Short-Term Memory (LSTM) networks, have been increasingly used to extract hidden features from raw sEMG data by leveraging temporal contexts in laboratory studies, the use of such models on prosthetic controllers is often associated with large memory and computational overheads, thus necessitating expensive hardware. To address these challenges, this study proposes a novel handcrafted feature extraction method, termed Myoelectric Temporal Patching (MTP), that works on extracting multi-signal features from patches within the short-segments of sEMG and propagating information across the windows, to capture both short- and long-term temporal dynamics of sEMG signals, without the high computational burden. Two pattern recognition experiments were conducted to validate the proposed method: gait phase recognition using the SIAT-LLMD dataset and locomotion mode recognition using the MyPredict 1 dataset. Results demonstrated that the MTP feature set consistently outperformed (p < 0.0001) traditional and spatial feature sets across three machine learning models - Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The proposed method achieved peak accuracies of 85.11% in gait phase recognition and 87.70% in locomotion mode recognition when using SVM. These findings underscore the effectiveness of the proposed temporal features in decoding lower-limb motion intentions, emphasizing the critical role of temporal dynamics of sEMG signals.Clinical relevanceThis work opens the door for pushing forward the assistive and prosthetic devices of the lower limbs to meet commercial-level requirements by providing robust and feasible solutions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354333

Inertial-Based 3D Knee Joint Angular Kinematics Estimation: Effect of Number of Repetitions During Functional Calibration
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Scattolini, M.; Tigrini, A.; Verdini, F.; Burattini, L.; Fioretti, S.; Mengarelli, A.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Inertial-based joint kinematics is gaining significant attention due to the compactness and low cost of inertial measurement unit (IMU). Anatomical reference frames from IMUs can be defined considering specific subject posture and movements; this procedure is known as functional approach. Typically, movements are repeated a certain number of times, mainly ten times, to improve the accuracy of the estimated frames. However, no studies have investigated whether fewer repetitions result in a significant degradation of the angle estimates. Thus, the main aim of the present work is to present an anatomical calibration approach based on subject movements to define the anatomical reference frames reducing gradually the duration of the considered trial used for the calibration. Based on the results, knee joint 3D kinematics has been estimated including one, three and ten repetitions of the calibration movements, and then compared with the gold-standard optoelectronic system. Errors in the estimates were assessed using the root mean square (RMSE) and the mean absolute percentage (MAPE) errors. The best results have been obtained including ten repetitions, RMSE of 2.1 deg, 3.8 deg, and 4.6 deg for flexion/extension (FE), abduction/adduction (AA) and internal/external (IE) rotation, respectively, outperforming other studies. Notably, these results were not statistically different from the condition with three repetitions for the FE, while a strong difference has been observed for the IE. These findings support the feasibility of obtaining clinically relevant kinematics from IMUs with reduced time for the functional calibration, thus improving patient comfort and minimizing fatigue.Clinical relevance - Presented outcomes allow the possibility to obtain reliable kinematics estimates with non-obtrusive sensors reducing the required time for sensor calibration, also improving patient comfort during evaluation session.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354332

Enabling Automatic Monitoring of Fluid Intake and Medical Adherence by Human Activities Recognition from a Wrist-Mounted MIMU Sensor
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Mengarelli, A.; Scattolini, M.; Tigrini, A.; Mobarak, R.; Verdini, F.; Burattini, L.; Iadarola, G.; Spinsante, S.; Fioretti, S.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The automatic identification of human activities is an important application for enabling remote home monitoring of health status in elderly and fragile people. Nowadays, commercially available wearable devices found a widespread diffusion, embedding various types of sensors that can be used for correctly recognizing activities of daily living (ADL). This work deals with the identification of ADL based on upper limb gestures from a single magnetic inertial measurement unit (MIMU) placed on the wrist. In particular, emphasis was devoted to the identification of drinking and pill intake, being direct indicators of water and medication assumption. To this aim, machine learning (ML) and deep learning (DL) models were directly compared, and single MIMU recordings were evaluated on three classification experiments. Outcomes showed that DL pipeline outperformed ML in distinguishing 14 ADL, with the best accuracy provided by the combination of gyroscope and magnetometer data (about 93%). The same configuration reached over 97% accuracy in identify drinking and pill intake among the other 12 confounding ADL. This study is a step toward the development of a robust solution for the continuous and minimally invasive monitoring of hydration behaviors and adherence to medical prescription within the home environment.Clinical relevance - This work provides evidences about the feasibility of a continuous and non-invasive monitoring of the hydration behaviors and adherence to medical prescriptions in elderly individuals.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354336

Temporal Context Informed Myoelectric Feature Extraction Uncovers Frequency Invariance in EMG-based Gesture Recognition
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Khushaba, R. N.; Mobarak, R.; Samuel, O. W.; Tigrini, A.; Burattini, L.; Al-Timemy, A. H.; Al-Nussairy, M.; Mengarelli, A.; Li, G.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Human-machine interfaces based on Electromyographic (EMG) armbands are commonly utilized for gesture recognition using cross-sectional feature extraction (FE) schemes, those typically ignoring long-and short-term activity trends. This approach lacks the ability to capture the different movements' context and often generates spurious decisions based on short windows of non-stationary EMG signals. The current study builds upon recent advances in spatial information extraction, as represented by our Phasor-based Multi-signal Waveform Length (MSWL) features, by encapsulating these features within a temporal context framework. Two streams of information are concatenated: a short-term memory component emphasizing partial correlation with previous analysis windows and a long-term component emphasizing the trend of the features belonging to the specific movements. The proposed method was evaluated on EMG datasets from: 1) twenty-two subjects using two simultaneously placed armbands with different sampling frequencies (200Hz MYO and 1000Hz 3DC), and 2) six transradial amputees following the NinaPro protocol and using the MYO armband for 17 movement classes. Our findings using the LibEMG toolbox show that context-aware EMG feature extraction achieves sampling frequency invariance in gesture pattern recognition. Despite literature favoring higher frequency armbands, our method delivers similar average accuracy (91%, p-value>0.05) across both high- and low-frequency armbands. Notably, our method outperforms 58 FE methods from the LibEMG toolbox, this is further supported by the findings on the amputees' database highlighting its efficacy in context-sensitive EMG pattern recognition.Clinical Relevance - This study shows that context-aware EMG feature extraction achieves high accuracy in clinical gesture recognition, challenging the traditional preference for higher frequency devices.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354334

Novel gait phases recognition framework leveraging the temporal structure of the myoelectric activity
JOURNAL OF NEURAL ENGINEERING
Autore/i: Mobarak, Rami; Mengarelli, Alessandro; Khushaba, Rami N; Al-Timemy, Ali H; Prinsen, Erik C; Verdini, Federica; Leijendekkers, Ruud A; Fioretti, Sandro; Burattini, Laura; Tigrini, Andrea
Classificazione: 1 Contributo su Rivista
Abstract: Objective. Reliable control of lower limb prostheses during gait using surface electromyography requires robust decoding of myoelectric signals to ensure safety and efficiency. Conventional myoelectric pattern recognition (PR) methods, which classify features extracted from each window, often yield inaccurate and unstable output, limiting their practical use. Approach. To deal with these issues, two novel temporal myoelectric-based gait phase recognition frameworks are presented. Temporal activation profile (TAP) considers a sequence of features extracted from consecutive windows, and dual activation shots (DAS) using features extracted from the current and a specific preceding window. These methods were tested on (1) publicly available SIAT-LLMD dataset of 40 healthy subjects under different locomotion conditions, and (2) two subjects with transfemoral amputation during normal walking. Main results. TAP and DAS significantly outperformed conventional PR methods, achieving accuracies of 88.50% and 87.97%, respectively, in healthy subjects during normal walking. TAP achieved optimal performance using features extracted from consecutive windows spanning 240 ms in the past, whereas DAS performed best when leveraging features from the current window combined with those from a window 160 ms prior. No significant differences were observed between TAP and DAS under optimal conditions. Both approaches effectively enhanced gait phase recognition performance when applied to transfemoral amputee gait data. The TAP framework achieved the highest performance, surpassing 87.80% accuracy with extended temporal context requirement, and outperforming the DAS approach (82.32%) under pathological conditions. Significance. Both TAP and DAS are robust solutions for gait phase recognition as they stabilize the decision output and reduce classification errors. DAS is more practically feasible due to lower temporal and computational demands, while TAP is more effective in the case of altered neuromuscular activation patterns. The findings of this paper highlight the potential of integrating these methods into real-time prosthetic controllers, ensuring safe and reliable use for patients.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/347033

Novel Physics-Informed Bayesian Fusion Post-Processor for Enhanced Gait Phase Recognition Using Surface Electromyography
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
Autore/i: Mobarak, Rami; Mengarelli, Alessandro; Khushaba, Rami N.; Al-Timemy, Ali H.; Verdini, Federica; Fioretti, Sandro; Burattini, Laura; Tigrini, Andrea
Classificazione: 1 Contributo su Rivista
Abstract: Myoelectric pattern recognition systems serve as a promising predictive control approach for the lower limbs prostheses and exoskeletons. However, their actual deployment is challenged by the signal stochastic nature that could contaminate the decision stream with physiologically implausible transitions, posing safety and metabolic cost concerns on the potential user. Therefore, this study proposes a novel Physics-Informed Bayesian Fusion (PI-BF) post-processor that embeds biomechanical sequentiality constraints into the posterior probabilistic output of the classifiers to suppress unstable transitions and promote natural gait progression. Time-Domain (TD) and Time-Dependent Power Spectrum Descriptors (TD-PSD) features were extracted from the lower limbs muscles surface electromyography (sEMG) signals and classified using Support vector machines (SVM), Artificial neural networks (ANN), K-Nearest Neighbour (KNN), and a CNN-LSTM hybrid deep learning model to predict five phases of gait cycle. The output of these classifiers was followed by the proposed PI-BF postprocessor and it was compared against Bayesian Fusion (BF) Majority voting (MV) as well as the performance without post-processing (WPP) using different numbers of votes from the previous windows. Results shows that PI-BF can increase the classification accuracy by up to 5.5% reaching up to 85% in SIAT-LLMD dataset (40 subjects) using SVM with 3 previous decision windows. It also reduced Transition Detection Difference (TDD) to 0.1 ± 59.8 ms and improved output stability by 5%, as measured by the Instability (INS) index. The proposedPI-BF exhibited consistent improvements in real-time gait phase recognition experiments, achieving classification accuracies of around 90%. These results demonstrate that PI-BF offers a practical, low-complexity solution for enhancing the safety, reliability, and real-time performance of myoelectric control in assistive lower-limb devices.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/348440

FetalBio-AI: Novel AI-based Software for Fetal Biometry Estimation
Convegno Nazionale di Bioingegneria
Autore/i: Sbrollini, A.; Gjika, M.; Mortada, M. J.; Alkalet, M.; Burattini, L.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Fetal development during pregnancy is a highly intricate biological process that requires continuous monitoring to ensure the health of both the mother and fetus. Ultrasound imaging has become the gold standard in obstetric care due to its non-invasive nature, ability to provide real-time images, and widespread accessibility. One of the primary applications of ultrasound in prenatal care is fetal biometry, which involves measuring key anatomical parameters such as head circumference (HC), biparietal diameter (BPD), and occipitofrontal diameter (OFD). The current process of fetal biometry is often performed manually, which can introduce inaccuracies due to the subjectivity of different observers and the time-consuming nature of the procedure. To address these challenges, this study introduces FetalBio-AI, an innovative AI-based software designed to automate the estimation of fetal head biometry from ultrasound images. By integrating a user-friendly interface and a U-Net model for image segmentation, FetalBio-AI accurately detects the fetal head and computes key biometric parameters, including BPD, OFD, and HC. In addition to automating these measurements, FetalBio-AI integrates maternal and fetal clinical data. The software was validated using the open-access HC18 Grand Challenge dataset, which includes 999 annotated 2D ultrasound images. The results demonstrated a strong correlation between the software’s predictions and manual annotations (Pearson’s correlation > 0.99), with minimal differences in head circumference measurements (mean difference of -0.2 mm). These findings confirm the high accuracy of FetalBio-AI, which provides automated fetal biometry with precision comparable to expert sonographers. Future studies will expand the software, including additional fetal biometric measurements, such as abdominal circumference and femur length, and further assess its performance across diverse clinical populations. The availability of FetalBio-AI on GitHub ensures that it is accessible to the research community, promoting collaboration and ongoing improvement of AI-driven solutions in obstetric care.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354875

Cerebellar Functional Connectivity Reorganization in a Split-Brain Patient
2025 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE)
Autore/i: Iammarino, Erica; Marcantoni, Ilaria; Reversi, Luca; Mariotti, Francesco; Piccolantonio, Giusi; Foschi, Nicoletta; Ghoushi, Mojgan; Devivo, Luisa; Polonara, Gabriele; Fabri, Mara; Burattini, Laura
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The Functional Connectivity (FC) assesses the functional relationships between different brain regions. Interhemispheric FC is assumed to be specifically supported by the corpus callosum (CC). This study aims to investigate FC between cerebellum and resting state networks (RSNs), as well as intra-cerebellar FC, in a patient who underwent surgical resection of CC and in a healthy control. The investigation contributes to verify the hypothesis of a compensatory cerebellar role in maintaining a certain degree of interhemispheric FC after callosal resection. Anatomical and functional magnetic resonance images were analyzed using CONN. After standard preprocessing, the brain was parcellated into 30 cortical RSN regions of interest (ROIs) based on the Human Connectome Project (HCP) networks, and the cerebellum was parcellated into 18 ROIs according to the Automated Anatomical Labeling (AAL) atlas. FC was evaluated by computing the Fisher z-transformed bivariate correlation coefficients, and statistical differences were assessed by Wilcoxon signed rank test. Distinct patterns of FC were observed between patient and healthy control, both within the cerebellum and between cerebellar and cortical RSN ROIs. The patient's cerebellar FC with RSN ROIs was statistically different from that of the control (in most instances higher) in 11 cerebellar ROIs, 7 of which in the right of the cerebellum and 4 in the left. The patient intra-cerebellar FC was also statistically different from that of the control (in most instances higher). These results suggest that the cerebellum may have a role in the maintenance of interhemispheric FC after surgical resection of the CC.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/352252

Cerebellar Functional Connectivity Reorganization in a Split-Brain Patient
Conference Proceedings - 2025 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2025
Autore/i: Iammarino, Erica; Marcantoni, Ilaria; Reversi, Luca; Mariotti, Francesco; Piccolantonio, Giusi; Foschi, Nicoletta; Ghoushi, Mojgan; De Vivo, Luisa; Polonara, Gabriele; Fabri, Mara; Burattini, Laura
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The Functional Connectivity (FC) assesses the functional relationships between different brain regions. Interhemispheric FC is assumed to be specifically supported by the corpus callosum (CC). This study aims to investigate FC between cerebellum and resting state networks (RSNs), as well as intra-cerebellar FC, in a patient who underwent surgical resection of CC and in a healthy control. The investigation contributes to verify the hypothesis of a compensatory cerebellar role in maintaining a certain degree of interhemispheric FC after callosal resection. Anatomical and functional magnetic resonance images were analyzed using CONN. After standard preprocessing, the brain was parcellated into 30 cortical RSN regions of interest (ROIs) based on the Human Connectome Project (HCP) networks, and the cerebellum was parcellated into 18 ROIs according to the Automated Anatomical Labeling (AAL) atlas. FC was evaluated by computing the Fisher z-transformed bivariate correlation coefficients, and statistical differences were assessed by Wilcoxon signed rank test. Distinct patterns of FC were observed between patient and healthy control, both within the cerebellum and between cerebellar and cortical RSN ROIs. The patient's cerebellar FC with RSN ROIs was statistically different from that of the control (in most instances higher) in 11 cerebellar ROIs, 7 of which in the right of the cerebellum and 4 in the left. The patient intra-cerebellar FC was also statistically different from that of the control (in most instances higher). These results suggest that the cerebellum may have a role in the maintenance of interhemispheric FC after surgical resection of the CC.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354812

Prognostic Role of Electrocardiographic Alternans in Ischemic Heart Disease
JOURNAL OF CLINICAL MEDICINE
Autore/i: Marcantoni, Ilaria; Iammarino, Erica; Dell'Orletta, Alessandro; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Background/Objectives: Noninvasive arrhythmic risk stratification in patients with ischemic heart disease is poor nowadays, and further investigations are needed. The most correct approach is based on the use of electrocardiogram (ECG) with the extraction of indices such as ECG alternans (ECGA). The aim of this study is to monitor the ECG evidence of ischemic coronary artery occlusion by the ECGA and to verify its ability to monitor the time course of balloon inflation, with the final goal of contributing to the exploration of the prognostic role of ECGA in ischemic heart disease. Methods: The ECGA amplitude and magnitude were computed by the correlation method (CM) on the STAFF III database, where ischemic coronary artery occlusion was induced in a controlled manner through coronary artery blockage by balloon inflation. ECGA computed during balloon inflation was also compared with periods before and after the inflation. Results: ECGA values became statistically higher during inflation than in the pre-inflation period and increased as inflation time increased, although not always in a statistically significant manner. ECGA went from values in the range 4–7 µV and 169–396 µV·beat before inflation to values in the range 5–9 µV and 208–573 µV·beat during 5 min of inflation (resulting statistically higher than before inflation), returning towards values in the range 4–8 µV and 182–360 µV·beat after inflation for amplitude and magnitude, respectively. Conclusions: CM-based ECGA detection was able to track the balloon inflation period. Our ECGA investigation represents a contribution in the field of research exploring its prognostic role as a noninvasive electrical risk index in ischemic heart disease.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/343733

Assessing hypoglycemia risk during hemodialysis using an explainable machine learning approach based on continuous glucose monitoring metrics
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Autore/i: Piersanti, A.; Morettini, M.; Cristino, S.; Del Giudice, L. L.; Burattini, L.; Mosconi, G.; Gobl, C. S.; Mambelli, E.; Tura, A.
Classificazione: 1 Contributo su Rivista
Abstract: Continuous glucose monitoring (CGM) can identify hypoglycemia in hemodialysis (HD) patients, who are at risk for this event. On the other hand, machine learning has remarkable value in CGM-based studies, but none of previous studies addressed the problem of hypoglycemia prediction in HD patients. Therefore, we conducted this study to setup different machine learning models based on CGM data (specifically, CGM metrics) to assess the risk of mild and severe hypoglycemia during HD sessions. We studied a cohort of twenty patients (11 with and 9 without diabetes) undergoing chronic HD. All patients underwent CGM for up to 2 weeks. We identified 92 HD sessions and related pre-HD sessions of 8 h length. HD sessions were used to identify mild (<70 mg/dL) and severe (<54 mg/dL) hypoglycemia, whereas pre-HD sessions were used to compute 48 CGM metrics. We then performed feature selection to identify the most relevant metrics for hypoglycemia prediction. The metrics performance was assessed with binary decision tree, k-nearest neighbors, penalized logistic regression, Naïve Bayes, random forest ensemble algorithm. We found that mild hypoglycemia was best predicted by six metrics (M-value100, TIR70-180, ADRR, MAGE-, MAG30, CONGA1h), whereas severe hypoglycemia by three metrics (TIR70-180, ADRR, CONGA1h). The best overall performance was achieved by the tree, showing area under receiver operating characteristic curve (AUC) equal to 68.2 % for prediction of mild hyperglycemia, and AUC equal to 81.2 % for severe hyperglycemia. Notably, individual hypoglycemia risk assessment has potential to guide personalized HD-related clinical decisions to minimize such risk.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/338314

U-Grad: A Grad-CAM-Guided Reduced U-Net for Efficient Lung Cancer Segmentation
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Bruschi, G.; Sbrollini, A.; Carletti, M.; Mortada, M. J.; Burattini, L.
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Lung cancer is the most common cause of cancerrelated death worldwide. The detection of lung nodules from Computed Tomography (CT) scans is essential for assessing disease progression, monitoring treatment response, and guiding therapeutic strategies. Deep learning has emerged as a powerful tool for image segmentation, demonstrating significant potential in medical imaging applications. This work aims to introduce U-Grad, a novel model designed for lung nodule segmentation from 2D CT slices. It integrates an encoder that generates heatmaps using Gradient-weighted Class Activation Mapping (Grad-CAM), which are then concatenated with CT slices and fed into a Reduced U-Net to enhance nodule representation. The Reduced U-Net is characterized by an encoder-decoder structure whose maximum depth, in terms of filter size, is (256,256), Additionally, it employs the Leaky Rectified Linear Unit as an alternative activation function, enhancing its representational capacity. NSCLC Radiogenomics dataset from The Cancer Imaging Archive was used to train and test the proposed U-Grad for 100 epochs. The performance of both the Reduced U-Net and U-Grad models was evaluated using the Dice Coefficient (DC) and the Intersection over Union (IoU) metrics. The results demonstrate that both models outperform existing models in the literature. The Reduced U-Net achieves a DC of 93.15% and an IoU of 89.02%, while U-Grad achieves a DC of 91.27% and an IoU of 86.26% in test set. Although both models exhibit comparable performance, U-Grad demonstrates slightly lower overfitting, making it a more robust alternative. Moreover, U-Grad's ability to generate interpretable heatmaps enhances its utility for clinical applications and research, particularly in resource-limited settings where annotated data are scarce.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354913

Single Hidden Layer Perceptron GAN for Mixed Meal Continuous Glucose Monitoring Data
Conference Proceedings - 2025 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2025
Autore/i: Del Giudice, L. L.; Piersanti, A.; Salotti, M.; Gobl, C.; Burattini, L.; Tura, A.; Morettini, M.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Generative Adversarial Networks (GANs) have emerged as valuable solutions for generating realistic data, addressing challenges such as missing values and/or data scarcity. In the context of diabetes management, where data scarcity is an issue, GAN s may offer a method for generating synthetic continuous glucose monitoring (CGM) traces resembling the characteristics of real data. This study focuses on developing a GAN for CGM mixed meal traces generation leveraging on single-macronutrient CGM traces. To this aim, a GAN model, based on a single hidden layer perceptron architecture, was designed using a set of freely-available single-macronutrients data; hyperparameter settings was performed using a random search approach. Reliability of GAN generated mixed meal data was tested through comparison with real mixed meal data taken from a second freely-available dataset. Comparison was performed using the Two One-Sided Test (TOST) for equivalence on a set of ten characteristics features (area under the curve, median, mean, standard deviation, coefficient of variation, maximum, minimum, sample at which maximum and minimum occur, time in range) extracted from generated and real mixed-meal data. The median area under the curve (AUC) of the generated and real data resulted equal to 3.40 [3.13, 3.94]× 103mg/dL (median [1st quartile, 3rd quartile]), and 3.95 [3.60, 4.10]× 103mg/dL, respectively. The results of the TOST showed substantial equivalence between generated and real mixed meal CGM traces for all the features. Indeed, the margin of equivalence δ was no more than 0.4 standard deviation of each feature. In conclusion, the proposed GAN appears promising to generate CGM mixed meal traces leveraging on single-macronutrient CGM traces.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354981

Ic4FECG: A New Index for Automatic Selection of the Most Relevant Independent Component in Noninvasive Fetal Electrocardiography
Computing in Cardiology
Autore/i: Giordano, N.; Burattini, L.; Sbrollini, A.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Independent Component Analysis is often used to extract fetal ECG (FECG) from maternal abdominal signals, but choosing the correct independent component (IC) has traditionally been empirical and subjective. This study introduces Ic4FECG, a quantitative index for automatically selecting the most relevant IC. The index is based on the assumption, supported by the literature, that the typical Fetal Heart Rate (FHR) is around 140bpm, (RR interval of 428ms), and that deviations reflect noise or maternal contamination. Ic4FECG is defined as Ic4FECG = ||(428ms-μFRR)×σFRR||, where μFRR and σFRR are mean and standard deviation of the fetal RR interval series. Using 36 maternal abdominal recordings from the “NInFEA” database, maternal interference was first reduced with PCA, assuming FECG lies in the lowest 5% variance. ICA then decomposed the residual into 20 ICs. Fetal R-peaks were detected in each IC, and Ic4FECG was computed. The IC with the lowest Ic4FECG was selected, and its FHR (FHRIC) was compared with ultrasound-derived FHR (FHRDUS). Results showed strong agreement with FHRIC = 140 ± 9 bpm, and FHRDUS = 141 ± 8 bpm, and significant correlation (ρ = 0.75, p < 10-8). Ic4FECG appears to be a potentially useful tool for automated selection of the most relevant IC in FECG analysis.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354877

F-wave sway in paroxysmal and chronic atrial fibrillation
JOURNAL OF ELECTROCARDIOLOGY
Autore/i: Sbrollini, A.; Rivolta, M. W.; Van Dam, P.; Viani, E.; Morettini, M.; Sassi, R.; Burattini, L.; Locati, E. T.
Classificazione: 1 Contributo su Rivista
Abstract: Vectorcardiography (VCG) can evaluate the vector loops of electrocardiographic waves, being a time-spatial representation of the heart vector into the three orthonormal leads. During atrial fibrillation (AF), F waves reflect the disorganized depolarization of the atria, replacing the organized P wave. Usually, paroxysmal AF (PAF) spontaneously terminates, differently from chronic AF (CAF), possibly due to the still-preserved main direction of the P-wave vector loop. To investigate this hypothesis, this study aims to evaluate the similarities between the P-wave vector loop and F-wave vector sway in subjects affected by PAF and CAF. Overall, 10-s VCG were acquired from 10 healthy (HEA) subjects showing normal sinus rhythm, 10 subjects affected by PAF (one during normal sinus rhythm and one during AF), and 10 subjects affected by CAF. P waves were extracted using ECGdeli software, while F waves were extracted after QRST cancellation. Ellipse axes and eccentricities were calculated as the root mean square of VCG components and the ratio between axes, respectively. Overall, 84 beats of HEA, 205 beats of PAF (89 beats during normal sinus rhythm and 116 during fibrillation), and 103 beats of CAF were analyzed. Distributions of axes and eccentricities of PAF are not statistically different (P-value>0.05) than normal sinus rhythm but features related to the Z axis of CAF were statistically lower than PAF (Pvalue(10- 3). F-wave vector sway in PAF resembles the P-wave vector loop, suggesting the maintenance of the atrial depolarization main direction in subjects with self-terminating AF. Moreover, the F-wave vector sway is more manifest in PAF than in CAF.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354880

Quantifying CineECG Output for Enhancing Electrocardiography Signals Classification
IEEE OPEN JOURNAL OF ENGINEERING IN MEDICINE AND BIOLOGY
Autore/i: Mortada, M. H. D. J.; Sbrollini, A.; Marcantoni, I.; Iammarino, E.; Burattini, L.; Van Dam, P.
Classificazione: 1 Contributo su Rivista
Abstract: CineECG, a vectorcardiography-based method, uses standard 12-lead electrocardiography and 3D heart and torso models to depict the electrical activation path during the heart cycle, offering detailed visualization of cardiac electrical activity without numerical quantification. Our research aims to quantify CineECG outputs by defining 54 features that describe the route, shape, and direction of electrical activation. These features were used to develop a multinomial regression model classifying electrocardiography signals into normal sinus rhythm, left bundle branch block, right bundle branch block, and undetermined abnormalities. Trained and tested on 6,860 signals from the PhysioNet/Computing in Cardiology Challenge 2020 and THEW project, the model achieved an F1 score over 84% (normal sinus rhythm: 93%, left bundle branch block: 93%, right bundle branch block: 90%, undetermined abnormalities: 84%). The results suggest CineECG's potential in enhancing electrocardiography interpretation and aiding in the accurate diagnosis of various abnormalities.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354887

Hypoglycemia Prediction from Pre-Exercise Continuous Glucose Monitoring Time Series: Deep-Learning Versus Feature-Based Machine-Learning Approaches
Conference Proceedings - 2025 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2025
Autore/i: Piersanti, A.; Del Giudice, L. L.; Beltramba, G.; Gobl, C.; Burattini, L.; Tura, A.; Morettini, M.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Exercise-induced hypoglycemia poses significant risks to individuals with type 1 diabetes (T1D), discouraging their involvement in physical activity and preventing them from exploiting its known benefits. Although continuous glucose monitoring (CGM) systems may alert the patient of impending high or low glucose levels, they still lack efficient and specific algorithms enabling a safe hypoglycemia prediction prior exercise. Deep learning (DL) and machine learning (ML) approaches now represent potential solutions for the development of clinical decision support systems in the field of diabetes. Thus, this study examined CGM time series preceding the exercise and evaluated the use of DL and feature-based ML approaches to predict hypoglycemia occurring from the start of exercise until the following morning. We analyzed 47 CGM recordings pertaining to T1D young patients that performed a controlled exercise on a treadmill. Recordings were labelled as HYPO or NO-HYPO, based on the occurrence or absence of hypoglycemic episodes, respectively. A Bidirectional-Long Short-Term Memory (Bi-LSTM) model was trained using raw CGM time series and validated through leave-one-out cross validation. Data augmentation techniques were applied to enhance the small and unbalanced dataset. Results were compared to those previously obtained with ML approaches based on clinically relevant CGM features extracted from the same data. The comparison showed that while the Bi-LSTM DL model exhibited very high specificity (SPDL=84.6%vs SPML=76.1%), feature-based ML was superior in terms of sensitivity (SEML=87.2% vs SEDL=67.7%), especially important in clinical decision making. In conclusion, DL and ML-based approaches both revealed their potential for exercise-induced hypoglycemia prediction.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354980

LuCa: A Novel Method for Lung Cancer Delineation
APPLIED SCIENCES
Autore/i: Carletti, M.; Bruschi, G.; Mortada, M. H. D. J.; Burattini, L.; Sbrollini, A.
Classificazione: 1 Contributo su Rivista
Abstract: Lung cancer remains the leading cause of cancer-related deaths worldwide, with over 2.4 million new diagnoses in 2022. Early diagnosis remains challenging due to the non-specificity of symptoms, often resulting in late-stage detection. Although 2-D and 3-D medical imaging, particularly computed tomography (CT), is widely used for detecting lung cancer, it is associated with manual segmentation, which remains time-consuming and user-dependent. This study proposes LuCa as an innovative 2.5-D deep learning model for lung cancer delineation, which combines the benefits of 2-D segmentation with 3-D volume delineation. The main novelty of LuCa is focused on its pipeline, specifically designed to be of clinical use, in order to guarantee the usability of the method. LuCa employs a U-Net architecture for segmentation, followed by a post-image-processing step for 3-D tumor volume delineation and false-positive correction. The method was trained and evaluated using the "NSCLC-Radiomics" database, comprising CT images of 422 non-small cell lung cancer patients, with clinical manual tumor annotations as ground truth. The model achieved strong performance, with high dice coefficients (87 +/- 12%), intersection over union (81 +/- 17%), sensitivity (84 +/- 16%), and positive predictive value (94 +/- 10%) on the test set. Performance was particularly high for larger tumors, reflecting the ability of the model to delineate more visible lesions accurately. Statistical analysis confirmed the high correlation and minimal error between predicted and ground truth tumor volumes. The results highlight the potential of the 2.5-D approach to improve clinical efficiency by enabling accurate tumor segmentation with reduced computational cost, compared to traditional 3-D methods. Future research will focus on assessing the use of LuCa as real-time clinical decision support, particularly for assessing tumors during treatment.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354891

Quinidine-Induced Microvolt Electrocardiographic Alternans
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Marcantoni, Ilaria; Iammarino, Erica; Burattini, Laura
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Quinidine is a class Ia antiarrhythmic agent, but it seems also associated with an increased risk of ventricular arrhythmia and sudden death. This study aims to evaluate whether the possible risk of arrhythmia due to quinidine can be confirmed and tracked over time on electrocardiograms (ECGs) acquired on a healthy population before and within 24 hours after quinidine administration. The study population belongs to the "ECG Effects of Ranolazine, Dofetilide, Verapamil, and Quinidine in Healthy Subjects"database. The ECG analysis was performed through the enhanced correlation method (ECM) to quantify ECG alternans (ECGA), defined as beat-to-beat fluctuation of ECG wave morphology and recognized in the literature as an index of arrhythmia risk. ECM identified all forms of ECGA, thus not only T-wave alternans (TWA) as in its original formulation, but also P-wave alternans (PWA) and QRS-complex alternans (QRSA), quantified by amplitude and magnitude. The results showed that quinidine induced an increase in ECGA within 6 hours after administration, in accordance with its elimination half-life, and then returned to baseline (pre-dose) values. Depending on the ECGA form and quantification feature, the maximum increase was observed two to four times the baseline value. Furthermore, ECGA magnitude seemed to reveal transient changes better than amplitude, resulting in more post-dose time points, especially in the range 3.5-7 hours after quinidine administration, at which ECGA was statistically different than at the pre-dose time point. Thus, ECGA appears to disclose the higher risk of arrhythmia associated with quinidine.Clinical Relevance - The present study provides a contribution to guide therapy involving quinidine through the analysis of its proarrhythmic risk by electrocardiographic alternans.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354937

Development of a Sensor-Based Ecosystem for Measuring Comfort and Activities in a Multi-Resident Context: the Age-SenseAI Project
2025 IEEE International Workshop on Metrology for Living Environment, MetroLivEnv 2025 - Proceedings
Autore/i: Casaccia, Sara; Ciuffreda, Ilaria; Meletani, Sara; Caponetto, Riccardo; Monteriù, Andrea; Gambi, Ennio; Burattini, Laura; Marinelli, Luca; Revel, Gian Marco
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The aging population is rapidly growing, increasing the demand for innovative solutions to support elderly individuals while minimizing the burden on caregivers. This paper presents the Age-SenseAI project, a novel measurement ecosystem designed to monitor comfort and activities in multi-resident environments. The system integrates a network of non-invasive environmental and physiological sensors, combined with Artificial Intelligence (AI) and data fusion techniques, to assess daily activities, indoor comfort, and potential health risks. A co-design approach involving professionals was adopted to define technical requirements, ensuring compliance and ethical considerations. The proposed sensor network collects real-Time data, enabling personalized comfort assessments and detection of behaviour. Two primary use cases were developed: Activity recognition in multi-resident contexts and indoor comfort assessment, integrating both objective environmental parameters and subjective user feedback. The architecture leverages cloud-based processing and AI-driven analytics to provide real-Time insights and adaptive control mechanisms, enhancing elderly autonomy and safety. Future research will focus on improving personalization, deep learning models, and validating the ecosystem in real-world multi-resident scenarios. The Age-SenseAI project represents a significant step toward scalable, intelligent monitoring solutions for elderly care.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/347850

Electroencephalogram-derived Involvement Indexes in Sensory Processing Sensitivity
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Iammarino, Erica; Marcantoni, Ilaria; Burattini, Laura
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Sensory processing sensitivity (SPS) is a temperament trait observed in highly sensitive persons (HSPs) characterized by heightened responsiveness to environmental and social stimuli. Up to now, this condition has been assessed through the HSP scale, but the neurophysiological correlates of SPS have started to be investigated by the electroencephalogram (EEG). In this context, this study aims to investigate the role of EEG-derived involvement indexes as physiological markers for characterizing and possibly identifying HSPs, contributing to existing evidence of SPS by resting-state EEG. To do so, restingstate EEG data published by Dimulescu et al. were analyzed in EEGLAB. After preprocessing involving 0.5-80 Hz band-pass filtering, average re-referencing, and artifact removal via independent component analysis, EEG rhythms were extracted, and 37 involvement indexes were computed as the ratio of powers and/or power summations of two or more EEG rhythms. Comparisons between HSPs and non-HSPs were performed per brain rhythm using the Wilcoxon rank-sum test, setting statistical significance p to 0.05, while group differences in involvement indexes were evaluated by analysis of variance (ANOVA). A more pronounced EEG brain rhythm activity in HSPs was observed, except for the alpha rhythm that resulted to be more pronounced in the non-HSP group. As for involvement indexes, 13 indexes resulted to be statistical significant in distinguishing HSPs from non-HSPs. Our results suggest that: (1) HSPs and non-HSPs exhibit different spectral patterns in resting-state EEG; (2) EEG-derived involvement indexes, especially those defined considering both low-frequency and high-frequency oscillations, may be useful to characterize SPS. - Clinical Relevance: The present study provides electroencephalographic evidence to identify highly sensitive persons, contributing to create an objective way to recognize this temperament trait.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354938

Identifying Hypothyroidism as Complication of Type 1 Diabetes from Continuous Glucose Monitoring Data
2025 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Autore/i: Piersanti, Agnese; Callegari, Agnese; Del Giudice, Libera L.; Göbl, Christian; Burattini, Laura; Tura, Andrea; Morettini, Micaela
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Recent studies have shown that type 1 diabetes mellitus (T1DM) is an important risk factor for the development of hypothyroidism. In this regard, a timely intervention is fundamental to limit adverse effects. Providing real-time measurements of interstitial glucose, Continuous Glucose Monitoring (CGM) devices may represent a powerful source of data to feed machine-learning based algorithms for the discovery of hidden patterns related to the development of diabetes complications such as hypothyroidism. Aim of this study was to setup a machine-learning-based approach capable to identify subjects with hypothyroidism among those with T1DM, starting from CGM tracings. CGM data acquired during a period of 26 weeks and relating to 79 subjects with T1DM taken from the REPLACE-BG campaign database, of which 51 had hypothyroidism and 28 had T1DM with no other complication, were used. The CGM traces were pre-processed to handle the presence of missing data and 41 features were extracted with the use of AGATA software. The feature set was then reduced through Two-Step Decision Tree-Embedded Feature Selection (DT-EFS), leading to the inclusion of 8 final features. The best performing model was the decision tree, showing the following testing performances: area under receiver operating characteristics of 72.3%, accuracy of 71.4%, precision of 74.6%, F1 score of 70.1%, sensitivity of 71.4% and specificity of 69.5%. The 8 features identified herein describe the long-term variability of the subjects' glycemic trace which may suggests a possible connection with the presence of hypothyroidism in T1DM.Clinical Relevance-This establishes the possibility to automatically detect hypothyroidism in T1DM from clinically meaningful CGM glycemic patterns.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/350955

Availability of Open Dynamic Glycemic Data in the Field of Diabetes Research: A Scoping Review
JOURNAL OF DIABETES SCIENCE AND TECHNOLOGY
Autore/i: Del Giudice, L. L.; Piersanti, A.; Gobl, C.; Burattini, L.; Tura, A.; Morettini, M.
Classificazione: 1 Contributo su Rivista
Abstract: Background: Poor data availability and accessibility characterizing some research areas in biomedicine are still limiting potentialities for increasing knowledge and boosting technological advancement. This phenomenon also characterizes the field of diabetes research, in which glycemic data may serve as a basis for different applications. To overcome this limitation, this review aims to provide a comprehensive analysis of the publicly available data sets related to dynamic glycemic data. Methods: Search was performed in four different sources, namely scientific journals, Google, a comprehensive registry of clinical trials and two electronic databases. Retrieved data sets were analyzed in terms of their main characteristics and on the typology of data provided. Results: Twenty-five data sets were identified including data from challenge tests (5 of 25) or data from Continuous Glucose Monitoring (CGM, 20 of 25). As for the data sets including challenge tests, all of them were freely downloadable; most of them (80%) related only to oral glucose tolerance test (OGTT) with standard duration (2 h), but varying for timing and number of collected blood samples, and variables collected in addition to glucose levels (with insulin levels being the most common); the remaining 20% of them also included intravenous glucose tolerance test (IVGTT) data. As for the data sets related to CGM, 7 of 20 were freely downloadable, whereas the remaining 13 were downloadable upon completion of a request form. Conclusions: This review provided an overview of the readily usable data sets, thus representing a step forward in fostering data access in diabetes field.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/341232

Inertial Sensing for Human Motion Analysis: Enabling Sensor-to-Body Calibration Through an Anatomical and Functional Combined Approach
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
Autore/i: Scattolini, Mara; Tigrini, Andrea; Verdini, Federica; Burattini, Laura; Fioretti, Sandro; Mengarelli, Alessandro
Classificazione: 1 Contributo su Rivista
Abstract: The use of inertial measurement units is gaining attention to estimate human joint kinematics. However, to obtain clinically meaningful results, sensor frame needs to be aligned with the underlying anatomical one. Although during the years different approaches have been proposed, a common consensus has not been reached. Further, inertial sensor positioning on human segments can affect frame definition and kinematics estimation. Thus, the aim of the present work is to define an anatomical calibration procedure for lower limb joints kinematics, robust with respect to sensor misalignment, and based on a limited set of movements, with static and functional assumptions. To this purpose, straight walking and turning motor tasks in six healthy subjects were considered, and results were compared with those provided by an optoelectronic system. Three sensor placements have been also evaluated to test the procedure with respect to sensor positioning. After offset removal, an average RMSE ≤2.5 deg in gait, and ≤2 deg in turning for all the configurations were obtained, outperforming results from previous approaches. Average offset values resulted about 6 deg for hip and ankle, whereas negligible for the knee. Outcomes of this study enable a simple and accurate measurement of clinically meaningful joints kinematics, also without a strict sensor placement.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/345152

Clinically interpretable multiclass neural network for discriminating cardiac diseases
HELIYON
Autore/i: Sbrollini, A.; Leoni, C.; Morettini, M.; Swenne, C. A.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Background: Deep-learning applications in cardiology typically perform trivial binary classification and are able to discriminate between subjects affected or not affected by a specific cardiac disease. However, this working scenario is very different from the real one, where clinicians are required to recognize the occurrence of one cardiac disease among the several possible ones, performing a multiclass classification. The present work aims to create a new interpretable deep-learning tool able to perform a multiclass classification and, thus, discriminate among several different cardiac diseases. Methods: The "China Physiological Signal Challenge in 2018" Physionet database was used to develop a multiclass neural network, constructed by the Advanced Repeated Structuring & Learning Procedure (AdvRS&LP). Data, consisting of 6877 12-lead 10-second electrocardiograms, was processed to obtain 252 electrocardiographic and vectorcardiographic input features, used to classify the data into eight classes (normal sinus rhythm, atrial fibrillation, first-degree atrioventricular block, left bundle branch block, right bundle branch block, premature atrial contraction, premature ventricular contraction, and unknown). Classification performance was evaluated by the area under the curve of the receiver operating characteristics. Clinical interpretability was assessed by standard statistical analysis and the local interpretable model-agnostic explainer algorithm. Results: Performance ranged from 89.88% to 90.10% (95.98 ± 3.32%) in the learning dataset and from 69.15% to 91.14% (83.65 ± 8.24%) in the testing dataset. These results are good considering the difficult, realistic multiclass classification task. Conclusions: The proposed multiclass neural network constructed using the AdvRS&LP represents a promising deep-learning tool for discriminating several cardiac diseases while ensuring clinical interpretability.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354890

Role of pre-exercise CGM metrics on hypoglycemic events in young patients with type 1 diabetes
IL DIABETE
Autore/i: Piersanti, Agnese; Del Giudice, Libera Lucia; Göbl, Christian; Burattini, Laura; Tura, Andrea; Morettini, Micaela
Classificazione: 1 Contributo su Rivista
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/337440

Exercise effect on insulin sensitivity: model-based and data-driven quantification from OGTT
IL DIABETE
Autore/i: Del Giudice, Libera Lucia; Piersanti, Agnese; Burattini, Laura; Tura, Andrea; Morettini, Micaela
Classificazione: 1 Contributo su Rivista
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/337441

NSCLC-Pro ClustAI: A Machine Learning Model to prognostically stratify patients with advanced NSCLC treated with immune checkpoint inhibitors
ESMO OPEN
Autore/i: Cognigni, V.; Pecci, F.; Bruschi, G.; Sbrollini, A.; Paoloni, F.; Galassi, T.; Cantini, L.; Santamaria, L.; Gualtieri, M.; Lunerti, V.; Villani, S.; Savino, F. D.; Ambrosini, E.; Chiodi, N.; Agostinelli, V.; Mentrasti, G.; Burattini, L.; Berardi, R.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/331354

85P NSCLC-Pro ClustAI: A machine learning model to prognostically stratify patients with advanced NSCLC treated with immune checkpoint inhibitors
ESMO OPEN
Autore/i: Cognigni, V.; Pecci, F.; Bruschi, G.; Sbrollini, A.; Paoloni, F.; Galassi, T.; Cantini, L.; Santamaria, L.; Gualtieri, M.; Lunerti, V.; Villani, S.; Savino, F. D.; Ambrosini, E.; Chiodi, N.; Agostinelli, V.; Mentrasti, G.; Burattini, L.; Berardi, R.
Classificazione: 1 Contributo su Rivista
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/331271

On the Feasibility of Locating Myocardial Bridge though the 12-Lead Electrocardiogram: a Case Study
Computing in Cardiology
Autore/i: Mortada, J.; Sbrollini, A.; Van Dam, P.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Myocardial bridge (MB) is a coronary artery variation where the artery tunnels through the myocardium rather than running on its surface, potentially causing ischemia and sudden cardiac death. Locating MB typically requires various imaging modalities, making widespread screening impractical. Consequently, clinical tests are usually performed after symptoms occur. We aimed to explore the feasibility of using a 12-lead electrocardiogram (ECG) to detect and locate MB by utilizing a 12-lead Holter ECG from a male patient with MB proximal to the anterior descending branch of the left coronary artery, as assessed via echocardiography. Additionally, a synthetic 12-lead ECG simulating the presence of ischemia in the same location and normal sinus rhythm, respectively, was used to feed CineECG, which processes the 12-lead ECG to generate a video where a moving vector represents the average electrical activation sequence in the heart. Visual inspection of the CineECG images indicated that, in correspondence with the ST segment, typically displaced in case of ischemia, the vector pointed towards the left anterior wall and septum rather than towards the heart apex, as observed in the normal resting ECG, suggesting that CineECG can detect ischemic-like changes associated with MB, appears to be a promising method for detecting and locating MB.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354881

Minimalist Approach to 3-D Heart Modeling: A Novel Morphing Algorithm Relying on Four Anatomical Landmarks
Computing in Cardiology
Autore/i: Mortada, J.; Sbrollini, A.; Burattini, L.; Van Dam, P.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Computer heart modeling serves as a pivotal tool across diverse disciplines, facilitating the interpretation of electrical and mechanical information. The process of generating accurate patient-specific 3D heart model poses significant challenges, demanding time, expertise, and computational resources as established by both manual and artificial intelligent and deep-learning driven methods. In this paper, we introduce a novel morphing algorithm for generating 3D heart models with minimal input. By pinpointing four key anatomical landmarks which are the heart apex and the centers of the Mitral, Pulmonary, and Tricuspid valves - our approach leverages a template model for the ventricles. This algorithm scales the ventricles of the heart along their primary axes and aligns them using translation and rotation based on the landmark locations. It was tested on a dataset of 94 models revealing promising outcomes, both visually and quantitatively. Specifically, the median percentage error in the estimation of endocardial left volume and of endocardial right volume are lower than 13% and 6%, respectively. Importantly, our method offers a rapid, efficient alternative, making it accessible to a broader range of users which would open the way for a new modeling method that is fast and might satisfy the need in inverse ECG applications.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354886

Interhemispheric functional connectivity: an fMRI study in callosotomized patients
FRONTIERS IN HUMAN NEUROSCIENCE
Autore/i: Marcantoni, Ilaria; Piccolantonio, Giusi; Ghoushi, Mojgan; Valenti, Marco; Reversi, Luca; Mariotti, Francesco; Foschi, Nicoletta; Lattanzi, Simona; Burattini, Laura; Fabri, Mara; Polonara, Gabriele
Classificazione: 1 Contributo su Rivista
Abstract: Introduction: Functional connectivity (FC) is defined in terms of temporal correlations between physiological signals, which mainly depend upon structural (axonal) connectivity; it is commonly studied using functional magnetic resonance imaging (fMRI). Interhemispheric FC appears mostly supported by the corpus callosum (CC), although several studies investigating this aspect have not provided conclusive evidence. In this context, patients in whom the CC was resected for therapeutic reasons (split-brain patients) provide a unique opportunity for research into this issue. The present study was aimed at investigating with resting-state fMRI the interhemispheric FC in six epileptic patients who have undergone surgical resection of the CC. Methods: The analysis was performed using fMRI of the Brain Software Library; the evaluation of interhemispheric FC and the recognition of the resting-state networks (RSNs) were performed using probabilistic independent component analysis. Results: Generally, bilateral brain activation was often observed in primary sensory RSNs, while in the associative areas, such as those composing the default mode and fronto-parietal networks, the activation was often unilateral. Discussion: These results suggest that even in the absence of the CC, some interhemispheric communication is still present. This residual FC might be supported through extra-callosal pathways that are likely subcortical, making it possible for some interhemispheric integration. Further studies are needed to confirm these conclusions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/329836

Mapping Lower Limb EMG Activity to Ground Reaction Force in Free Walking Condition
2024 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2024 - Proceedings
Autore/i: Mengarelli, A.; Scattolini, M.; Mobarak, R.; Verdini, F.; Fioretti, S.; Burattini, L.; Tigrini, A.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Continuous control of lower limb prosthetic and assistive devices is usually performed by mapping electromyography (EMG) activity to joints angular kinematics. However, the inclusion of ground reaction force information within the regulation scheme would be valuable in order to provide a more physiological walking mechanics, thus enhancing patient comfort and usability in real context scenarios. In this paper, we explored the feasibility of a reliable EMG-based estimation of the vertical ground reaction force (VGRF) component during unconstrained walking. The EMG activity from six lower limb muscles was recorded from five healthy subjects who performed four gait trials, and the VGRF was recorded during the stance phase of gait by dynamometric plates. As a regression model, we relied on a LSTM network. Results showed very promising performances for VGRF estimation, without any drop between training and testing (R2 of about 0.90, and a RMSE of 8.7%). The three thigh muscles failed in providing reliable results (R2 <0.7 and RMSE>14%), whereas shank muscles alone provided no significantly different outcomes with respect to using all the muscles, pointing out the possibility of using a reduced EMG recording setup, thus impacting on actual usability. These findings can be considered as a step toward the inclusion of dynamics information in myoelectric volitional control schemes for enhancing movement reconstruction.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/333732

Leveraging Inertial Information from a Single IMU for Human Daily Activity Recognition
2024 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2024 - Proceedings
Autore/i: Scattolini, M.; Tigrini, A.; Verdini, F.; Iadarola, G.; Spinsante, S.; Fioretti, S.; Burattini, L.; Mengarelli, A.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Being able to recognize human activities is important for home monitoring, with the possibility for clinicians to early recognize possible cognitive or physical impairments, but also for rehabilitation and prosthetics control. Nowadays, with the diffusion of wearable devices embedding inertial sensors (IMU) in the market, e.g. bracelets or smartwatches, the attention is moved toward the possibility to automatically recognize daily activities just from this sensor information, including accelerometer and gyroscope. However, the majorities of the studies consider a small set of simple daily activities or high computationally demand models to recognize the chosen tasks. For this reason, the aim of the present study is to consider three shallow machine learning classifiers to recognize 17 different complex activities just from the inertial information of a myo armband, i.e. accelerometer, gyroscope and quaternions. The best performance was reached combining accelerometer and gyroscope features with an accuracy of 98.6% and a LDA model. On the other hand, the KNN seemed to be the most suitable classifier when dealing with quaternion information: accuracy equal to 80% was obtained against 75% of LDA and SVM. Obtained results outperformed classification performances present in the literature, highlighting also a possible role of quaternions for pattern recognition problems.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/333734

Using Adaptive Surface EMG Envelope Extraction for Onset Detection: A Preliminary Study on Upper Limb Amputees
2024 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2024 - Proceedings
Autore/i: Ranaldi, S.; Tigrini, A.; Al-Timemy, A. H.; Verdini, F.; Mengarelli, A.; Schmid, M.; Fioretti, S.; Burattini, L.; Conforto, S.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Surface electromyography is a valid and widely used tool for the characterization and the intention of human movement in healthy and pathological subjects; in particular, the thorough identification of the transient phase of EMG activity is an important problem to be solved for both myoelectric control applications for prosthetics and rehabilitation and in movement analysis in general. Among the possible algorithmic solutions, the ones based on the statistical properties of the signal have been considered able to yield stable performance in a variety of different scenarios. In this paper, an adaptive and statistically optimised algorithm for the extraction of the amplitude envelope is exploited for the onset detection from EMG data coming from the shoulder muscles of two upper limb amputees. In particular, onset events have been detected from the optimised point-by-point window length of the adaptive filter, as the instants in which this time series reaches a local minimum, and compared with those coming from visual inspection of accelerometer data from the shoulder. These preliminary results show how using such techniques can yield acceptable performance, supporting the hypothesis of exploiting such an algorithm for the improvement of the performance of myoelectric control algorithms to be applied in clinical contexts.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/333735

HIKE: A COMPOSITE METRIC FOR HYPOGLYCEMIA RISK IN EXERCISE UNDER CONTROLLED CONDITIONS
DIABETES TECHNOLOGY & THERAPEUTICS
Autore/i: Piersanti, A; Salvatori, B; Gobl, C; Burattini, L; Tura, A; Morettini, M
Classificazione: 1 Contributo su Rivista
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354815

HEMODIALYSIS-INDUCED HYPOGLYCEMIA: A MACHINE-LEARNING APPROACH BASED ON CONTINUOUS GLUCOSE MONITORING METRICS TO UNDERSTAND THE RISK FOR UPCOMING EVENTS
DIABETES TECHNOLOGY & THERAPEUTICS
Autore/i: Piersanti, A; Morettini, M; Salvatori, B; Göbl, C; Burattini, L; Cristino, S; Mosconi, G; Mambelli, E; Tura, A
Classificazione: 1 Contributo su Rivista
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354816

Diabetic Retinopathy Detection: A Machine-Learning Approach Based on Continuous Glucose Monitoring Metrics
Advances in Digital Health and Medical Bioengineering
Autore/i: Piersanti, A; Salvatori, B; D'Avino, P; Burattini, L; Göbl, C; Tura, A; Morettini, M
Editore: SPRINGER INTERNATIONAL PUBLISHING AG
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Diabetic Retinopathy (DR) is an extremely common complication of diabetes mellitus (DM) and a timely treatment may decelerate its progression before the occurrence of irreversible vision loss. Machine learning (ML) represents a powerful tool for addressing the massive screening burden, nowadays performed with the time consuming and operator dependent analysis of fundus photography. Continuous glucose monitoring (CGM) are wearable devices whose information could be exploited also in real-time. This study aimed to explore the potential of CGM and ML for DR detection. A classification task was pursued to identify DR class (n = 50) from the non-DR class (NDR, n = 28) based on data from anthropometric characteristics and extracted CGM metrics. Among the tested models, Logistic Regression achieved the best performances (72.7% of classification accuracy), with a balanced number of misclassifications accounting for less than 30% of misclassified cases. The approach could be suitable for real-time applications.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/337436

The Prognostic Value of Electrocardiographic Alternans in the Primary Prevention on Patients Having an Implantable Cardioverter Defibrillator
2024 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2024 - Proceedings
Autore/i: Iammarino, Erica; Marcantoni, Ilaria; Sbrollini, Agnese; Morettini, Micaela; Swenne, Cees A.; Burattini, Laura
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Primary prevention therapy with implantable cardioverter defibrillator (ICD) may benefit in specificity evaluating the left ventricular ejection fraction together with other electrocardiogram (ECG)-derived cardiac risk indexes, such as ECG alternans (ECGA). ECGA, the ABAB morphology fluctuation of ECG waves (P wave/QRS complex/T wave), results in P-wave/QRS/T-wave alternans (PWA/QRSA/TWA). This work aims to validate ECGA prognostic value on ECGs acquired from ICD patients (Leiden University Medical Center Database). Thus, 82 controls (ICD therapy was not needed) and 40 cases (ICD therapy was needed) were enrolled. ECGA was analyzed by the enhanced adaptive matched filter method at rest and exercise. Median ECGA features (amplitude-Am, duration-D, area-Ar, magnitude-M) were computed over leads and ICD groups. ECGA ability to discriminate between ICD groups was evaluated by the area under the curve (AUC) of the receiver operating characteristic curve. Precordial leads allowed a better discrimination than all leads (higher AUC). QRSA, at both rest (controls/cases: Am=5/10 μV, D=33/45 beats, Ar=360/760 μV·ms, M=351/603 μV·beats) and exercise (controls/cases: Am=16/20 μV, D=55/57 beats, Ar=1280/1600 μV·ms, M=992/1316 μV·beats) has the best discriminant power, with AUC values higher than 0.7 at rest. ECGA feature normalization by the ECG mean amplitude was also considered. We can conclude that (1) ECGA predictive power is best expressed at rest, and QRSA seems to be the best ECGA form to identify patients who should benefit from primary prevention ICD therapy, (2) normalization seems not to improve our results.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/334092

Automatic Handwriting Recognition with a Minimal EMG Electrodes Setup: A Preliminary Investigation
2024 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2024 - Proceedings
Autore/i: Tigrini, A.; Ranaldi, S.; Mengarelli, A.; Verdini, F.; Scattolini, M.; Mobarak, R.; Fioretti, S.; Conforto, S.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Electromyographic (EMG)-based human-machine interfaces showed great potential in hand gesture recognition and recently they have been developed for realizing automatic recognition of handwritten characters or digits. Although smart sensors were commercialized for the forearm, the optimal electrode configuration for high accuracy with minimal channels remains debated. A total of six healthy subjects were asked to write a set of thirty common words of the english vocabulary while EMG signals from forearm and wrist were acquired to perform handwriting recognition using five state of the art feature sets and three pattern recognition models, i.e., K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM). Among the three classifiers the KNN outperformed both LDA and SVM showing a mean accuracy of 71.4% and 96.5 % respectively without and with majority voting post-processor when using combined forearm and wrist EMG information. On the other hand, using only wrist electrodes showed significantly performance drop in all classifiers with accuracy lower than 30.0%. Hence, combining forearm and wrist EMG data is crucial for accurate handwriting recognition with sparse electrode configurations, and limiting the sensing area to the wrist alone may not be sufficient for complex myoelectric decoding tasks. Further research is needed to explore alternative feature sets to improve performance with limited electrode setups.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/333736

Enhanced Gait Phases Recognition by EMG and Kinematics Information Fusion and a Minimal Recording Setup
AL-KHWARIZMI ENGINEERING JOURNAL
Autore/i: Mobarak, Rami; Mengarelli, Alessandro; Verdini, Federica; Fioretti, Sandro; Burattini, Laura; Tigrini, Andrea
Classificazione: 1 Contributo su Rivista
Abstract: The limited mobility of lower limb amputees highlights the need for advancements in prosthetic control strategies to restore natural locomotion. This paper proposes an information fusion approach for gait phase recognition using surface electromyography (sEMG) and kinematics data. Time-domain (TD) features were extracted from the myoelectric data and three data-driven models, specifically Support Vector Machine (SVM), K-Nearest Neighbours (KNN), and Artificial Neural Network (ANN), were compared in three different input conditions i.e. sEMG features, hip angle, and their fusion. Gait phase estimation results averaged from 40 healthy participants during normal walking with 10 strides per each demonstrated that the proposed fusion approach has consistently outperformed (p<0.0001) the other two conditions achieving a maximum accuracy of 85.48% with SVM. The findings suggest promising applications in prosthetic motion control and rehabilitative exoskeletons, highlighting the potential for improved user-driven strategies in lower limb prostheses.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/331239

Individual Estimation of Parameters Describing the Glucose-Insulin Regulatory System: A Modeling Approach with Regularization for Reduced-Sampling Oral Glucose Tolerance Test Data
Advances in Digital Health and Medical Bioengineering
Autore/i: Del Giudice, Ll; Piersanti, A; Burattini, L; Tura, A; Morettini, M
Editore: SPRINGER INTERNATIONAL PUBLISHING AG
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: A recent modeling approach of the glucose-insulin regulatory system exploits a regularization procedure to allow estimation of model parameters from a 5-samples oral glucose tolerance test (OGTT). However, the complexity of the regularization procedure may limit its applicability; in addition, a considerable number of OGTT presents only 4 time samples rather than 5. Thus, leveraging such a glucose-insulin system model, the objective of the present work was to simplify the regularization procedure and to adapt the model approach to the case of 4-samples OGTT. Simplifying regularization involved minimizing the sum of squared residuals, in conjunction with applying appropriate weights (w1, w2) to the second derivatives of glucose and insulin vectors. Validation of the approach was conducted using both 5-samples and 4-samples OGTTs. In the case of the 4-sample OGTT, the available data did not provide sufficient information to estimate all 13 parameters, thus the number of parameters was reduced to 9. For the remaining four parameters, two sets of values were derived from 10 and 11-samples OGTTs. The selection between the two options was based on which one provided estimates closer to physiological values. Ultimately, the validation of the suggested approach was carried out for protocols with 4 and 5-samples OGTTs, employing appropriate weights, i.e., w1 = 2 and w2 = 0.0100, and w1 = 0.0680 and w2 = 0.0015, respectively. The obtained results yielded a root mean square error of 1.0258 and 1.3062, respectively.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/337435

Glucagon-like peptide-1 and interleukin-6 interaction in response to physical exercise: An in-silico model in the framework of immunometabolism
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
Autore/i: Morettini, M.; Palumbo, M. C.; Bottiglione, A.; Danieli, A.; Del Giudice, S.; Burattini, L.; Tura, A.
Classificazione: 1 Contributo su Rivista
Abstract: Background and objective: Glucagon-like peptide 1 (GLP-1) is classically identified as an incretin hormone, secreted in response to nutrient ingestion and able to enhance glucose-stimulated insulin secretion. However, other stimuli, such as physical exercise, may enhance GLP-1 plasma levels, and this exercise-induced GLP-1 secretion is mediated by interleukin-6 (IL-6), a cytokine secreted by contracting skeletal muscle. The aim of the study is to propose a mathematical model of IL-6-induced GLP-1 secretion and kinetics in response to physical exercise of moderate intensity. Methods: The model includes the GLP-1 subsystem (with two pools: gut and plasma) and the IL-6 subsystem (again with two pools: skeletal muscle and plasma); it provides a parameter of possible clinical relevance representing the sensitivity of GLP-1 to IL-6 (k0). The model was validated on mean IL-6 and GLP-1 data derived from the scientific literature and on a total of 100 virtual subjects. Results: Model validation provided mean residuals between 0.0051 and 0.5493 pg⋅mL-1 for IL-6 (in view of concentration values ranging from 0.8405 to 3.9718 pg⋅mL-1) and between 0.0133 and 4.1540 pmol⋅L-1 for GLP-1 (in view of concentration values ranging from 0.9387 to 17.9714 pmol⋅L-1); a positive significant linear correlation (r = 0.85, p<0.001) was found between k0 and the ratio between areas under GLP-1 and IL-6 curve, over the virtual subjects. Conclusions: The model accurately captures IL-6-induced GLP-1 kinetics in response to physical exercise.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/326556

Neuromechanical-Driven Ankle Angular Position Control during Gait Using Minimal Setup and LSTM Model
2024 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2024 - Proceedings
Autore/i: Mobarak, R.; Mengarelli, A.; Verdini, F.; Al-Timemy, A. H.; Fioretti, S.; Burattini, L.; Tigrini, A.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Data-driven decoding of lower limb muscles surface electromyography (sEMG) and joints kinematics is a crucial approach for enhancing prosthetic control and assistive reha-bilitation. In this study, three different neuromechanical-driven ankle angle estimation strategies were investigated, i.e. Least Squares - Support Vector Machine (LS-SVM) fed with Time Domain (TD) features, single hidden layer Long Short Term Memory (1HL-LSTM) deep learning model fed within the same features, and 2 hidden layers LSTM (2HL-LSTM) fed with a sequence of raw data windows. The above mentioned schemes were tested with three myoelectric-mechanical combinations, i.e. three thigh muscles (3M), their fusion with hip joint angle (3M+Hip), and Biceps Femoris muscle with the hip (BF+Hip). A combined TD features with 1HL-LSTM has outperformed the other two models in all three input combinations, with an RMSE equal to 2.18 ± 0.44 deg in the case of BF+Hip as input, that appeared to be the best muscles configuration. The results of this study provide a robust ankle angle estimation strategy while preventing the computational cost from being drastically increased. They also highlight the reliability of the BF + Hip combination, thus representing a further step in the advancement of effective control strategies for active ankle prosthesis and rehabilitative devices.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/333737

Computerized otoscopy image-based artificial intelligence model utilizing deep features provided by vision transformer, grid search optimization, and support vector machine for otitis media diagnosis
NEURAL COMPUTING & APPLICATIONS
Autore/i: Cömert, Zafer; Sbrollini, Agnese; Demircan, Furkancan; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Otitis media (OM) is an inflammation of the middle ear, often associated with fluid accumulation and characterized by symptoms such as ear pain, fever, and impaired hearing. Timely and accurate diagnosis of OM is essential to facilitate prompt treatment and mitigate the risk of complications such as hearing loss or chronic infection, particularly in regions with limited access to healthcare professionals. In this study, we introduce an advanced computational model for automated OM diagnosis, utilizing the vision transformer (ViT) architecture to extract highly discriminative features from otoscope images. The proposed approach employs a grid search optimization algorithm in combination with a support vector machine (SVM) classifier to accurately recognize different types of OM based on deep feature representations. All experiments were conducted using a publicly accessible Ear Imagery dataset containing 880 otoscope images, categorized into four distinct classes. As a result, the proposed model demonstrated remarkable efficacy, achieving an impressive accuracy rate of 99.37%. It successfully classified all OM types. At its core, the emergence of advanced computational models in healthcare represents a transformative leap that promises to close gaps in access to medical expertise and revolutionize diagnostic practices. Harnessing the power of machine learning and leveraging vast datasets, these models offer unprecedented accuracy and efficiency, paving the way for early intervention and improving patient outcomes on a global scale.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/338832

A Minimal and Multi-Source Recording Setup for Ankle Joint Kinematics Estimation During Walking Using Only Proximal Information From Lower Limb
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
Autore/i: Mobarak, R.; Tigrini, A.; Verdini, F.; Al-Timemy, A. H.; Fioretti, S.; Burattini, L.; Mengarelli, A.
Classificazione: 1 Contributo su Rivista
Abstract: In this study, a minimal setup for the ankle joint kinematics estimation is proposed relying only on proximal information of the lower-limb, i.e. thigh muscles activity and joint kinematics. To this purpose, myoelectric activity of Rectus Femoris (RF), Biceps Femoris (BF), and Vastus Medialis (VM) were recorded by surface electromyography (sEMG) from six healthy subjects during unconstrained walking task. For each subject, the angular kinematics of hip and ankle joints were synchronously recorded with sEMG signal for a total of 288 gait cycles. Two feature sets were extracted from sEMG signals, i.e. time domain (TD) and wavelet (WT) and compared to have a compromise between the reliability and computational capacity, they were used for feeding three regression models, i.e. Artificial Neural Networks, Random Forest, and Least Squares - Support Vector Machine (LS-SVM). BF together with LS-SVM provided the best ankle angle estimation in both TD and WT domains (RMSE < 5.6 deg). The inclusion of Hip joint trajectory significantly enhanced the regression performances of the model (RMSE < 4.5 deg). Results showed the feasibility of estimating the ankle trajectory using only proximal and limited information from the lower limb which would maximize a potential transfemoral amputee user's comfortability while facing the challenge of having a small amount of information thus requiring robust data-driven models. These findings represent a significant step towards the development of a minimal setup useful for the control design of ankle active prosthetics and rehabilitative solutions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/327112

Acquisition Devices for Fetal Phonocardiography: A Scoping Review
BIOENGINEERING
Autore/i: Giordano, N.; Sbrollini, A.; Morettini, M.; Rosati, S.; Balestra, G.; Gambi, E.; Knaflitz, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Timely and reliable fetal monitoring is crucial to prevent adverse events during pregnancy and delivery. Fetal phonocardiography, i.e., the recording of fetal heart sounds, is emerging as a novel possibility to monitor fetal health status. Indeed, due to its passive nature and its noninvasiveness, the technique is suitable for long-term monitoring and for telemonitoring applications. Despite the high share of literature focusing on signal processing, no previous work has reviewed the technological hardware solutions devoted to the recording of fetal heart sounds. Thus, the aim of this scoping review is to collect information regarding the acquisition devices for fetal phonocardiography (FPCG), focusing on technical specifications and clinical use. Overall, PRISMA-guidelines-based analysis selected 57 studies that described 26 research prototypes and eight commercial devices for FPCG acquisition. Results of our review study reveal that no commercial devices were designed for fetal-specific purposes, that the latest advances involve the use of multiple microphones and sensors, and that no quantitative validation was usually performed. By highlighting the past and future trends and the most relevant innovations from both a technical and clinical perspective, this review will represent a useful reference for the evaluation of different acquisition devices and for the development of new FPCG-based systems for fetal monitoring.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/330095

Unveiling Muscular Engagement: Evidence of Activity in Mental Imagery and Action Observation
2024 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2024 - Proceedings
Autore/i: Verdini, F.; Capecci, M.; Tigrini, A.; Scattolini, M.; Mobarak, R.; Burattini, L.; Fioretti, S.; Benedetti, M. G.; Ceravolo, M. G.; Mengarelli, A.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The cognitive processes associated with the move-ment representation in the absence of physical execution, specif-ically motor imagery (MI), or with the action observation (AO), have been extensively investigated to understand how these activities can affect the endurance and the physical strength. The observed improvements of the motor performance have been attributed not only to the modifications in the central motor program but also to changes in the peripheral neuronal and musculoskeletal systems. Despite these efforts, capturing these effects has proven challenging, with inconsistent results obtained when analyzing electromyographic activity (EMG). This study aims to explore distinctive myoelectric patterns during MI and AO tasks, contrasting them with baseline patterns associated with a resting condition. Eight healthy subjects participated in imagining and observing a fine motor task involving hand and arm. Surface EMG signals from Opponens Pollicis, Flexor Radialis Carpi and Biceps Brachialis were analyzed for both experimental conditions and compared with signals obtained during rest (REST). Features in the time and the time-frequency domains were computed and two their subsets, resulting statisti-cally different for MI and for AO, in comparison to REST, were selected. These features were then inputted into three shallow machine learning models (KNN, SVM, and LDA) to assess the consistency of muscular engagements. The KNN classifier demonstrated the best performance in terms of accuracy (87 %) for MI vs REST, utilizing a subset of features exclusively defined in the time-domain. To capture muscular activity during AO, a more comprehensive feature subset, including some time-frequency features, was required to KNN to reach an accuracy of 89%.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/333733

Myoelectric-Based Estimation of Vertical Ground Reaction Force During Unconstrained Walking by a Stacked One-Dimensional Convolutional Long Short-Term Memory Model
SENSORS
Autore/i: Mengarelli, A.; Tigrini, A.; Scattolini, M.; Mobarak, R.; Burattini, L.; Fioretti, S.; Verdini, F.
Classificazione: 1 Contributo su Rivista
Abstract: The volitional control of powered assistive devices is commonly performed by mapping the electromyographic (EMG) activity of the lower limb to joints’ angular kinematics, which are then used as the input for regulation. However, during walking, the ground reaction force (GRF) plays a central role in the modulation of the gait, providing dynamic stability and propulsion during the stance phase. Including this information within the control loop of prosthetic devices can improve the quality of the final output, providing more physiological walking dynamics that enhances the usability and patient comfort. In this work, we explored the feasibility of the estimation of the ground reaction force vertical component (VGRF) by using only the EMG activities of the thigh and shank muscles. We compared two deep learning models in three experiments that involved different muscular configurations. Overall, the outcomes show that the EMG signals could be leveraged to obtain a reliable estimation of the VGRF during walking, and the shank muscles alone represent a viable solution if a reduced recording setup is needed. On the other hand, the thigh muscles failed in providing performance enhancements, either when used alone or together with the shank muscles. The results outline the feasibility of including GRF information within an EMG-driven control scheme for prosthetic and assistive devices.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/338317

Quantification of the Individual Effect of an Exercise Bout on Insulin Sensitivity: In-Silico Modeling and Linear Regression Combined to Reduce Sampling Protocol Requirements
2024 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2024: Proceedings
Autore/i: Del Giudice, L. L.; Piersanti, A.; Burattini, L.; Tura, A.; Morettini, M.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Exercise modulates metabolism by also acting on insulin sensitivity, being the biological response to insulin stimulation of target tissues. Among the available methods for insulin sensitivity quantification, an option is represented by mathematical-model interpretation of data from dynamic tests (i.e. administration of a glucose challenge). When using such methods, the requirements in terms of data samples in relation to the model characteristics are critical. Thus, starting from a modeling approach previously proposed in the literature to interpret data from oral glucose tolerance test (OGTT), the aim of this study was to provide a simplified procedure for a reliable (model-based) quantification of the effect of an exercise bout on insulin sensitivity without the need to repeat the full test, as the modelling approach otherwise would require. A mathematical model comprising five differential equations was exploited to estimate 13 unknown parameters, with a particular focus on the parameter kxgi, representing insulin sensitivity. The parameter kxgi and other indexes of insulin sensitivity (Matsuda, Cederholm, Stumvoll, OGIS120 and PREDIM) were assessed in a group of ten men who underwent a 75-gram OGTT before and after an exercise bout. Then, Pearson correlation coefficients were calculated between kxgi percentage changes before and after exercise and change in each of the other indexes, revealing Stumvoll as the most strongly correlated (ρ=0.83). Consequently, a linear regression model was set up to estimate kxgi after exercise from changes in the Stumvoll index (β0=-7.1062, β1=14.6745 for coefficients of the linear regression), thus eliminating the need of two full-protocol OGTT tests.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/334032

Scalp Electroencephalogram-Derived Involvement Indexes during a Working Memory Task Performed by Patients with Epilepsy
SENSORS
Autore/i: Iammarino, Erica; Marcantoni, Ilaria; Sbrollini, Agnese; Mortada, MHD Jafar; Morettini, Micaela; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Electroencephalography (EEG) wearable devices are particularly suitable for monitoring a subject’s engagement while performing daily cognitive tasks. EEG information provided by wearable devices varies with the location of the electrodes, the suitable location of which can be obtained using standard multi-channel EEG recorders. Cognitive engagement can be assessed during working memory (WM) tasks, testing the mental ability to process information over a short period of time. WM could be impaired in patients with epilepsy. This study aims to evaluate the cognitive engagement of nine patients with epilepsy, coming from a public dataset by Boran et al., during a verbal WM task and to identify the most suitable location of the electrodes for this purpose. Cognitive engagement was evaluated by computing 37 engagement indexes based on the ratio of two or more EEG rhythms assessed by their spectral power. Results show that involvement index trends follow changes in cognitive engagement elicited by the WM task, and, overall, most changes appear most pronounced in the frontal regions, as observed in healthy subjects. Therefore, involvement indexes can reflect cognitive status changes, and frontal regions seem to be the ones to focus on when designing a wearable mental involvement monitoring EEG system, both in physiological and epileptic conditions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/334072

Identification of Electrocardiographic Patterns Related to Mortality with COVID-19
APPLIED SCIENCES
Autore/i: Sbrollini, Agnese; Leoni, Chiara; Morettini, Micaela; Rivolta, Massimo W.; Swenne, Cees A.; Mainardi, Luca; Burattini, Laura; Sassi, Roberto
Classificazione: 1 Contributo su Rivista
Abstract: COVID-19 is an infectious disease that has greatly affected worldwide healthcare systems, due to the high number of cases and deaths. As COVID-19 patients may develop cardiac comorbidities that can be potentially fatal, electrocardiographic monitoring can be crucial. This work aims to identify electrocardiographic and vectorcardiographic patterns that may be related to mortality in COVID-19, with the application of the Advanced Repeated Structuring and Learning Procedure (AdvRS&LP). The procedure was applied to data from the "automatic computation of cardiovascular arrhythmic risk from electrocardiographic data of COVID-19 patients" (COVIDSQUARED) project to obtain neural networks (NNs) that, through 254 electrocardiographic and vectorcardiographic features, could discriminate between COVID-19 survivors and deaths. The NNs were validated by a five-fold cross-validation procedure and assessed in terms of the area under the curve (AUC) of the receiver operating characteristic. The features' contribution to the classification was evaluated through the Local-Interpretable Model-Agnostic Explanations (LIME) algorithm. The obtained NNs properly discriminated between COVID-19 survivors and deaths (AUC = 84.31 +/- 2.58% on hold-out testing datasets); the classification was mainly affected by the electrocardiographic-interval-related features, thus suggesting that changes in the duration of cardiac electrical activity might be related to mortality in COVID-19 cases.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/334213

Intelligent Human–Computer Interaction: Combined Wrist and Forearm Myoelectric Signals for Handwriting Recognition
BIOENGINEERING
Autore/i: Tigrini, A.; Ranaldi, S.; Verdini, F.; Mobarak, R.; Scattolini, M.; Conforto, S.; Schmid, M.; Burattini, L.; Gambi, E.; Fioretti, S.; Mengarelli, A.
Classificazione: 1 Contributo su Rivista
Abstract: Recent studies have highlighted the possibility of using surface electromyographic (EMG) signals to develop human–computer interfaces that are also able to recognize complex motor tasks involving the hand as the handwriting of digits. However, the automatic recognition of words from EMG information has not yet been studied. The aim of this study is to investigate the feasibility of using combined forearm and wrist EMG probes for solving the handwriting recognition problem of 30 words with consolidated machine-learning techniques and aggregating state-of-the-art features extracted in the time and frequency domains. Six healthy subjects, three females and three males aged between 25 and 40 years, were recruited for the study. Two tests in pattern recognition were conducted to assess the possibility of classifying fine hand movements through EMG signals. The first test was designed to assess the feasibility of using consolidated myoelectric control technology with shallow machine-learning methods in the field of handwriting detection. The second test was implemented to assess if specific feature extraction schemes can guarantee high performances with limited complexity of the processing pipeline. Among support vector machine, linear discriminant analysis, and K-nearest neighbours (KNN), the last one showed the best classification performances in the 30-word classification problem, with a mean accuracy of 95% and 85% when using all the features and a specific feature set known as TDAR, respectively. The obtained results confirmed the validity of using combined wrist and forearm EMG data for intelligent handwriting recognition through pattern recognition approaches in real scenarios.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/331152

Feature Engineering Assessment of Tumor Infiltrating Lymphocytes in Lung Adenocarcinoma
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Bruschi, G.; Sbrollini, A.; Pecci, F.; Cognigni, V.; Paoloni, F.; Galassi, T.; Cantini, L.; Morettini, M.; Berardi, R.; Burattini, L.
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Tumor-Infiltrating Lymphocytes (TIL) are emerging as immunotherapy prognostic markers. Currently, TIL are assessed on hematoxylin and eosin (H&E)-stained slides of tumor tissue by pathologists. This approach is time-consuming, and subjected to inter-observer variability. The aim of this study is to propose a machine learning-based algorithm, called Feature Engineering TIL Assessment (FTA), for the automatic TIL assessment by using adenocarcinoma metadata (i.e., anamnestic, clinical and pathological data). The algorithm is an Elastic Net, tuned by Bayesian Optimization and validated by Leave-One-Subject-Out cross validation. Obtained coefficients were used for feature ranking. Results confirms the goodness of performance of FTA, with an overall Mean Absolute Error of 2.1%, Concordance Correlation Coefficient equal to 0.71 and difference in the Bland- Altman plot equal to -0.001. The obtained feature ranking revealed the key role of gender, as confirmed by the clinical literature. In conclusion, FTA is the first image-independent automatic TIL assessment procedure, having the potential to address challenges associated with inter-observer variability and the time-consuming nature of classical procedures.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354883

Selection of Dataframes Presenting Glioma from Magnetic Resonance Images: A Deep Learning Approach
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Bruschi, G.; Vassallo, F.; Sbrollini, A.; Morettini, M.; Burattini, L.
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Due to its complexity and time-consuming nature, identifying gliomas at the Magnetic Resonance Imaging (MRI) slice-level before segmentation could assist clinicians in minimizing the time required for this procedure. In the literature, many studies proposed machine learning and deep learning-based algorithms for glioma identification at MRI slice-level. However, all these methods classify the slices using the previously extracted MRI features. So, the aim of this work is to propose a deep learning-based algorithm for the automatic detection of glioma from F LAIR MRI slices. Performance were assessed with a 5-fold cross validation and quantified by SENsitivity (SEN), SPEcificity (SPE), ACCuracy (ACC) and Area Under the Curve (AUC). Finally, a PDF report is generated reporting the MRI slice indexes where the tumor is. Results confirm the goodness of the proposed model with SEN=100%, SPE=99.4%, ACC=99.8% and AUC=99.9%. The model outperforms all studies found in the literature. In conclusion, the proposed model is the first feature-independent automated approach for glioma identification at the MRI slice-level. Additionally, the generation of a PDF report makes the model ready to use for clinicians.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354884

Role of the Historical Electrocardiogram in Identifying Acute Coronary Syndrome
Computing in Cardiology
Autore/i: Sbrollini, A.; Burattini, L.; Swenne, C. A.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Sensitivity (SE) and specificity (SP) for diagnosing acute coronary syndrome in prehospital ECGs is insufficient. The guidelines state that comparison of prehospital ECGs and a previous ECG tracing is valuable, particularly in case of pre-existing ECG abnormalities. Our study investigates the additional value of the historical ECG in detecting ischemia in prehospital phase. Data belong to the SUBTRACT study, which includes couples of 10-second 12-lead prehospital and historical ECGs from 1182 patients. Retrospective evaluation of the prehospital ECGs yielded 169 patients with, and 1013 patients without ischemia in prehospital ECG. Overall, each ECG couple were characterized by 47 features, which were grouped in the first set, including 18 direct measurements from the prehospital ECG, and the second set, including the first set and 29 serial prehospital-historical ECG differences. The sets were used to create two dendrograms, that divided the data into two clusters. Clusters were labeled as ischemia cluster (i.e., including over 50% of the ischemia patients) and non-ischemia cluster, and evaluated by SE and SP. Metrics of the second dendrogram (SE=71%; SP=69%) are higher than those of the first dendrogram (SE=22%; SP=57%). We conclude that serial differences improve ischemia identification in the ambulance, thus proving the additional diagnostic value of a historical ECG.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354889

A Novel Deep-Learning Method for Fibrillatory Waves Extraction from Electrocardiograms
Computing in Cardiology
Autore/i: Goffi, L.; Sbrollini, A.; Mortada, J.; Morettini, M.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Atrial fibrillation (AF) is the most common supraventricular arrhythmia and its most specific feature on the electrocardiogram (ECG) is the presence of fibrillatory waves (F-waves). The aim of this study is to present a new method that innovatively uses deep-learning (DL) as a filter to optimize the extraction of F-waves from ECGs. To do so, the CPSC database, containing 918 12-lead ECGs showing normal sinus rhythm (NSR), and Reference database, containing 30 12-lead ECG created by combining real F-waves and QRST complexes, were used. Zero-padding vectors and the real F-waves were used as ground truth to evaluate the method. ECGs were segmented into 1-second windows, that represent the inputs of the method. The DL method comprises two convolutional neural networks having the same architecture (six sequential multipath modules), but different loss functions. The root mean squared error (RMSE) between amplitudes of the estimated and ground truth F-waves was computed, together with the area under the curve (AUC) of the receiver operating characteristics. Results indicate a low testing RMSE (NSR: 6.02 µV; AF: 11.14 µV) and a high testing AUC (>99%). In conclusion, our DL method can reliably extract reliably extract F-waves from ECGs; their estimated amplitude permits reliable discrimination of AF patients.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354888

Into-the-Field Assessment of Maximal Heart Rate during Exercise
Computing in Cardiology
Autore/i: Sbrollini, A.; Morettini, M.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Exercise is normally recommended for its beneficial effects on health; however, exercising at very high heart rate (HR) may increase the risk of cardiac events. Theoretical maximal HR (TMHR) is subject dependent and may be easily computed through several formulas; according to the guidelines, recommended target HR range during a stress test for clinical evaluation is 50 to 85% of TMHR. Considering the new widely diffused use of wearable sensors, an into-the-field assessment of the highest HR (HHR) reached during exercise is now possible. Thus, the present study aims to assess HHR during uncontrolled exercise and to relate it to TMHR. To this aim, 178 HR series were acquired through wearable sensors from 122 athletes, while practicing 15 different sports. TMHR was assessed by applying seven well-known mathematical formulae. Percentage of athletes whose HHR overcame 85% of TMHR (i.e., recommended target HR range during a stress test) and TMHR were computed. Moreover, HHR and TMHR distributions were compared by paired T-Student test (statistical significance at 0.05). HHR of 90% or more of athletes overcame 85% of TMHR. HHR of 39% or more of athletes overcame TMHR. Thus, HHR normally approaches, and sometimes overcomes, TMHR when exercising.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354876

Phasor-Based Myoelectric Synergy Features: A Fast Hand-Crafted Feature Extraction Scheme for Boosting Performance in Gait Phase Recognition
SENSORS
Autore/i: Tigrini, A.; Mobarak, R.; Mengarelli, A.; Khushaba, R. N.; Al-Timemy, A. H.; Verdini, F.; Gambi, E.; Fioretti, S.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Gait phase recognition systems based on surface electromyographic signals (EMGs) are crucial for developing advanced myoelectric control schemes that enhance the interaction between humans and lower limb assistive devices. However, machine learning models used in this context, such as Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), typically experience performance degradation when modeling the gait cycle with more than just stance and swing phases. This study introduces a generalized phasor-based feature extraction approach (PHASOR) that captures spatial myoelectric features to improve the performance of LDA and SVM in gait phase recognition. A publicly available dataset of 40 subjects was used to evaluate PHASOR against state-of-the-art feature sets in a five-phase gait recognition problem. Additionally, fully data-driven deep learning architectures, such as Rocket and Mini-Rocket, were included for comparison. The separability index (SI) and mean semi-principal axis (MSA) analyses showed mean SI and MSA metrics of 7.7 and 0.5, respectively, indicating the proposed approach’s ability to effectively decode gait phases through EMG activity. The SVM classifier demonstrated the highest accuracy of 82% using a five-fold leave-one-trial-out testing approach, outperforming Rocket and Mini-Rocket. This study confirms that in gait phase recognition based on EMG signals, novel and efficient muscle synergy information feature extraction schemes, such as PHASOR, can compete with deep learning approaches that require greater processing time for feature extraction and classification.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/334932

A Computer-Aided Screening Solution for the Identification of Diabetic Neuropathy from Standing Balance by Leveraging Multi-Domain Features
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
Autore/i: Mengarelli, A.; Tigrini, A.; Verdini, F.; Scattolini, M.; Mobarak, R.; Burattini, L.; Rabini, R. A.; Fioretti, S.
Classificazione: 1 Contributo su Rivista
Abstract: The early diagnosis of diabetic neuropathy (DN) is fundamental in order to enact timely therapeutic strategies for limiting disease progression. In this work, we explored the suitability of standing balance task for identifying the presence of DN. Further, we proposed two diagnosis pathways in order to succeed in distinguishing between different stages of the disease. We considered a cohort of non-neuropathic (NN), asymptomatic neuropathic (AN), and symptomatic neuropathic (SN) diabetic patients. From the center of pressure (COP), a series of features belonging to different description domains were extracted. In order to exploit the whole information retrievable from COP, a majority voting ensemble was applied to the output of classifiers trained separately on different COP components. The ensemble of kNN classifiers provided over 86% accuracy for the first diagnosis pathway, made by a 3-class classification task for distinguishing between NN, AN, and SN patients. The second pathway offered higher performances, with over 97% accuracy in identifying patients with symptomatic and asymptomatic neuropathy. Notably, in the last case, no asymptomatic patient went undetected. This work showed that properly leveraging all the information that can be mined from COP trajectory recorded during standing balance is effective for achieving reliable DN identification. This work is a step toward a clinical tool for neuropathy diagnosis, also in the early stages of the disease.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/332752

Normalization of Electrocardiogram-Derived Cardiac Risk Indices: A Scoping Review of the Open-Access Literature
APPLIED SCIENCES
Autore/i: Iammarino, Erica; Marcantoni, Ilaria; Sbrollini, Agnese; Morettini, Micaela; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Featured Application: This scoping review provides an overall assessment of the application of normalization on electrocardiogram-derived cardiac risk indices, aiming to clarify the rationale behind its application and the consistency and comparability of these normalized indices in the literature. Changes in cardiac function and morphology are reflected in variations in the electrocardiogram (ECG) and, in turn, in the cardiac risk indices derived from it. These variations have led to the introduction of normalization as a step to compensate for possible biasing factors responsible for inter- and intra-subject differences, which can affect the accuracy of ECG-derived risk indices in assessing cardiac risk. The aim of this work is to perform a scoping review to provide a comprehensive collection of open-access published research that examines normalized ECG-derived parameters used as markers of cardiac anomalies or instabilities. The literature search was conducted from February to July 2024 in the major global electronic bibliographic repositories. Overall, 39 studies were selected. Results suggest extensive use of normalization on heart rate variability-related indices (49% of included studies), QT-related indices (18% of included studies), and T-wave alternans (5% of included studies), underscoring their recognized importance and suggesting that normalization may enhance their role as clinically useful risk markers. However, the primary objective of the included studies was not to evaluate the effect of normalization itself; thus, further research is needed to definitively assess the impact and advantages of normalization across various ECG-derived parameters.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/336938

Cardiorespiratory DB: Collection of cardiorespiratory data acquired during normal breathing, deep breathing and breath holding
DATA IN BRIEF
Autore/i: Sbrollini, A.; Marcantoni, I.; Lunghi, T.; Morettini, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: The database is constituted by 50 datasets containing cardiorespiratory signals acquired from 50 healthy volunteer subjects (one dataset for each subject; 23 males and 27 females; age: 23±5 years) while performing normal breathing, deep breathing, and breath holding, and two spreadsheet files, namely the “SubjectsInfo.xlsx” and “DBInfo.xlsx” containing the metadata of subjects (including demographic data) and of acquired signals, respectively. Cardiorespiratory signals consisted in simultaneously recorded 12-lead electrocardiograms acquired by the clinical M12 Global InstrumentationⓇ digital Holter ECG recorder, and single-lead electrocardiograms and respiration signals acquired by the wearable chest strap BioHarness 3.0 by Zephyr. The database may be useful to: (1) validate the use of wearable sensors in the acquisition of cardiorespiratory data during different respiration kinds, including apnea; (2) investigate the physiological association between cardiovascular and respiratory systems; (3) validate algorithms able to indirectly extract the respiration signal from the electrocardiogram; (4) study the fatigue level induced by a series of controlled respiration patterns; and (5) investigate the effect of COVID-19 infection on the cardiorespiratory system.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/329034

Interhemispheric functional connectivity in split-brain patients: evidence from resting state fMRI
73rd National Congress of the Italian Society of Physiology, Programme and Abstracys
Autore/i: Fabri, M.; Marcantoni, I.; Piccolantonio, G.; Vitti, E.; Polonara, G.; Ghoushi, M.; Valenti, M.; Reversi, L.; Foschi, N.; Lattanzi, S.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354983

A Reliable User-Independent Motion Intent Detection from Transient EMG Data for Shoulder Joint
Convegno Nazionale di Bioingegneria
Autore/i: Scattolini, M.; Tigrini, A.; Verdini, F.; Fioretti, S.; Burattini, L.; Morettini, M.; Mengarelli, A.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Motion intent detection (MID) through transient surface electromyographic (sEMG) is becoming central for the development of real-time assistive and rehabilitative technologies. However, the adaptation of such myoelectric interfaces in a user-independent framework represents a cutting-edge problem that hampers the practical usage of sEMG based human-machine interfaces. In this study least square canonical correlation analysis (LS-CCA) was employed together with SVM classifier in order to solve a shoulder joint MID problem. A publicly available dataset comprising eight healthy subjects was employed and four shoulder movements were considered. The LS-CCA was used for computing a subject-independent feature space using training data and then the trained SVM model was tested on an unseen subject, eventually implementing a leave-one-subject-out validation. Two window lengths for feature extraction (50 and 150 ms) and three feature sets were also compared. Overall, the best results were obtained using the 50 ms window length (multiuser classification accuracy about 70%), without any significant difference among the three feature sets.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/324353

Sport DB 2.0: A New Database of Data Acquired by Wearable and Portable Devices While Practicing Sport
Computing in Cardiology
Autore/i: Romagnoli, S.; Sbrollini, A.; Nocera, A.; Morettini, M.; Gambi, E.; Bondi, D.; Pietrangelo, T.; Verratti, V.; Burattini, L.
Editore: IEEE Computer Society
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Sport DB 2.0 is a collection of 168 cardiorespiratory datasets, acquired through wearable sensors and portable devices from 130 subjects while practicing 11 different sports during training and competition. Each dataset consists of demographic data (sex, age, weight, height, smoking habit, alcohol consumption, caffeine consumption, weekly training rate, presence of diseases and dietary supplement consumption), cardiorespiratory signals (electrocardiogram, heart-rate series, RR-interval series, and/or breathing-rate series), and training note data (sport-dependent training protocol). Cardiorespiratory signals were acquired through the BioHarness 3.0 by Zephyr, the KardiaMobile by AliveCor, the Kardia 6L by AliveCor, the Polar M400 by Polar, and heart-rate sensor H7 by Polar, on the playing field or gym following a specific acquisition protocol for each sport. Sport DB 2.0 may be useful to support research activity finalized to investigate the cardiorespiratory pathophysiological mechanisms triggered by sport, to develop automatic algorithms for monitoring athletes' health while practicing sports, to validate the reliability of wearable sensors and portable devices in sport, and to develop data analytics techniques and artificial intelligence applications to support sport sciences.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/326419

Leukocyte classification for acute lymphoblastic leukemia timely diagnosis by interpretable artificial neural network
Journal of Autonomous Intelligence
Autore/i: Sbrollini, A.; Tomassini, S.; Sharaan, R.; Morettini, M.; Dragoni, A. F.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Leukemia is a blood cancer characterized by leukocyte overproduction. Clinically, the reference for acute lymphoblastic leukemia diagnosis is a blood biopsy that allows obtain microscopic images of leukocytes, whose early-stage classification into leukemic (LEU) and healthy (HEA) may be disease predictor. Thus, the aim of this study is to propose an interpretable artificial neural network (ANN) for leukocyte classification to timely diagnose acute lymphoblastic leukemia. The “ALL_IDB2” dataset was used. It contains 260 microscopic images showing leukocytes acquired from 130 LEU and 130 HEA subjects. Each microscopic image shows a single leukocyte that was characterized by 8 morphological and 4 statistical features. An ANN was developed to distinguish microscopic images acquired from LEU and HEA subjects, considering 12 features as inputs and the local-interpretable model-agnostic explanatory (LIME) algorithm as an interpretable post-processing algorithm. The ANN was evaluated by the leave-one-out cross-validation procedure. The performance of our ANN is promising, presenting a testing area under the curve of the receiver operating characteristic equal to 87%. Being implemented using standard features and having LIME as a post-processing algorithm, it is clinically interpretable. Therefore, our ANN seems to be a reliable instrument for leukocyte classification to timely diagnose acute lymphoblastic leukemia, guaranteeing a high clinical interpretability level.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/320131

DL-LVEF: Deep-Learning Measurement of the Left Ventricular Ejection Fraction from Echocardiographic Images
Computing in Cardiology
Autore/i: Sbrollini, A.; Mortada, M. H. D. J.; Tomassini, S.; Anbar, H.; Morettini, M.; Burattini, L.
Editore: IEEE Computer Society
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Left ventricular ejection fraction (LVEF) is a commonly used index of cardiac functionality. Thus, accuracy in its measurement is fundamental. LVEF measure is usually manually performed by clinicians from echocardiographic images. Use of automatic algorithms could make LVEF measurement more objective. Thus, the aim of the present work is to present DL-LVEF, a new automatic algorithm for LVEF measurement based on deep learning identification and segmentation of the left ventricular endocardium performed by combining the YOLOv7 algorithm and a U-Net. To this aim, the CAMUS database was used, which includes 1800 echocardiographic images acquired from 450 patients with annotated LVEF values and manual segmentation of the left ventricular endocardium. The database was divided into training dataset (70%) and testing dataset (30%). In both datasets, measured and annotated LVEF values (%) were found to be highly correlated (p=0.96 and p=0.89, respectively) and not statistically different (52.6% vs. 52.6% and 54.6% vs. 53.9%, respectively); mean absolute error was 4% and 5%, respectively. Thus, DL-LVEF provided objective and accurate LVEF measurement. Future DL-LVEF evolutions will also provide segmentation of other cardiac anatomical structures and, thus, will allow measurement of other clinically relevant cardiac indexes.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/326411

Identification of Respiration Types Through Respiratory Signal Derived from Clinical and Wearable Electrocardiograms
IEEE OPEN JOURNAL OF ENGINEERING IN MEDICINE AND BIOLOGY
Autore/i: Sbrollini, A.; Morettini, M.; Gambi, E.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Goal: To evaluate suitability of respiratory signals derived from clinical 12-lead electrocardiograms (ECGs) and wearable 1-lead ECG to identify different respiration types. Methods: ECGs were simultaneously acquired through the M12R ECG Holter by Global Instrumentation and the chest strap BioHarness 3.0 by Zephyr from 42 healthy subjects alternating normal breathing, breath holding, and deep breathing. Respiration signals were derived from the ECGs through the Segmented-Beat Modulation Method (SBMM)-based algorithm and the algorithms by Van Gent, Charlton, Soni and Sarkar, and characterized in terms of breathing rate and amplitude. Respiration classification was performed through a linear support vector machine and evaluated by F1 score. Results: Best F1 scores were 86.59%(lead V2) and 80.57%, when considering 12-lead and 1-lead ECGs, respectively, and using SBMM-based algorithm. Conclusion: ECG-derived respiratory signals allow reliable identification of different respiration types even when acquired through wearable sensors, if associated to appropriate processing algorithms, such as the SBMM-based algorithm.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/325571

Interhemispheric functional connectivity: an fMRI study in two split-brain patients
Convegno Nazionale di Bioingegneria- GNB2023
Autore/i: Marcantoni, I.; Piccolantonio, G.; Vitti, E.; Polonara, G.; Ghoushi, M.; Valenti, M.; Reversi, L.; Foschi, N.; Lattanzi, S.; Burattini, L.; Fabri, M.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Resting state networks (RSNs) were most studied using functional magnetic resonance imaging (fMRI). Interhemispheric functional connectivity (FC) appears mostly supported by the corpus callosum (CC) and several studies have investigated this aspect, still not providing conclusive evidence. In this context, patients in whom the CC was resected for therapeutic reasons (split-brain patients) provide a unique opportunity of research. The purpose of this pilot study is to investigate, with resting state fMRI, the interhemispheric FC in two callosotomized patients operated in adult age, and in four healthy control subjects with intact brain. The analysis was performed with fMRI of the Brain (FMRIB) Software Library (FSL); the evaluation of interhemispheric FC and the recognition of the RSNs were performed by using the probabilistic independent component analysis (PICA). The multi-subject analysis on control subjects allowed the identification of three RSNs: medial visual, default mode, and sensory motor. Both patients showed a bilateral brain activation in the medial visual network, comparable with the controls; in the sensory motor and the default mode networks the activation was unilateral, at variance with controls. These results seem to suggest that the brain, during its maturation, builds new subcortical communication pathways, alternative to the CC, which might support interhemispheric FC in case of callosotomy. Further studies are needed to confirm the observations obtained and reported in this preliminary research.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/324913

Mathematical model of glucagon kinetics during an oral glucose tolerance test based on a dual regulation mechanism
Convegno Nazionale di Bioingegneria- GNB2023
Autore/i: Morettini, M.; Piersanti, A.; Gobl, C.; Burattini, L.; Tura, A.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Glucagon is a hormone secreted by the pancreatic alpha cells and plays a key role in glucose homeostasis and in the pathophysiology of type 2 diabetes (T2D). Different mechanisms are involved in its regulation, but exact mechanisms are still largely unknown. This study aimed to propose a model describing glucagon inhibition during an oral glucose tolerance test (OGTT), accounting for a double regulation mechanism. The model has been developed starting from a model previously proposed by our group that includes two differential equations, one for plasma glucagon and one for C-peptide (marker of insulin at pancreatic level). In the new model, in addition to plasma C-peptide, plasma glucose is included as model input. The model provides two parameters of possible clinical relevance, namely SGLUCA and kG (alpha-cell insulin and glucose sensitivity, respectively) and has been validated on mean literature data of healthy subjects and subjects affected by T2D (CNT and T2D, respectively). Model analysis yielded SGLUCA estimates ranging from -0.1515 to 0.7629 and from -5.5602 to 1.1067 (ng of glucagon·nmol of C-peptide-1) in CNT and T2D groups, respectively; according to the 95% confidence intervals (CIs), SGLUCA was significantly different from zero in 4 and in 0 out of 8 time points, in CNT and T2D. Estimates for kG were equal to 2.8302 (95% CIs: 1.1973-4.4632) and 0.9913 (95% CIs: -0.5559-2.5386) ng of glucagon·mmol of glucose-1. Thus, results suggest both insulin (represented by C-peptide) and glucose significantly contributes to glucagon inhibition in healthy subjects, but not in T2D. In conclusion, the proposed model may help to describe different mechanisms acting on glucagon inhibition in the single individuals.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/324914

Software Packages and Tools for the Analysis of Continuous Glucose Monitoring Data
DIABETES TECHNOLOGY & THERAPEUTICS
Autore/i: Piersanti, Agnese; Giurato, Francesco; Göbl, Christian; Burattini, Laura; Tura, Andrea; Morettini, Micaela
Classificazione: 1 Contributo su Rivista
Abstract: The advancement of technology in the field of glycemic control has led to the widespread use of continuous glucose monitoring (CGM), which can be nowadays obtained from wearable devices equipped with a minimally invasive sensor, that is, transcutaneous needle type or implantable, and a transmitter that sends information to a receiver or smart device for data storage and display. This work aims to review the currently available software packages and tools for the analysis of CGM data. Based on the purposes of this work, 12 software packages have been identified from the literature, published until December 2021, namely: GlyCulator, EasyGV (Easy Glycemic Variability), CGM-GUIDE(C) (Continuous Glucose Monitoring Graphical User Interface for Diabetes Evaluation), GVAP (Glycemic Variability Analyzer Program), Tidepool, CGManalyzer, cgmanalysis, GLU, CGMStatsAnalyser, iglu, rGV, and cgmquantify. Comparison of available software packages and tools has been done in terms of main characteristics (i.e., publication year, presence of a graphical user interface, availability, open-source code, number of citations, programming language, supported devices, supported data format and organization of the data structure, documentation, presence of a toy example, video tutorial, data upload and download, measurement-units conversion), preprocessing procedures, data display options, and computed metrics; also, each of the computed metrics has been analyzed in terms of its adherence to the American Diabetes Association (ADA) 2017 international consensus on CGM data analysis and the ADA 2019 international consensus on time in range. Eventually, the agreement between metrics computed by different software and tools has been investigated. Based on such comparison, usability and complexity of data management, as well as the possibility to perform customized or patients-group analyses, have been discussed by highlighting limitations and strengths, also in relation to possible different user categories (i.e., patients, clinicians, researchers). The information provided could be useful to researchers interested in working in the diabetic research field as to clinicians and endocrinologists who need tools capable of handling CGM data effectively.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/308564

Brugada Syndrome: Characterization of QT Interval Components and Correction
Convegno Nazionale di Bioingegneria- GNB2023
Autore/i: Sbrollini, A.; Romagnoli, S.; Locati, E. T.; Morettini, M.; Burattini, L.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Brugada syndrome (BrS) is an inherited cardiac disorder at high risk of sudden death. There are two ECG patterns for BrS: Type 1 (coved-type), representing the only diagnostic pattern for BrS (BrS1), while type 2 (saddle-back type) is only suggestive of BrS (BrS2). The QT interval on surface ECG, known to be heart-rate (HR) dependent, characterizes ventricular activity and is associated with the risk of ventricular arrhythmias. Aim of this study is to investigate the role of QT-interval and QT-interval-segment correction in subjects with BrS1 and BrS2, compared to controls (CTR). Open-access “Brugada ECG Database” by Zenodo was considered, containing HR, QT interval and its segments (QJ, JTp, and TpTe) of 60 subjects with BrS1, 27 subjects with BrS2 and 51 CTR. Time intervals and segments were corrected according to nine correction formulae. Feature distributions of BrS1, BrS2 and CTR were compared by unpaired Wilcoxon rank sum test. All BrS1 and BrS2 features were statistically different from CTR. QT interval and corrected QT interval were significantly longer in BrS1 and BrS2 than in CTR, mainly due to longer QJ and TpTe, while JTp was significantly shorter in BrS1 and BrS2 than in CTR. No significant differences were observed in QJ and JTp between BrS1 and BrS2, whereas five correction formulae revealed that BrS1 had significantly longer TpTe interval than BrS2, suggesting physiological differences between BrS1 and BrS2 in late repolarization phase. In conclusion, major differences exist between BrS patients and CRT in QT-interval duration, mainly due to longer QJ and shorter JTp duration in BrS patients, while differences may exist between BrS1 and BrS2 patients in the late repolarization phase, highlighting the need of proper QT-HR correction to better characterize BrS patients.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/324912

mmWave Radars Data Processing for Gait Parameters Extraction
Convegno Nazionale di Bioingegneria- GNB2023
Autore/i: Nocera, A.; Verdini, F.; Fioretti, S.; Ciattaglia, G.; Raimondi, M.; Burattini, L.; Senigagliesi, L.; Gambi, E.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: A person's mobility can be examined to learn vital details about their health.Non-contact technology can be used for this investigation with the aim of ensuring freedom of movement of the subject and realistic analysis of movement. Automotive mmWaves radars, while made for different uses, are a powerful low-cost technology for detecting human movement without physical contact, which can introduce fascinating implications as an aid to health monitoring at home or at work. This paper shows how to process the data recorded by commercial radars to extract simple spatio-temporal parameters of people's walking. The processing algorithms provides the cadence, step length and step duration with a good approximation of the true gait parameters.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/324911

Symbolic Analysis of Heart-Rate Variability during Training and Competition in Short Distance Running
Proceedings - IEEE Symposium on Computer-Based Medical Systems
Autore/i: Romagnoli, S.; Sbrollini, A.; Morettini, M.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: During physical exercise, the assessment of cardiac autonomic regulation through the analysis of heart-rate variability is difficult due to non-stationarity of RR intervals. The short duration of stationary epoch of RR-interval series makes not possible the computation of classical time-and frequency-domain parameters. Symbolic analysis can deal with short epoch of RR interval; thus, this study aims to apply symbolic analysis to analyze heart-rate variability of short-distance runners during training and competition. Data consists of RR-intervals extracted from 30s-long electrocardiograms acquired by KardiaMobile of Alivecor in 8 short-distance runners (1/7 M/F, 17[16;20] years) during training and competition. Symbolic analysis classifies a reduced number (in this study, three) of consecutive RR intervals in four patterns according to the sign and number of variations: no variation (0V); one variation (1V); two like variations (2LV); two unlike variations (2UV). An increase in low amount of variations (0V or 1V patterns) is usually linked with increased sympathetic control and vagal withdrawal, while an increase in high amount of variations (2LV and 2UV patterns) is usually linked with sympathetic withdrawal and increased vagal control. In our results, pattern 0V /2LV increases/decreases from rest to post exercise and decreases/increases during recovery, in both training and competition. Thus, our results confirm the opposite trends between low and high variations of symbolic patterns. In conclusion, symbolic analysis seems to be an efficient tool to characterize heart-rate variability during physical exercise at different level of psychophysical stress.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/320313

A Machine-Learning Framework based on Continuous Glucose Monitoring to Prevent the Occurrence of Exercise-Induced Hypoglycemia in Children with Type 1 Diabetes
Proceedings - IEEE Symposium on Computer-Based Medical Systems
Autore/i: Piersanti, A.; Salvatori, B.; Gobl, C.; Burattini, L.; Tura, A.; Morettini, M.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Physical activity is recommended in patients with type 1 diabetes (T1D), but therapy management still lacks efficient tools to avoid exercise-induced hypoglycemia. Machine learning represents a powerful solution in the field of decision support for diabetes management and its application to continuous glucose monitoring (CGM) data appears promising in pre-exercise prediction of upcoming adverse events. Aim of this study was to investigate the possibility to distinguish if a specific configuration of CGM metrics evaluated before starting of exercise is more prone to induce hypoglycemia after the start of the exercise session until the following day. A total of 47 CGM recordings from T1D children have been used to extract CGM metrics from pre-exercise CGM data. Acquisitions were labelled as HYPO or as NO-HYPO, respectively if belonging to subjects who experienced or did not experience hypoglycemia during the time following the exercise. Anthropometric characteristics and extracted features have been given as input to a decision tree classification algorithm to select those with the most predictive power. The selected features were then further evaluated with respect to the classification problem by using them as input to other three classification models: random forest, adaboost and gradient boosting. Performance results in terms of area under receiver operating characteristic (AUC) were as follows: 85.5%, 82.1%, 78.1% and 74.3% for decision tree, gradient boosting, random forest and adaboost, respectively. M-value, maximum glucose, time above 180 mg/dL and time above 250 mg/dL could have a role in predicting upcoming hypoglycemia prior the starting of exercise.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/320314

CLAUDIA: Cloud-based Automatic Diagnosis of Alzheimer's Prodromal Stage and Disease from 3D Brain Magnetic Resonance
Proceedings - IEEE Symposium on Computer-Based Medical Systems
Autore/i: Tomassini, S.; Sbrollini, A.; Morettini, M.; Dragoni, A. F.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Alzheimer's Disease (AD) is the most common neurodegenerative disease. Its first stage, namely prodromal or Mild Cognitive Impairment (MCI), is characterized by slightly structural changes in the subcortical structures of the temporal lobe. Brain Magnetic Resonance (MR) is the most utilized neu-roimaging modality for the diagnosis of AD. Although an early therapeutic intervention during the initial stages of AD appears to have a positive impact on the progression of symptoms, its accurate diagnosis is still very difficult. Deep Learning (DL)-based decision-support systems hold great potential in generalizing even under subtle anatomical changes of the brain, like the ones caused by AD at its onset. To our knowledge, we were the first to develop a Convolutional Long Short-Term Memory (ConvLSTM)-based decision-support system and an improved version of it for the automatic diagnosis of AD from 3D brain MR. The research presented in this paper aims to extend their applicability to MCI for effectiveness verification through the development of CLAUDIA, a new on-cloud decision-support system for the automatic diagnosis of Alzheimer's prodromal stage and disease from 3D brain MR. To this aim, we selected 438 unenhanced scans from the ADNI-1 dataset, preprocessed them, and injected the preprocessed scans to the ConvLSTM-based neural network for automatic feature extraction and binary/multiclass classification. On test data, CLAUDIA achieved very encouraging results that highlight the superiority of the multiclass classifier in comparison to the two binary classifiers. On the basis of the achieved outcomes, we demonstrated that CLAUDIA, being the first to extend the applicability of a ConvLSTM-based neural network to MCI for effectiveness verification, represents a promising scan-, DL-based decision-support system for the automatic diagnosis of Alzheimer's prodromal stage and disease from 3D brain MR. Moreover, its cloud thus machine-independent nature ensures a full reproducibility of the implementation while guaranteeing cost saving and sustainability.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/320312

Toward a Minimal sEMG Setup for Knee and Ankle Kinematic Estimation during Gait
Proceedings - IEEE Symposium on Computer-Based Medical Systems
Autore/i: Mengarelli, A.; Verdini, F.; Al-Timemy, A. H.; Mobarak, R.; Scattolini, M.; Fioretti, S.; Burattini, L.; Tigrini, A.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 2 Contributo in Volume
Abstract: Modern rehabilitation and assistive devices require the use of smart interfaces able to capture the subject's intent of motion and translate such intent to specific control strategies. The use of surface electromyography (sEMG) signals, in combination with data-driven models, constitutes a viable framework to solve the aforementioned problem. Although literature highlighted the tendency toward a multiple sensors approach, a minimal set-up may reduce costs and complexity of myoelectric interfaces. In this study, gastrocnemius lateralis (GAL) and tibialis anterior (TA) sEMG signals were used in order to investigate their single and combined role in the flexion-extension angles estimation of ankle and knee during gait. Least-square support vector machine (LS-SVM) with linear, polynomial, and radial basis function (RBF) kernel was employed to estimate the most suitable function that maps the myoelectric information from single muscle and from the combination of both, in lower limbs joint kinematics. LS-SVM with RBF outperformed the other kernels in the ankle and knee kinematics estimation for all the 6 subjects examined. Moreover, when using RBF with the only GAL data, the median root mean square error (RMSE) values were above 5 degrees for ankle and 8 degrees for knee angles whereas the combined information from GAL and TA showed slightly better results. Outcomes support a minimal electrodes set-up for the development of lower limb myoelectric interfaces for kinematic estimation.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/320311

Model-based Estimators of QT Series Time Delay in Following Heart-Rate Changes
Proceedings of the 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Autore/i: Romagnoli, S.; Perez, C.; Burattini, L.; Pueyo, E.; Morettini, M.; Sbrollini, A.; Martinez, J. P.; Laguna, P.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Sudden cardiac death is the leading cause of death among cardiovascular diseases. Markers for patient risk stratification focusing on QT-interval dynamics in response to heart-rate (HR) changes can be characterized in terms of parametric QT to RR dependence and QT/RR hysteresis. The QT/RR hysteresis can be quantified by the time delay the QT interval takes to accommodate for the HR changes. The exercise stress test has been proposed as a proper test, with large HR dynamics, to evaluate the QT/RR hysteresis. The present study aims at evaluating several time-delay estimators based on noise statistic (Gaussian or Laplacian) and HR changes profile at stress test (gradual transition change). The estimator's performance was assessed on a simulated QT transition contaminated by noise and in a clinical study including patients affected by coronary arteries disease (CAD). As expected, the Laplacian and Gaussian estimators yield the best results when noise follows the respective distribution. Further, the Laplacian estimator showed greater discriminative power in classifying different levels of cardiac risk in CAD patients, suggesting that real data fit better the Laplacian distribution than the Gaussian one. The Laplacian estimator appears to be the choice for time-delay estimation of QT/RR hysteresis lag in response to HR changes in stress test.Clinical Relevance-The proposed time-delay estimator of QT/RR hysteresis lag improves its significance as biomarkers for coronary artery diseases risk stratification.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/325438

Gait Event Timeseries Assessment through Spectral Biomarkers and Machine Learning
Proceedings - IEEE Symposium on Computer-Based Medical Systems
Autore/i: Tigrini, A.; Verdini, F.; Fioretti, S.; Scattolini, M.; Mobarak, R.; Gambi, E.; Burattini, L.; Mengarelli, A.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The study of motor disorders due to neurodegenerative diseases (NDD) is assuming a central role in healthcare systems, this is certainly due to the needs of early recognition systems that can allow a better management of the patients daily-life. Many studies in the literature faced the problem of finding digital biomarkers from data collected through gait experiments to discriminate between control (CN) and NDD groups without systematically face the problem of which gait time-series were more appropriate to extract opportune descriptors for characterizing the NDD considered. In this work, such problem was modeled through a machine learning approach. Thus, 6 time-dependent spectral features (PSDTD) were extracted from 4 gait time-series, i.e., stride (SR), stance (SA), swing (SW) and double support (DS) duration intervals. A publicly available data set containing data of CN, Parkinson's (PD), Huntington's (HD) and amyotrophic lateral sclerosis (ALS) diseases was employed to the purpose. Low error rates using leave one out validation scheme were obtained using PSDTD features computed over DS and SA for CN-PD and CN-HD classification, i.e., error rate < 0.1 for DS and < 0.15 for SA. Regarding CN-ALS classification, best results were obtained using SA features, i.e. error rate <0.07. This supports the research line that dynamic equilibrium phases of the gait can hide important biomarkers for the characterization of different NDD.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/320291

Physiological and Biomechanical Monitoring in American Football Players: A Scoping Review
SENSORS
Autore/i: Nocera, A.; Sbrollini, A.; Romagnoli, S.; Morettini, M.; Gambi, E.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: American football is the sport with the highest rates of concussion injuries. Biomedical engineering applications may support athletes in monitoring their injuries, evaluating the effectiveness of their equipment, and leading industrial research in this sport. This literature review aims to report on the applications of biomedical engineering research in American football, highlighting the main trends and gaps. The review followed the PRISMA guidelines and gathered a total of 1629 records from PubMed (n = 368), Web of Science (n = 665), and Scopus (n = 596). The records were analyzed, tabulated, and clustered in topics. In total, 112 studies were selected and divided by topic in the biomechanics of concussion (n = 55), biomechanics of footwear (n = 6), biomechanics of sport-related movements (n = 6), the aerodynamics of football and catch (n = 3), injury prediction (n = 8), heat monitoring of physiological parameters (n = 8), and monitoring of the training load (n = 25). The safety of players has fueled most of the research that has led to innovations in helmet and footwear design, as well as improvements in the understanding and prevention of injuries and heat monitoring. The other important motivator for research is the improvement of performance, which has led to the monitoring of training loads and catches, and studies on the aerodynamics of football. The main gaps found in the literature were regarding the monitoring of internal loads and the innovation of shoulder pads.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/313789

Automatic diagnosis of newly emerged heart failure from serial electrocardiography by repeated structuring & learning procedure
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Autore/i: Sbrollini, A.; Barocci, M.; Mancinelli, M.; Paris, M.; Raffaelli, S.; Marcantoni, I.; Morettini, M.; Swenne, C. A.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Heart failure (HF) diagnosis, typically visually performed by serial electrocardiography, may be supported by machine-learning approaches. Repeated structuring & learning procedure (RS&LP) is a constructive algorithm able to automatically create artificial neural networks (ANN); it relies on three parameters, namely maximal number of hidden layers (MNL), initializations (MNI) and confirmations (MNC), arbitrarily set by the user. The aim of this study is to evaluate RS&LP robustness to varying values of parameters and to identify an optimized combination of parameter values for HF diagnosis. To this aim, the Leiden University Medical Center HF database was used. The database is constituted by 129 serial ECG pairs acquired in patients who experienced myocardial infarction; 48 patients developed HF at follow-up (cases), while 81 remained clinically stable (controls). Overall, 15 ANNs were created by considering 13 serial ECG features as inputs (extracted from each serial ECG pair), 2 classes as outputs (cases/controls), and varying values of MNL (1, 2, 3, 4 and 10), MNI (50, 250, 500, 1000 and 1500) and MNC (2, 5, 10, 20 and 50). The area under the curve (AUC) of the receiver operating characteristic did not significantly vary with varying parameter values (P ≥ 0.09). The optimized combination of parameter values, identified as the one showing the highest AUC, was obtained for MNL = 3, MNI = 500 and MNC = 50 (AUC = 86 %; ANN structure: 3 hidden layers of 14, 14 and 13 neurons, respectively). Thus, RS&LP is robust, and the optimized ANN represents a potentially useful clinical tool for a reliable automatic HF diagnosis.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/306258

Assessment of electrical dyssynchrony in cardiac resynchronization therapy: 12-lead electrocardiogram vs. 96-lead body surface map
EUROPACE
Autore/i: Sedova, Ksenia A; van Dam, Peter M; Sbrollini, Agnese; Burattini, Laura; Necasova, Lucie; Blahova, Marie; Bocek, Jan; Sramko, Marek; Kautzner, Josef
Classificazione: 1 Contributo su Rivista
Abstract: Aims: The standard deviation of activation time (SDAT) derived from body surface maps (BSMs) has been proposed as an optimal measure of electrical dyssynchrony in patients with cardiac resynchronization therapy (CRT). The goal of this study was two-fold: (i) to compare the values of SDAT in individual CRT patients with reconstructed myocardial metrics of depolarization heterogeneity using an inverse solution algorithm and (ii) to compare SDAT calculated from 96-lead BSM with a clinically easily applicable 12-lead electrocardiogram (ECG). Methods and results Cardiac resynchronization therapy patients with sinus rhythm and left bundle branch block at baseline (n = 19, 58% males, age 60 +/- 11 years, New York Heart Association Classes II and III, QRS 167 +/- 16) were studied using a 96-lead BSM. The activation time (AT) was automatically detected for each ECG lead, and SDAT was calculated using either 96 leads or standard 12 leads. Standard deviation of activation time was assessed in sinus rhythm and during six different pacing modes, including atrial pacing, sequential left or right ventricular, and biventricular pacing. Changes in SDAT calculated both from BSM and from 12-lead ECG corresponded to changes in reconstructed myocardial ATs. A high degree of reliability was found between SDAT values obtained from 12-lead ECG and BSM for different pacing modes, and the intraclass correlation coefficient varied between 0.78 and 0.96 (P < 0.001). Conclusion Standard deviation of activation time measurement from BSM correlated with reconstructed myocardial ATs, supporting its utility in the assessment of electrical dyssynchrony in CRT. Importantly, 12-lead ECG provided similar information as BSM. Further prospective studies are necessary to verify the clinical utility of SDAT from 12-lead ECG in larger patient cohorts, including those with ischaemic cardiomyopathy.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/309104

On-cloud decision-support system for non-small cell lung cancer histology characterization from thorax computed tomography scans
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS
Autore/i: Tomassini, Selene; Falcionelli, Nicola; Bruschi, Giulia; Sbrollini, Agnese; Marini, Niccolò; Sernani, Paolo; Morettini, Micaela; Müller, Henning; Dragoni, Aldo Franco; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Non-Small Cell Lung Cancer (NSCLC) accounts for about 85% of all lung cancers. Developing non-invasive techniques for NSCLC histology characterization may not only help clinicians to make targeted therapeutic treatments but also prevent subjects from undergoing lung biopsy, which is challenging and could lead to clinical implications. The motivation behind the study presented here is to develop an advanced on-cloud decisionsupport system, named LUCY, for non-small cell LUng Cancer histologY characterization directly from thorax Computed Tomography (CT) scans. This aim was pursued by selecting thorax CT scans of 182 LUng ADenocarcinoma (LUAD) and 186 LUng Squamous Cell carcinoma (LUSC) subjects from four openly accessible data collections (NSCLC-Radiomics, NSCLC-Radiogenomics, NSCLC-Radiomics-Genomics and TCGA-LUAD), in addition to the implementation and comparison of two end-to-end neural networks (the core layer of whom is a convolutional long short-term memory layer), the performance evaluation on test dataset (NSCLC-RadiomicsGenomics) from a subject-level perspective in relation to NSCLC histological subtype location and grade, and the dynamic visual interpretation of the achieved results by producing and analyzing one heatmap video for each scan. LUCY reached test Area Under the receiver operating characteristic Curve (AUC) values above 77% in all NSCLC histological subtype location and grade groups, and a best AUC value of 97% on the entire dataset reserved for testing, proving high generalizability to heterogeneous data and robustness. Thus, LUCY is a clinically-useful decision-support system able to timely, non-invasively and reliably provide visuallyunderstandable predictions on LUAD and LUSC subjects in relation to clinically-relevant information.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/325437

Decoding transient sEMG data for intent motion recognition in transhumeral amputees
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Autore/i: Tigrini, A.; Al-Timemy, A. H.; Verdini, F.; Fioretti, S.; Morettini, M.; Burattini, L.; Mengarelli, A.
Classificazione: 1 Contributo su Rivista
Abstract: The use of surface electromyographic (sEMG) signals, alongside pattern recognition (PR) systems, is fundamental in the design and control of assistive technologies. Transient sEMG signal epochs at the early beginning of the movement provide important information for upper-limb intent of motion recognition. However, only few studies investigated the role of transient sEMG for myoelectric control architectures. Therefore, in this work, focus was given to transient sEMG signals of intact-limb (IL) subjects and transhumeral amputees (AMP), who performed a series of shoulder movements. The role of the window length for feature extraction was investigated by sub-windowing the transient epochs at 200, 150, 100, and 50 ms window length (WL). Gaussian kernel discriminant analysis (SRKDA) and support vector machine (SVM) were used for recognizing seven classes of motion at different hold-out percentage of training/testing data, i.e. 70%–30%, 60%–40% and 50%–50%. In all the latter conditions, the median classification accuracy and F1 score were greater than 80% for both IL and AMP groups when using SRKDA. Wilcoxon rank sum test was employed to verify possible differences between WL conditions. Although the latter did not show significant differences, 100 ms WL showed the best classification performances for both groups (classification accuracy greater than 90%, near that of a usable PR system). Results demonstrated that a reliable motion intent recognition of shoulder joint in transhumeral amputee patients can be obtained employing transient sEMG epochs. This can be used in a better design of myoelectric control architectures of assistive technologies, involving the upper-limb for clinical use.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/313727

Segmentation of Anatomical Structures of the Left Heart from Echocardiographic Images Using Deep Learning
DIAGNOSTICS
Autore/i: Mortada, Mhd Jafar; Tomassini, Selene; Anbar, Haidar; Morettini, Micaela; Burattini, Laura; Sbrollini, Agnese
Classificazione: 1 Contributo su Rivista
Abstract: Knowledge about the anatomical structures of the left heart, specifically the atrium (LA) and ventricle (i.e., endocardium-Vendo-and epicardium-LVepi) is essential for the evaluation of cardiac functionality. Manual segmentation of cardiac structures from echocardiography is the baseline reference, but results are user-dependent and time-consuming. With the aim of supporting clinical practice, this paper presents a new deep-learning (DL)-based tool for segmenting anatomical structures of the left heart from echocardiographic images. Specifically, it was designed as a combination of two convolutional neural networks, the YOLOv7 algorithm and a U-Net, and it aims to automatically segment an echocardiographic image into LVendo, LVepi and LA. The DL-based tool was trained and tested on the Cardiac Acquisitions for Multi-Structure Ultrasound Segmentation (CAMUS) dataset of the University Hospital of St. Etienne, which consists of echocardiographic images from 450 patients. For each patient, apical two- and four-chamber views at end-systole and end-diastole were acquired and annotated by clinicians. Globally, our DL-based tool was able to segment LVendo, LVepi and LA, providing Dice similarity coefficients equal to 92.63%, 85.59%, and 87.57%, respectively. In conclusion, the presented DL-based tool proved to be reliable in automatically segmenting the anatomical structures of the left heart and supporting the cardiological clinical practice.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/316996

Wearable and Portable Devices for Acquisition of Cardiac Signals while Practicing Sport: A Scoping Review
SENSORS
Autore/i: Romagnoli, Sofia; Ripanti, Francesca; Morettini, Micaela; Burattini, Laura; Sbrollini, Agnese
Classificazione: 1 Contributo su Rivista
Abstract: Wearable and portable devices capable of acquiring cardiac signals are at the frontier of the sport industry. They are becoming increasingly popular for monitoring physiological parameters while practicing sport, given the advances in miniaturized technologies, powerful data, and signal processing applications. Data and signals acquired by these devices are increasingly used to monitor athletes' performances and thus to define risk indices for sport-related cardiac diseases, such as sudden cardiac death. This scoping review investigated commercial wearable and portable devices employed for cardiac signal monitoring during sport activity. A systematic search of the literature was conducted on PubMed, Scopus, and Web of Science. After study selection, a total of 35 studies were included in the review. The studies were categorized based on the application of wearable or portable devices in (1) validation studies, (2) clinical studies, and (3) development studies. The analysis revealed that standardized protocols for validating these technologies are necessary. Indeed, results obtained from the validation studies turned out to be heterogeneous and scarcely comparable, since the metrological characteristics reported were different. Moreover, the validation of several devices was carried out during different sport activities. Finally, results from clinical studies highlighted that wearable devices are crucial to improve athletes' performance and to prevent adverse cardiovascular events.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/313147

Spatial distribution of BOLD activations evoked by three different tastants to build a chemotopic map of primary gustatory area: A pilot study
Proceedings - IEEE Symposium on Computer-Based Medical Systems
Autore/i: Marcantoni, I.; Tomaiuolo, F.; Piccolantonio, G.; Sbrollini, A.; Morettini, M.; Fiori, F.; Vignini, A.; Polonara, G.; Burattini, L.; Fabri, M.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The gustatory areas of the brain include the primary (GI) and the secondary (GII) gustatory cerebral cortex. A spatial mechanism has been recently hypothesized to explain the taste quality recognition. This research investigates the spatial distribution of blood oxygen level dependent (BOLD) activations evoked in the human area GI by different tastants, aimed at building a chemotopic map. The chemotopic organization of the human GI was studied in seven healthy subjects by applying three taste stimuli (salty, sweet, neutral) to either side of the tongue, using a 5-min functional magnetic resonance imaging (fMRI) block-designed protocol, alternating periods of rest and stimulation. Data were analyzed by the Functional Magnetic Resonance Imaging of the Brain (FMRIB) Software Library (FSL). Unilateral tongue stimulation consistently evoked bilateral activation in area GI. Ipsilateral foci were generally larger and signal increases greater. The foci evoked by each tastant exhibited slightly but not significantly different mean coordinates, broad overlap and high interindividual variability; the salty stimuli generally evoked more anterior foci and sweet stimuli more posterior activation. Results confirm that the gustatory pathways from tongue to cortex are bilaterally distributed, with an ipsilateral predominance. Although distinct GI zones were activated by the different taste stimuli, a clear topographical organization could not be recognized. Possibly, fMRI technique is unable to resolve fine topographical arrangements or GI discriminative role for different tastants is subserved by another mechanism. Bilateral activation of the primary somatosensory area in the parietal cortex (contralateral predominance) and of middle insula (ipsilateral predominance) were also observed.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/320315