180 pubblicazioni classificate nel seguente modo:

Glycaemic control and pregnancy outcomes with real-time continuous glucose monitoring in gestational diabetes (GRACE): an open-label, multicentre, multinational, randomised controlled trial
THE LANCET DIABETES & ENDOCRINOLOGY
Autore/i: Linder, Tina; Dressler-Steinbach, Iris; Wegener, Silke; Schellong, Karen; Schmidt, Saskia; Eppel, Daniel; Monod, Cécile; Heinzl, Florian; Redling, Katharina; Winzeler, Bettina; Mosimann, Beatrice; Weschenfelder, Friederike; Groten, Tanja; Mittlböck, Martina; Jendle, Johan; Henrich, Wolfgang; Morettini, Micaela; Bozkurt, Latife; Tura, Andrea; Göbl, Christian
Classificazione: 1 Contributo su Rivista
Abstract: BACKGROUND: Data regarding the impact of real-time continuous glucose monitoring (rt-CGM) on reducing adverse pregnancy outcomes in women with gestational diabetes are contradictory. We aimed to assess differences in the proportion of large-for-gestational-age (LGA) newborns between women using rt-CGM versus self-monitoring of blood glucose (SMBG). METHODS: For this open-label, parallel-group, multicentre, randomised controlled trial, women aged 18-55 years with singleton pregnancy and gestational diabetes (diagnosed according to the International Association of the Diabetes and Pregnancy Study Groups criteria), were randomly assigned (1:1) to rt-CGM or SMBG. The first allocation was by chance; for subsequent allocations, minimisation was used to balance three prespecified factors: gestational age at study entry, previous gestational diabetes, and preconceptional BMI. SMBG participants used blinded CGM for 10 days after randomisation and at 36-38 weeks; rt-CGM participants used open rt-CGM until delivery. All were managed according to standard care protocols in four university hospitals in Austria, Germany, and Switzerland. The primary endpoint was the proportion of LGA newborns (using the Perinatal Institute's GROW customised birthweight percentiles), assessed in the intention-to-treat population. Secondary endpoints included the requirement for glucose-lowering medication, CGM metrics, and non-glycaemic maternal and neonatal outcomes. Recruitment and follow-up are complete. This study is registered with ClinicalTrials.gov (NCT03981328). FINDINGS: Between Aug 24, 2020, and May 30, 2024, 610 women were screened for eligibility, of whom 375 (diagnosed with gestational diabetes at a mean of 25·2 weeks [SD 2·3] of gestation), were randomly assigned to rt-CGM (n=190) or SMBG (n=185) at a mean of 28·6 weeks (SD 1·9) of gestation. 170 intervention and 175 control participants with available data were assessed for the primary endpoint. LGA neonates were born to six (4%) of 170 rt-CGM and 18 (10%) of 175 SMBG participants (OR 0·32, 95% CI 0·10-0·87, p=0·014). Small-for-gestational-age (SGA) neonates were born to 33 (19%) and 23 (13%) participants, respectively (OR 1·59, 0·86-2·99, p=0·11). Serious adverse events occurred in 23 (12%) of 190 versus 28 (15%) of 185 participants (OR 0·77, 0·42-1·40, p=0·39). INTERPRETATION: rt-CGM use in women with gestational diabetes reduced LGA births, without differences in serious adverse events. The higher-than-expected overall prevalence of SGA infants, possibly related to the tight glycaemic control in our cohort, requires further research.Dexcom. TRANSLATION: For the German translation of the abstract see Supplementary Materials section.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354813

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

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

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

Sensors and Devices Based on Electrochemical Skin Conductance and Bioimpedance Measurements for the Screening of Diabetic Foot Syndrome: Review and Meta-Analysis
BIOSENSORS
Autore/i: Verdini, F.; Mengarelli, A.; Chemello, G.; Salvatori, B.; Morettini, M.; Gobl, C.; Tura, A.
Classificazione: 1 Contributo su Rivista
Abstract: Diabetic foot syndrome is a multifactorial disease involving different etiological factors. This syndrome is also insidious, due to frequent lack of early symptoms, and its prevalence has increased in recent years. This justifies the remarkable attention being paid to the syndrome, although the problem of effective early screening for this syndrome, possibly at a patient’s home, is still unsolved. However, some options appear available in this context. First, it was demonstrated that the temperature measurement of the foot skin is an interesting approach, but it also has some limitations, and hence a more effective approach should combine data from temperature and from other sensors. For this purpose, foot skin conductance or bioimpedance measurement may be a good option. Therefore, the aim of this study was to review those studies where skin conductance/bioimpedance measurement was used for the detection of diabetic foot syndrome. In addition, we performed a meta-analysis of some of those studies, where a widely used device was exploited (SUDOSCAN®) for foot skin conductance measurement, and we found that skin conductance levels can clearly distinguish between groups of patients with and without diabetic neuropathy, the latter being one of the most relevant factors in diabetic foot syndrome.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/341834

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

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

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

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

Towards Prediabetes Detection from Generative AI-Augmented Continuous Glucose Monitoring of Postprandial Glycemic Response using Bi-LSTM
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.; Marraudino, F.; 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: Prediabetes is an intermediate condition between normal glucose tolerance and diabetes. An early detection of such condition is important to prevent diabetes onset and its associated complications. An opportunity for at-home diagnosis could be found in the diffusion of Continuous Glucose Monitoring (CGM) devices, which provide interstitial glucose measurements every 1 to 15 minutes. Artificial Intelligence (AI) can be exploited for the development of clinical decision support systems for CGM-based early detection of prediabetes. Moreover, given the paucity of freely available CGM data with meal information, the developed approaches may benefit from data augmentation strategies based on Generative Adversarial Networks (GANs). Aim of this study was to perform binary sequence-to-label classification of CGM time-series into prediabetes (PD) and normal (CNT) postprandial glycemic response categories using a bidirectional long-short term memory (Bi-LSTM) network. Moreover, synthetic standardized meals were generated leveraging GANs for model pretraining, i.e., to obtain a better model initialization. CGM tracings recorded from 30 participants during standardized meals were labelled as CNT or as PD according to the standard definition of prediabetes. Then, 150 non-standardized meals were generated, having the same proportions of PD and CNT as in the real dataset. Results achieved a testing classification accuracy of 77.8% when trained on the real dataset and of 80% when using the augmented dataset during model pretraining. In conclusion, although confirmation would be required on real non-standardized meal data, the proposed Bi-LSTM-based approach revealed the possibility to detect prediabetes from CGM data acquired during a meal.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354982

Gestational Diabetes Mellitus Subtypes Derived by Clustering Analysis Show Heterogeneity in Glucometabolic Parameters Already at Early Pregnancy
NUTRIENTS
Autore/i: Kotzaeridi, Grammata; Salvatori, Benedetta; Piersanti, Agnese; Heinzl, Florian; Zarotti, Sophie; Kiss, Herbert; Wegener, Silke; Dressler-Steinbach, Iris; Henrich, Wolfgang; Morettini, Micaela; Tura, Andrea; Göbl, Christian S.
Classificazione: 1 Contributo su Rivista
Abstract: Background/Objectives: The classification of patients with diabetes into phenotypes with distinct risks and therapeutic needs is crucial for individualized care. We recently introduced a clustering model for gestational diabetes mellitus (GDM). This study aims to further characterize the proposed clusters and to identify cluster-specific differences in glucometabolic parameters during early pregnancy in an independent cohort. The metabolic profiles and dietary habits of GDM clusters will be compared with those of a normal glucose-tolerant (NGT) control group. Methods: 1088 women (195 who developed GDM and 893 who remained NGT) underwent a broad risk evaluation at early pregnancy. GDM patients were further categorized into the three proposed GDM subtypes (CL1 to CL3). Results: Among GDM patients, 7.7% were classified as CL1, 35.9% as CL2, and 56.4% as CL3. CL1 showed higher age, pregestational BMI, and increased glucose concentrations both at fasting and during the diagnostic oral glucose tolerance test. CL2 was characterized by elevated BMI and fasting glucose, while CL3 showed higher glucose concentrations after the oral glucose load, with BMI levels comparable to NGT mothers. Women in the CL1 group exhibited impaired insulin sensitivity and β-cell function at early pregnancy and showed elevated lipid levels. Compared to NGT women, a positive family history of diabetes was more prevalent in CL1 and CL3, but not in CL2. Dietary patterns were similar across all groups. Conclusions: Our study showed distinct alterations in glucometabolic parameters already at early pregnancy among GDM subtypes. Patients in CL1 exhibited the most unfavorable risk constellation and could benefit from lifestyle changes and nutrition therapy in early pregnancy, despite showing similar dietary patterns as the NGT group.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/350954

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

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

Generating Synthetic Metabolic and Hormonal Data via Physiological In-Silico Modelling: Assessment of Reliability in Different Fitness Conditions
Conference Proceedings - 2025 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2025
Autore/i: Palumbo, M. C.; Morettini, M.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Synthetic data generation is helpful when real data are not easily available; this often happens in the medical field, as real data can be not only private but also expensive, such as those requiring blood sampling. In this work, we present a dataset generated by a previously developed and validated computational modelling approach consisting of 139 ordinary differential equations, adapted to account for individual variability in the metabolic and hormonal changes that occur in response to eating meals and performing physical exercise. The generated dataset consists of a total of 1080 virtual subjects, spanning different fitness classes (fair and excellent) and undergoing exercises differing in modality (arm and leg cycling, running, stepping and walking) and intensity levels (low and high). The response in terms of oxygen consumption, plasma concentrations of epinephrine, glucose, and insulin is considered to evaluate model performance in capturing different fitness conditions and exercise modalities. Oxygen consumption, expressed as a percentage of the individual maximum, shows saturation values consistent with the target values computed considering the modality and intensity of exercise, as well as the fitness class of the subject. Moreover, oxygen consumption in some cases exceeds 100%, thus suggesting a lack of coherence between the exercise and the subject's characteristics. Epinephrine responses show lower values for trained individuals than for untrained ones, according to the findings of the literature. Trends for glycemia and insulinemia show that, considering the same intensity and modality of exercise, non-trained individuals experience a more pronounced decrease compared to trained ones.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354978

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

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

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

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

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)
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354888

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

Machine Learning-Based Indices Assessing Different Aspects of Beta-Cell Function in Pregnancy
Advances in Digital Health and Medical Bioengineering
Autore/i: Salvatori, B; Piersanti, A; Linder, T; Eppe, D; Morettini, M; Gob, C; Tura, A
Editore: SPRINGER INTERNATIONAL PUBLISHING AG
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Accurate assessment of pancreatic beta-cell function parameters, such as glucose sensitivity (G-Sens), rate sensitivity (R-Sens), and potentiation factor ratio (PFR), relies on mathematical modelling coupled with C-peptide measurement, both not always accessible in clinical settings. Machine learning may provide surrogate markers of model-and-C-peptide-based parameters. Aim of the study was to leverage machine learning to build predictive equations of G-Sens, R-Sens, and PFR in pregnant women, without the need of modeling and C-peptide. To this aim, predictive approaches were implemented (multivariate polynomial regressions), under different scenarios of data availability. We found that G-Sens prediction showed good performance (R-adj(2) = 0.45, p<0.0001 in test set), whereas results were unsatisfactory for R-Sens. PFR prediction showed moderate performance (R-adj(2) = 0.33, p < 0.01 in test set). In conclusion, machine learning is appropriate for G-Sens and PFR prediction, while R-Sens prediction appears hardly feasible.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/337438

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

Feature Engineering Assessment of Tumor Infiltrating Lymphocytes in Lung Adenocarcinoma
2024
Autore/i: Bruschi, G.; Sbrollini, A.; Pecci, F.; Cognigni, V.; Paoloni, F.; Galassi, T.; Cantini, L.; Morettini, M.; Berardi, R.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354883

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

Glucagon kinetics assessed by mathematical modelling during oral glucose administration in people spanning from normal glucose tolerance to type 2 diabetes
FRONTIERS IN ENDOCRINOLOGY
Autore/i: Andreozzi, F; Mancuso, E; Rubino, M; Salvatori, B; Morettini, M; Monea, G; Göbl, C; Mannino, Gc; Tura, A
Classificazione: 1 Contributo su Rivista
Abstract: Background/Objectives: Glucagon is important in the maintenance of glucose homeostasis, with also effects on lipids. In this study, we aimed to apply a recently developed model of glucagon kinetics to determine the sensitivity of glucagon variations (especially, glucagon inhibition) to insulin levels ("alpha-cell insulin sensitivity"), during oral glucose administration.Subjects/Methods: We studied 50 participants (spanning from normal glucose tolerance to type 2 diabetes) undergoing frequently sampled 5-hr oral glucose tolerance test (OGTT). The alpha-cell insulin sensitivity and the glucagon kinetics were assessed by a mathematical model that we developed previously.Results: The alpha-cell insulin sensitivity parameter (named S-GLUCA; "GLUCA": "glucagon") was remarkably variable among participants (CV=221%). SGLUCA was found inversely correlated with the mean glycemic values, as well as with 2-hr glycemia of the OGTT. When stratifying participants into two groups (normal glucose tolerance, NGT, N=28, and impaired glucose regulation/type 2 diabetes, IGR_T2D, N=22), we found that S-GLUCA was lower in the latter (1.50 +/- 0.50.10(-2) vs. 0.26 +/- 0.14.10(-2) ng.L-GLUCA(-1)/pmol.L-INS(-1), in NGT and IGR_T2D, respectively, p=0.009; "INS": "insulin").Conclusions: The alpha-cell insulin sensitivity is highly variable among subjects, and it is different in groups at different glucose tolerance. This may be relevant for defining personalized treatment schemes, in terms of dietary prescriptions but also for treatments with glucagon-related agents.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/329421

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

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

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

Selection of Dataframes Presenting Glioma from Magnetic Resonance Images: A Deep Learning Approach
2024
Autore/i: Bruschi, G.; Vassallo, F.; Sbrollini, A.; Morettini, M.; Burattini, L.
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

Into-the-Field Assessment of Maximal Heart Rate during Exercise
51
Autore/i: Sbrollini, A.; Morettini, M.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354876

Glucometabolism in Kidney Transplant Recipients with and without Posttransplant Diabetes: Focus on Beta-Cell Function
BIOMEDICINES
Autore/i: Kurnikowski, A.; Salvatori, B.; Krebs, M.; Budde, K.; Eller, K.; Pascual, J.; Morettini, M.; Gobl, C.; Hecking, M.; Tura, A.
Classificazione: 1 Contributo su Rivista
Abstract: Posttransplant diabetes mellitus (PTDM) is a common complication after kidney transplantation. Pathophysiologically, whether beta-cell dysfunction rather than insulin resistance may be the predominant defect in PTDM has been a matter of debate. The aim of the present analysis was to compare glucometabolism in kidney transplant recipients with and without PTDM. To this aim, we included 191 patients from a randomized controlled trial who underwent oral glucose tolerance tests (OGTTs) 6 months after transplantation. We derived several basic indices of beta-cell function and insulin resistance as well as variables from mathematical modeling for a more robust beta-cell function assessment. Mean ± standard deviation of the insulin sensitivity parameter PREDIM was 3.65 ± 1.68 in PTDM versus 5.46 ± 2.57 in NON-PTDM. Model-based glucose sensitivity (indicator of beta-cell function) was 68.44 ± 57.82 pmol∙min−1∙m−2∙mM−1 in PTDM versus 143.73 ± 112.91 pmol∙min−1∙m−2∙mM−1 in NON-PTDM, respectively. Both basic indices and model-based parameters of beta-cell function were more than 50% lower in patients with PTDM, indicating severe beta-cell impairment. Nonetheless, some defects in insulin sensitivity were also present, although less marked. We conclude that in PTDM, the prominent defect appears to be beta-cell dysfunction. From a pathophysiological point of view, patients at high risk for developing PTDM may benefit from intensive treatment of hyperglycemia over the insulin secretion axis.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/329435

Identification and validation of gestational diabetes subgroups by data-driven cluster analysis
DIABETOLOGIA
Autore/i: Salvatori, B.; Wegener, S.; Kotzaeridi, G.; Herding, A.; Eppel, F.; Dressler-Steinbach, I.; Henrich, W.; Piersanti, A.; Morettini, M.; Tura, A.; Gobl, C. S.
Classificazione: 1 Contributo su Rivista
Abstract: Aims/hypothesis: Gestational diabetes mellitus (GDM) is a heterogeneous condition. Given such variability among patients, the ability to recognise distinct GDM subgroups using routine clinical variables may guide more personalised treatments. Our main aim was to identify distinct GDM subtypes through cluster analysis using routine clinical variables, and analyse treatment needs and pregnancy outcomes across these subgroups. Methods: In this cohort study, we analysed datasets from a total of 2682 women with GDM treated at two central European hospitals (1865 participants from Charité University Hospital in Berlin and 817 participants from the Medical University of Vienna), collected between 2015 and 2022. We evaluated various clustering models, including k-means, k-medoids and agglomerative hierarchical clustering. Internal validation techniques were used to guide best model selection, while external validation on independent test sets was used to assess model generalisability. Clinical outcomes such as specific treatment needs and maternal and fetal complications were analysed across the identified clusters. Results: Our optimal model identified three clusters from routinely available variables, i.e. maternal age, pre-pregnancy BMI (BMIPG) and glucose levels at fasting and 60 and 120 min after the diagnostic OGTT (OGTT0, OGTT60 and OGTT120, respectively). Cluster 1 was characterised by the highest OGTT values and obesity prevalence. Cluster 2 displayed intermediate BMIPG and elevated OGTT0, while cluster 3 consisted mainly of participants with normal BMIPG and high values for OGTT60 and OGTT120. Treatment modalities and clinical outcomes varied among clusters. In particular, cluster 1 participants showed a much higher need for glucose-lowering medications (39.6% of participants, compared with 12.9% and 10.0% in clusters 2 and 3, respectively, p<0.0001). Cluster 1 participants were also at higher risk of delivering large-for-gestational-age infants. Differences in the type of insulin-based treatment between cluster 2 and cluster 3 were observed in the external validation cohort. Conclusions/interpretation: Our findings confirm the heterogeneity of GDM. The identification of subgroups (clusters) has the potential to help clinicians define more tailored treatment approaches for improved maternal and neonatal outcomes
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/332573

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

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

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

An in-silico modeling approach to separate exogenous and endogenous plasma insulin appearance, with application to inhaled insulin
SCIENTIFIC REPORTS
Autore/i: Piersanti, A.; Pacini, G.; Tura, A.; D'Argenio, D. Z.; Morettini, M.
Classificazione: 1 Contributo su Rivista
Abstract: The aim of this study was to develop a dynamic model-based approach to separately quantify the exogenous and endogenous contributions to total plasma insulin concentration and to apply it to assess the effects of inhaled-insulin administration on endogenous insulin secretion during a meal test. A three-step dynamic in-silico modeling approach was developed to estimate the two insulin contributions of total plasma insulin in a group of 21 healthy subjects who underwent two equivalent standardized meal tests on separate days, one of which preceded by inhalation of a Technosphere® Insulin dose (22U or 20U). In the 30–120 min test interval, the calculated endogenous insulin component showed a divergence in the time course between the test with and without inhaled insulin. Moreover, the supra-basal area-under-the-curve of endogenous insulin in the test with inhaled insulin was significantly lower than that in the test without (2.1 ± 1.7 × 104 pmol·min/L vs 4.2 ± 1.8 × 104 pmol·min/L, p < 0.01). The percentage of exogenous insulin reaching the plasma, relative to the inhaled dose, was 42 ± 21%. The proposed in-silico approach separates exogenous and endogenous insulin contributions to total plasma insulin, provides individual bioavailability estimates, and can be used to assess the effect of inhaled insulin on endogenous insulin secretion during a meal.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/332572

Handwritten Digits Recognition from sEMG: Electrodes Location and Feature Selection
IEEE ACCESS
Autore/i: Tigrini, A.; Verdini, F.; Scattolini, M.; Barbarossa, F.; Burattini, L.; Morettini, M.; Fioretti, S.; Mengarelli, A.
Classificazione: 1 Contributo su Rivista
Abstract: Objective: Despite hand gesture recognition is a widely investigated field, the design of myoelectric architectures for detecting finer motor task, like the handwriting, is less studied. However, writing tasks involving cognitive loads represent an important aspect toward the generalization of myoelectric-based human-machine interfaces (HMI), and also for many rehabilitative tasks. In this study, the handwriting recognition of the ten digits was faced under the myoelectric control perspective, considering the probes setup and the feature extraction step. Methods: Time and frequency domain features were extracted from surface electromyography (sEMG) signals of 11 subjects who wrote the ten digits following a standardized template and 8 sEMG probes were equally distributed between forearm and wrist. Feature class separability was investigated and an aggregated feature set was built to train pattern recognition architectures, i.e. linear discriminant analysis (LDA) and quadratic support vector machine (QSVM). Also, four reduced probes setups were investigated. Results: LDA and QSVM showed mean accuracy of about 97%, with all the forearm and wrist sEMG information. A significant reduction of performances was observed considering the wrist or the forearm only (≤92%) and when LDA and QSVM were trained with two electrodes information (≤90%). Conclusions: For the reliable classification performances in a motor task involving high cognitive demands, like the handwriting, it is required the use of probes fully covering forearm and wrist. Outcomes support the methodological transfer from myoelectric hand gesture to the handwriting recognition, which represents a key aspect in the development of new HMI for rehabilitation tasks.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/318071

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

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

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

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

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

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

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

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

A computational model of the effects of macronutrients absorption and physical exercise on hormonal regulation and metabolic homeostasis
COMPUTERS IN BIOLOGY AND MEDICINE
Autore/i: Palumbo, M. C.; de Graaf, A. A.; Morettini, M.; Tieri, P.; Krishnan, S.; Castiglione, F.
Classificazione: 1 Contributo su Rivista
Abstract: Regular physical exercise and appropriate nutrition affect metabolic and hormonal responses and may reduce the risk of developing chronic non-communicable diseases such as high blood pressure, ischemic stroke, coronary heart disease, some types of cancer, and type 2 diabetes mellitus. Computational models describing the metabolic and hormonal changes due to the synergistic action of exercise and meal intake are, to date, scarce and mostly focussed on glucose absorption, ignoring the contribution of the other macronutrients. We here describe a model of nutrient intake, stomach emptying, and absorption of macronutrients in the gastrointestinal tract during and after the ingestion of a mixed meal, including the contribution of proteins and fats. We integrated this effort to our previous work in which we modeled the effects of a bout of physical exercise on metabolic homeostasis. We validated the computational model with reliable data from the literature. The simulations are overall physiologically consistent and helpful in describing the metabolic changes due to everyday life stimuli such as multiple mixed meals and variable periods of physical exercise over prolonged periods of time. This computational model may be used to design virtual cohorts of subjects differing in sex, age, height, weight, and fitness status, for specialized in silico challenge studies aimed at designing exercise and nutrition schemes to support health.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/319951

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

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

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

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 Double-Stage 3D U-Net for On-Cloud Brain Extraction and Multi-Structure Segmentation from 7T MR Volumes
INFORMATION
Autore/i: Tomassini, S.; Anbar, H.; Sbrollini, A.; Mortada, M. H. D. J.; Burattini, L.; Morettini, M.
Classificazione: 1 Contributo su Rivista
Abstract: The brain is the organ most studied using Magnetic Resonance (MR). The emergence of 7T scanners has increased MR imaging resolution to a sub-millimeter level. However, there is a lack of automatic segmentation techniques for 7T MR volumes. This research aims to develop a novel deep learning-based algorithm for on-cloud brain extraction and multi-structure segmentation from unenhanced 7T MR volumes. To this aim, a double-stage 3D U-Net was implemented in a cloud service, directing its first stage to the automatic extraction of the brain and its second stage to the automatic segmentation of the grey matter, basal ganglia, white matter, ventricles, cerebellum, and brain stem. The training was performed on the 90% (the 10% of which served for validation) and the test on the 10% of the Glasgow database. A mean test Dice Similarity Coefficient (DSC) of 96.33% was achieved for the brain class. Mean test DSCs of 90.24%, 87.55%, 93.82%, 85.77%, 91.53%, and 89.95% were achieved for the brain structure classes, respectively. Therefore, the proposed double-stage 3D U-Net is effective in brain extraction and multi-structure segmentation from 7T MR volumes without any preprocessing and training data augmentation strategy while ensuring its machine-independent reproducibility.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/316995

Glucometabolic Alterations in Pregnant Women with Overweight or Obesity but without Gestational Diabetes Mellitus: An Observational Study
OBESITY FACTS
Autore/i: Linder, T.; Eppel, D.; Kotzaeridi, G.; Yerlikaya-Schatten, G.; Rosicky, I.; Morettini, M.; Tura, A.; Gobl, C. S.
Classificazione: 1 Contributo su Rivista
Abstract: Introduction: Maternal overweight is a risk factor for gestational diabetes mellitus (GDM). However, emerging evidence suggests that an increased maternal body mass index (BMI) promotes the development of perinatal complications even in women who do not develop GDM. This study aims to assess physiological glucometabolic changes associated with increased BMI. Methods: Twenty-one women with overweight and 21 normal weight controls received a metabolic assessment at 13 weeks of gestation, including a 60-min frequently sampled intravenous glucose tolerance test. A further investigation was performed between 24 and 28 weeks in women who remained normal glucose tolerant. Results: At baseline, mothers with overweight showed impaired insulin action, whereby the calculated insulin sensitivity index (CSI) was lower as compared to normal weight controls (3.5 vs. 6.7 10-4 min-1 [microU/mL]-1, p = 0.025). After excluding women who developed GDM, mothers with overweight showed higher average glucose during the oral glucose tolerance test (OGTT) at the third trimester. Moreover, early pregnancy insulin resistance and secretion were associated with increased placental weight in normal glucose-tolerant women. Conclusion: Mothers with overweight or obesity show an unfavorable metabolic environment already at the early stage of pregnancy, possibly associated with perinatal complications in women who remain normal glucose tolerant.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/329436

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

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

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

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

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

Ratio Indexes Based on Spectral Electroencephalographic Brainwaves for Assessment of Mental Involvement: A Systematic Review
SENSORS
Autore/i: Marcantoni, Ilaria; Assogna, Raffaella; Del Borrello, Giulia; Di Stefano, Marina; Morano, Martina; Romagnoli, Sofia; Leoni, Chiara; Bruschi, Giulia; Sbrollini, Agnese; Morettini, Micaela; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: This review systematically examined the scientific literature about electroencephalogram-derived ratio indexes used to assess human mental involvement, in order to deduce what they are, how they are defined and used, and what their best fields of application are. (2) Methods: The review was carried out according to the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines. (3) Results: From the search query, 82 documents resulted. The majority (82%) were classified as related to mental strain, while 12% were classified as related to sensory and emotion aspects, and 6% to movement. The electroencephalographic electrode montage used was low-density in 13%, high-density in 6% and very-low-density in 81% of documents. The most used electrode positions for computation of involvement indexes were in the frontal and prefrontal cortex. Overall, 37 different formulations of involvement indexes were found. None of them could be directly related to a specific field of application. (4) Conclusions: Standardization in the definition of these indexes is missing, both in the considered frequency bands and in the exploited electrodes. Future research may focus on the development of indexes with a unique definition to monitor and characterize mental involvement.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/319611

Advanced repeated structuring and learning procedure to detect acute myocardial ischemia in serial 12-lead ECGs
PHYSIOLOGICAL MEASUREMENT
Autore/i: Sbrollini, A.; Ter Haar, C. C.; Leoni, C.; Morettini, M.; Burattini, L.; Swenne, C. A.
Classificazione: 1 Contributo su Rivista
Abstract: Objectives. Acute myocardial ischemia in the setting of acute coronary syndrome (ACS) may lead to myocardial infarction. Therefore, timely decisions, already in the pre-hospital phase, are crucial to preserving cardiac function as much as possible. Serial electrocardiography, a comparison of the acute electrocardiogram with a previously recorded (reference) ECG of the same patient, aids in identifying ischemia-induced electrocardiographic changes by correcting for interindividual ECG variability. Recently, the combination of deep learning and serial electrocardiography provided promising results in detecting emerging cardiac diseases; thus, the aim of our current study is the application of our novel Advanced Repeated Structuring and Learning Procedure (AdvRS&LP), specifically designed for acute myocardial ischemia detection in the pre-hospital phase by using serial ECG features.Approach. Data belong to the SUBTRACT study, which includes 1425 ECG pairs, 194 (14%) ACS patients, and 1035 (73%) controls. Each ECG pair was characterized by 28 serial features that, with sex and age, constituted the inputs of the AdvRS&LP, an automatic constructive procedure for creating supervised neural networks (NN). We created 100 NNs to compensate for statistical fluctuations due to random data divisions of a limited dataset. We compared the performance of the obtained NNs to a logistic regression (LR) procedure and the Glasgow program (Uni-G) in terms of area-under-the-curve (AUC) of the receiver-operating-characteristic curve, sensitivity (SE), and specificity (SP).Main Results. NNs (median AUC = 83%, median SE = 77%, and median SP = 89%) presented a statistically (Pvalue lower than 0.05) higher testing performance than those presented by LR (median AUC = 80%, median SE = 67%, and median SP = 81%) and by the Uni-G algorithm (median SE = 72% and median SP = 82%).Significance. In conclusion, the positive results underscore the value of serial ECG comparison in ischemia detection, and NNs created by AdvRS&LP seem to be reliable tools in terms of generalization and clinical applicability.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/321191

Feature Contributions to ECG-based Heart-Failure Detection: Deep Learning vs. Statistical Analysis
Computing in Cardiology
Autore/i: Sbrollini, A.; Leoni, C.; De Jongh, M. C.; Morettini, M.; Burattini, L.; Swenne, C. A.
Editore: IEEE Computer Society
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Assessing feature contributions to a specific diagnosis is commonly done by statistical analysis. In the context of heart failure (HF) diagnosis from the electrocardiogram (ECG), this work compares feature contributions assessed by deep learning with those obtained by statistical analysis. Data consists of ECG pairs (baseline and follow-up) from patients with a history of myocardial infarction. When the follow-up ECG was made, controls patients had remained stable, while cases patients had developed HF. The 42 features that characterized each ECG served as inputs of a deep-learning neural network (NN) created by our Repeated Structuring & Learning Procedure. Subject-specific feature ranking was obtained from the local-interpretable model-agnostic explanatory algorithm and processed to obtain feature relevances (FR). Additionally, 42 areas under the curve (AUC) by univariate statistical analysis were obtained. FR and AUC were compared by Pearson's correlation coefficient (p). After training, the NN had a 99% classification performance. FR ranged from 0.32 to 4.47; AUC ranged from 23% to 82%. Correlation analysis yielded no significant association between AUC and FR (ρ=0.18, P-value =0.25). Deep-learning and statistical-analysis feature contributions to HF detection were discordant. Further studies will investigate which of the two approaches better reflects clinical interpretation.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/314453

ECG diagnosis by a multiclass neural network
Journal of Electrocardiology
Autore/i: Sbrollini, Agnese; Mancinelli, Martina; Leoni, Chiara; Marcantoni, Ilaria; Morettini, Micaela; Swenne, Cees A.; Burattini, Laura
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/313187

Identification and Classification of Driving-Related Stress Using Electrocardiogram and Skin Conductance Signals
Proceeding of 17th IEEE International Symposium on Medical Measurements and Applications
Autore/i: Marcantoni, I.; Barchiesi, G.; Barchiesi, S.; Belbusti, C.; Leoni, C.; Romagnoli, S.; Sbrollini, A.; Morettini, M.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The development of on-board car electronics for automatic stress level detection is becoming an area of great interest. The literature showed that biomedical signal acquisition could provide significant information. Skin conductance (SC) and electrocardiogram (ECG) have demonstrated to provide the most significant stress-related features. Thus, the aim of this study is the classification of three-level and binary stress, using a minimal combination of SC and ECG features. The 'Stress Recognition in Automobile Drivers' database was used to test a procedure based on linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA). The database protocol includes three driving periods, corresponding to different levels of stress (low-medium-high). After data preprocessing, LDA and QDA three-level classifications were applied on all the extracted SC and ECG features to determine the best classification approach. Boruta algorithm allowed to select the most significant features for the classification. Then, the best classification approach was applied on this restricted set of features, performing both three-level (low vs medium vs high) and binary (high+medium vs low) stress classification. QDA was the most accurate classification method (accuracy: 96.0% for QDA vs 85.3% for LDA, considering all the features). QDA accuracy, considering only the selected features, was 86.7% for the three-level classification and 94.7% for the binary classification. This result represents an acceptable trade-off between classification accuracy and computational cost, associated to the number of considered features. In conclusion, ECG together with SC are suitable for the objective and automatic identification and classification of driving-related stress with a good accuracy.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/306161

Heart and Breathing Rate Measurement Using Low Intrusive Monitoring Systems
Lecture Notes in Bioengineering
Autore/i: Gaiduk, M.; Orcioni, S.; Seepold, R.; Madrid, N. M.; Pierleoni, P.; Gentili, A.; Burattini, L.; Sbrollini, A.; Marcantoni, I.; Morettini, M.; Conti, M.
Editore: Springer Science and Business Media Deutschland GmbH
Classificazione: 2 Contributo in Volume
Abstract: In many cases continuous monitoring of vital signals is required and low intrusiveness is an important requirement. Incorporating monitoring systems in the hospital or home bed could have benefits for patients and caregivers. The objective of this work is the definition of a measurement protocol and the creation of a data set of measurements using commercial and low-cost prototypes devices to estimate heart rate and breathing rate. The experimental data will be used to compare results achieved by the devices and to develop algorithms for feature extraction of vital signals.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/307682

Neonatal Clinical Outcomes: a Comparative Analysis
Proceeding of 17th IEEE International Symposium on Medical Measurements and Applications
Autore/i: Sbrollini, A.; Romagnoli, S.; Marcantoni, I.; Burattini, L.; Morettini, M.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The most popular neonatal clinical outcomes, which are blood pH (PH), base excess (BE) and Apgar after 5 minutes from birth (AP5), may provide contrasting information. Thus, aim of the paper is to perform a critical evaluation and comparison of PH, BE and AP5. Reliability of neonatal clinical outcomes was evaluated in relation to perinatal features. Neonatal and fetal cardiotocographic data of 391 newborns (CTU-CHB Intrapartum Cardiotocography Database) were analyzed. Newborns were classified as positive (i.e., as showing critical conditions) if PH<7.10 or BE<-10mmol/l or AP5<7, as negative (i.e., as showing healthy conditions) otherwise. Agreement between pairs of neonatal clinical outcomes was evaluated by computing the correlation coefficient. Fetal decelerations were characterized in terms of rate of occurrence, depth, mean, duration, and area. Correlation between PH and BE, PH and AP5 and BE and AP5 was 0.83, 0.45 and 0.38 (P<0.01), respectively; 329 newborns (84%) were equally classified by all neonatal clinical outcomes, 5 as positive and 324 as negative. Deceleration depth and rate of occurrence were comparable among positive/negative classes, while deceleration mean, duration and area were systematically higher in the positive than in the negative classes, also statistically only for PH classification. Positive class by PH counted the highest number of small newborns; large newborns were similarly distributed over all positive classes. Objective neonatal clinical outcomes, and in particular PH, seems to be more reliable than subjective clinical outcomes, and thus should be preferable for describing neonatal health status.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/306163

Role of the Window Length for Myoelectric Pattern Recognition in Detecting User Intent of Motion
Proceeding of 17th IEEE International Symposium on Medical Measurements and Applications
Autore/i: Tigrini, A.; Scattolini, M.; Mengarelli, A.; Fioretti, S.; Morettini, M.; Burattini, L.; Verdini, F.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In this study, the problem of electromyographic (EMG) based motion intention detection (MID) of upper limb was addressed, investigating the role of the window length for feature extraction. Two pattern recognition experiments were performed taking into account eight healthy subjects. The first involved the direct comparison of classification performances using feature computed over 150, 100 and 50 ms window length for eight class of shoulder movements. In the second one, a feature fusing scheme, based on canonical correlation analysis (CCA), was used to investigate whether pattern recognition architectures (PRAs), i.e. support vector machine, were able to boost their performances when 50 ms features were used as testing set. The rationale behind such investigations grounds on the lack of consensus regarding the most suitable window length for myoelectic pattern recognition. No drop of accuracy was observed in the first experiment for the three different windows length, maintaining values around 90%. Moreover, as observed in the second experiment, the CCA feature fusing scheme enhanced the performances of the PRAs when working over 50 ms features, reaching comparable results with feature at 150 ms. The proposed approach can be suitable for MID in real-time scenario, where the computational represents a central issue.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/306162

Artificial Intelligence Methodologies Applied to Technologies for Screening, Diagnosis and Care of the Diabetic Foot: A Narrative Review
BIOSENSORS
Autore/i: Chemello, Gaetano; Salvatori, Benedetta; Morettini, Micaela; Tura, Andrea
Classificazione: 1 Contributo su Rivista
Abstract: Diabetic foot syndrome is a multifactorial pathology with at least three main etiological factors, i.e., peripheral neuropathy, peripheral arterial disease, and infection. In addition to complexity, another distinctive trait of diabetic foot syndrome is its insidiousness, due to a frequent lack of early symptoms. In recent years, it has become clear that the prevalence of diabetic foot syndrome is increasing, and it is among the diabetes complications with a stronger impact on patient's quality of life. Considering the complex nature of this syndrome, artificial intelligence (AI) methodologies appear adequate to address aspects such as timely screening for the identification of the risk for foot ulcers (or, even worse, for amputation), based on appropriate sensor technologies. In this review, we summarize the main findings of the pertinent studies in the field, paying attention to both the AI-based methodological aspects and the main physiological/clinical study outcomes. The analyzed studies show that AI application to data derived by different technologies provides promising results, but in our opinion future studies may benefit from inclusion of quantitative measures based on simple sensors, which are still scarcely exploited.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/309949

Chemical Compounds and Ambient Factors Affecting Pancreatic Alpha-Cells Mass and Function: What Evidence?
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
Autore/i: Mannino, G. C.; Mancuso, E.; Sbrignadello, S.; Morettini, M.; Andreozzi, F.; Tura, A.
Classificazione: 1 Contributo su Rivista
Abstract: The exposure to different substances present in the environment can affect the ability of the human body to maintain glucose homeostasis. Some review studies summarized the current evidence about the relationships between environment and insulin resistance or beta-cell dysfunction. Instead, no reviews focused on the relationships between the environment and the alpha cell, although in recent years clear indications have emerged for the pivotal role of the alpha cell in glucose regulation. Thus, the aim of this review was to analyze the studies about the effects of chemical, biological, and physical environmental factors on the alpha cell. Notably, we found studies focusing on the effects of different categories of compounds, including air pollutants, compounds of known toxicity present in common objects, pharmacological agents, and compounds possibly present in food, plus studies on the effects of physical factors (mainly heat exposure). However, the overall number of relevant studies was limited, especially when compared to studies related to the environment and insulin sensitivity or beta-cell function. In our opinion, this was likely due to the underestimation of the alpha-cell role in glucose homeostasis, but since such a role has recently emerged with increasing strength, we expect several new studies about the environment and alpha-cell in the near future.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/309611

Empirical Index for Easy Assessment of Pancreatic Beta-Cell Glucose Sensitivity During Pregnancy: A Machine Learning Approach
2022 10th E-Health and Bioengineering Conference, EHB 2022
Autore/i: Salvatori, B.; Linder, T.; Eppel, D.; Morettini, M.; Gobl, C.; Tura, A.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Based on data measured during an oral glucose tolerance test, machine learning techniques were implemented to derive a simple empirical index for the estimation of the pancreatic beta-cell function in pregnant women, as assessed by mathematical modelling (beta-cell glucose sensitivity parameters). We studied a group of 84 pregnant women, who were analyzed by measuring and assessing a wide set of variables and parameters. Through a LASSO regularized support vector machine, we analyzed such wide batteries of variables/parameters and identified an index based on a simple algebraic equation (including glucose and C-peptide measurements only), which can predict the beta-cell glucose sensitivity with good accuracy (R2=0.64, p<0.0001, in the test set). In conclusion, the index is a good surrogate marker for the assessment of model-based beta-cell glucose sensitivity in pregnant women, thus it can be useful for easy application in the clinical context, where modelling analysis is not always possible.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/312748

Circadian Modulation of Electrocardiographic Alternans in Kidney Failure Patients on Dialysis
Computing in Cardiology
Autore/i: Marcantoni, I.; Leoni, C.; Peroni, C.; Sbrollini, A.; Morettini, M.; Burattini, L.
Editore: IEEE Computer Society
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Circadian rhythm (periodicity: 24 h) can modulate trends of indices based on the electrocardiogram (ECG), as ECG alternans (ABAB fluctuation of ECG waves; ECGA). This work aims to verify if circadian rhythm modulates ECGA in kidney failure patients - to our knowledge, not investigated yet - and to study the effect of dialysis treatment. ECGA was analyzed on 51 long-term (48 h on average) 12-lead ECG from end-stage renal disease (ESRD) patients. Acquisitions included dialysis, night after, and following day and night. Measures of P-wave, QRS-complex and T-wave alternans (PWA, QRSA, and TWA, respectively; μ V were obtained using the enhanced adaptive matched filter method. Results indicate that, in dialysis-free days, ECGA trend was affected by circadian modulation. PWA/QRSA/TWA trends reached their minima during the night and their maxima during the day (lead average, 7/9/16 μ V and 11/16/20 μ V, respectively; p<0.05). Dialysis interrupted ECGA circadian periodicity, reducing daytime PWA/QRSA/TWA (lead average, 8/12/17 μ V. Generally, ECGA values increased from dialysis to 24 h after, by +39%, +31% and +20% for PWA, QRSA, and TWA, respectively. Thus, in our ESRD population, circadian modulation affected ECGA, and dialysis treatment interrupted its periodicity, causing a decrement of ECGA.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/314452

Multiclass Convolutional Neural Networks for Atrial Fibrillation Classification
Proceeding of the Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Autore/i: Sbrollini, Agnese; Tomassini, Selene; Emaldi, Enrico; Marcantoni, Ilaria; Morettini, Micaela; Dragoni, Aldo F; Burattini, Laura
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Atrial fibrillation (AF) is a common supraventricular arrhythmia. Its automatic identification by standard 12-lead electrocardiography (ECG) is still challenging. Recently, deep learning provided new instruments able to mimic the diagnostic ability of clinicians but only in case of binary classification (AF vs. normal sinus rhythm-NSR). However, binary classification is far from the real scenarios, where AF has to be discriminated also from several other physiological and pathological conditions. The aim of this work is to present a new AF multiclass classifier based on a convolutional neural network (CNN), able to discriminate AF from NSR, premature atrial contraction (PAC) and premature ventricular contraction (PVC). Overall, 2796 12-lead ECG recordings were selected from the open-source "PhysioNet/Computing in Cardiology Challenge 2021" database, to construct a dataset constituted by four balanced classes, namely AF class, PAC class, PVC class, and NSR class. Each lead of each ECG recording was decomposed into spectrogram by continuous wavelet transform and saved as 2D grayscale images, used to feed a 6-layers CNN. Considering the same CNN architecture, a multiclass classifiers (all classes) and three binary classifiers (AF class, PAC class, and PVC class vs. NSR class) were created and validated by a stratified shuffle split cross-validation of 10 splits. Performance was quantified in terms of area under the curve (AUC) of the receiver operating characteristic. Multiclass classifier performance was high (AF class: 96.6%; PAC class: 95.3%; PVC class: 92.8%; NSR class: 97.4%) and preferable to binary classifiers. Thus, our CNN AF multiclass classifier proved to be an efficient tool for AF discrimination from physiological and pathological confounders. Clinical Relevance-Our CNN AF multiclass classifier proved to be suitable for AF discrimination in real scenarios.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/306481

Cloud-YLung for Non-Small Cell Lung Cancer Histology Classification from 3D Computed Tomography Whole-Lung Scans
Proceedings of the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Autore/i: Tomassini, Selene; Falcionelli, Nicola; Sernani, Paolo; Sbrollini, Agnese; Morettini, Micaela; Burattini, Laura; Dragoni, Aldo Franco
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Non-Small Cell Lung Cancer (NSCLC) represents up to 85% of all malignant lung nodules. Adenocarcinoma and squamous cell carcinoma account for 90% of all NSCLC histotypes. The standard diagnostic procedure for NSCLC histotype characterization implies cooperation of 3D Computed Tomography (CT), especially in the form of low-dose CT, and lung biopsy. Since lung biopsy is invasive and challenging (especially for deeply-located lung cancers and for those close to blood vessels or airways), there is the necessity to develop non-invasive procedures for NSCLC histology classification. Thus, this study aims to propose Cloud-YLung for NSCLC histology classification directly from 3D CT whole-lung scans. With this aim, data were selected from the openly-accessible NSCLC-Radiomics dataset and a modular pipeline was designed. Automatic feature extraction and classification were accomplished by means of a Convolutional Long Short-Term Memory (ConvLSTM)-based neural network trained from scratch on a scalable GPU cloud service to ensure a machine-independent reproducibility of the entire framework. Results show that Cloud- YLung performs well in discriminating both NSCLC histotypes, achieving a test accuracy of 75% and AUC of 84%. Cloud-YLung is not only lung nodule segmentation free but also the first that makes use of a ConvLSTM-based neural network to automatically extract high-throughput features from 3D CT whole-lung scans and classify them. Clinical relevance- Cloud-YLung is a promising framework to non-invasively classify NSCLC histotypes. Preserving the lung anatomy, its application could be extended to other pulmonary pathologies using 3D CT whole-lung scans.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/306482

Sport?Sicuro! A Graphical User Interface for Continuous Cardiovascular Monitoring while Playing Sport Based on Heart Rate and Heart-Rate Variability
2022 Computing in Cardiology (CinC)
Autore/i: Romagnoli, S.; Sbrollini, A.; Marcantoni, I.; Morettini, M.; Burattini, L.
Editore: IEEE Computer Society
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Heart rate (HR) and heart-rate variability (HRV) are increasingly used to assess the body response to heavy physical effort and to define cardiovascular risk indices for sport related sudden cardiac death. The complexity of physiological phenomena affecting HR and HRV makes difficult the interpretation of measures provided by commercial wearable technologies for athletes and trainers. Availability of interactive applications for analysis of HR series can optimize continuous cardiovascular self-monitoring while training. This paper proposes Sport?Sicuro!, a graphical user interface that allows automatic computation of prevention and performance indexes from HR series for cardiovascular monitoring while practicing sport. This tool is an interactive instrument to support self-monitoring of athletes as well as the work of sport medicine clinicians. Sport?Sicuro! was developed under MATLAB. Automatic analysis of HR series is based on some unchangeable features definitions provided in literature, and other arbitrary settings, the default values of which can be changed by the user. Eventually, Sport?Sicuro! provides a report file listing all the quantitative results of the HR analysis. Thus, Sport?Sicuro! represents a potentially useful graphical tool for automatic and objective analysis of HR series in sport.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/314454

Segmented-Beat Modulation Method-Based Procedure for Extraction of Electrocardiogram-Derived Respiration from Data Acquired by Wearable Sensors During High-Altitude Activity
Computing in Cardiology
Autore/i: Sbrollini, A.; Bondi, D.; Romagnoli, S.; Morettini, M.; Marcantoni, I.; Pietrangelo, T.; Verratti, V.; Burattini, L.
Editore: IEEE Computer Society
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: High-altitude sports are affected by hypoxic stress-related alterations and, consequently, may trigger severe events such as sport-related sudden death; thus, into-the-jield monitoring of respiration is essential. A Segmented-Beat Modulation Method (SBMM)-based procedure was previously proposed to extract electrocardiogram (ECG)- derived respiration (EDR). The aim of this study is to validate SBMM-based procedure for EDR extraction in data acquired by wearable sensors during high-altitude physical activities. Respiration signal (RES) and ECG were recorded using BioHarness 3.0 by Zephyr from 3 expeditioners, while performing a trek up to 4, 556m of altitude. EDR it was extracted from ECG by SBMM-based procedure. RES and EDR were segmented into 60-second windows and characterized in terms of breathing rate (BRRES and BREDR, respectively). BRRES and BREDR were compared by absolute difference (|δ|), concordance correlation coefficient (CCC) and linear regression analysis. Results confirmed EDR goodness, proved by low values of |δ| (2[1;4]cpm), satisfactory CCC(0.62; P-value < 0.05) and good fit of regression line (BRRES=0.91· BREDR+4.47cpm). In conclusion, SBMM-based procedure is a good method to extract EDR from data acquired by wearable sensors during high-altitude physical activities.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/314455

Estimation of Tidal Volume during Exercise Stress Test from Wearable-Device Measures of Heart Rate and Breathing Rate
APPLIED SCIENCES
Autore/i: Sbrollini, A; Catena, R; Carbonari, F; Bellini, A; Sacchetti, M; Burattini, L; Morettini, M
Classificazione: 1 Contributo su Rivista
Abstract: Tidal volume (TV), defined as the amount of air that moves in or out of the lungs with each respiratory cycle, is important in evaluating the respiratory function. Although TV can be reliably measured in laboratory settings, this information is hardly obtainable under everyday living conditions. Under such conditions, wearable devices could provide valuable support to monitor vital signs, such as heart rate (HR) and breathing rate (BR). The aim of this study was to develop a model to estimate TV from wearable-device measures of HR and BR during exercise. HR and BR were acquired through the Zephyr Bioharness 3.0 wearable device in nine subjects performing incremental cycling tests. For each subject, TV during exercise was obtained with a metabolic cart (Cosmed). A stepwise regression algorithm was used to create the model using as possible predictors HR, BR, age, and body mass index; the model was then validated using a leave-one-subject-out cross-validation procedure. The performance of the model was evaluated using the explained variance (R-2), obtaining values ranging from 0.65 to 0.72. The proposed model is a valid method for TV estimation with wearable devices and can be considered not subject-specific and not instrumentation-specific.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/304475

Brain-on-Cloud for automatic diagnosis of Alzheimer's disease from 3D structural magnetic resonance whole-brain scans
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
Autore/i: Tomassini, Selene; Sbrollini, Agnese; Covella, Giacomo; Sernani, Paolo; Falcionelli, Nicola; Müller, Henning; Morettini, Micaela; Burattini, Laura; Dragoni, Aldo Franco
Classificazione: 1 Contributo su Rivista
Abstract: Background and objective: Alzheimer’s disease accounts for approximately 70% of all dementia cases. Cortical and hippocampal atrophy caused by Alzheimer’s disease can be appreciated easily from a T1- weighted structural magnetic resonance scan. Since a timely therapeutic intervention during the initial stages of the syndrome has a positive impact on both disease progression and quality of life of af- fected subjects, Alzheimer’s disease diagnosis is crucial. Thus, this study relies on the development of a robust yet lightweight 3D framework, Brain-on-Cloud, dedicated to efficient learning of Alzheimer’s disease-related features from 3D structural magnetic resonance whole-brain scans by improving our re- cent convolutional long short-term memory-based framework with the integration of a set of data han- dling techniques in addition to the tuning of the model hyper-parameters and the evaluation of its diag- nostic performance on independent test data. Methods: For this objective, four serial experiments were conducted on a scalable GPU cloud service. They were compared and the hyper-parameters of the best experiment were tuned until reaching the best-performing configuration. In parallel, two branches were designed. In the first branch of Brain-on- Cloud, training, validation and testing were performed on OASIS-3. In the second branch, unenhanced data from ADNI-2 were employed as independent test set, and the diagnostic performance of Brain-on- Cloud was evaluated to prove its robustness and generalization capability. The prediction scores were computed for each subject and stratified according to age, sex and mini mental state examination. Results: In its best guise, Brain-on-Cloud is able to discriminate Alzheimer’s disease with an accuracy of 92% and 76%, sensitivity of 94% and 82%, and area under the curve of 96% and 92% on OASIS-3 and independent ADNI-2 test data, respectively. Conclusions: Brain-on-Cloud shows to be a reliable, lightweight and easily-reproducible framework for automatic diagnosis of Alzheimer’s disease from 3D structural magnetic resonance whole-brain scans, performing well without segmenting the brain into its portions. Preserving the brain anatomy, its appli- cation and diagnostic ability can be extended to other cognitive disorders. to other cognitive disorders. Due to its cloud nature, computational lightness and fast execution, it can also be applied in real-time diagnostic scenarios providing prompt clinical decision support
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/308181

Unraveling the Factors Determining Development of Type 2 Diabetes in Women With a History of Gestational Diabetes Mellitus Through Machine-Learning Techniques
FRONTIERS IN PHYSIOLOGY
Autore/i: Ilari, L.; Piersanti, A.; Gobl, C.; Burattini, L.; Kautzky-Willer, A.; Tura, A.; Morettini, M.
Classificazione: 1 Contributo su Rivista
Abstract: Gestational diabetes mellitus (GDM) is a type of diabetes that usually resolves at the end of the pregnancy but exposes to a higher risk of developing type 2 diabetes mellitus (T2DM). This study aimed to unravel the factors, among those that quantify specific metabolic processes, which determine progression to T2DM by using machine-learning techniques. Classification of women who did progress to T2DM (labeled as PROG, n = 19) vs. those who did not (labeled as NON-PROG, n = 59) progress to T2DM has been performed by using Orange software through a data analysis procedure on a generated data set including anthropometric data and a total of 34 features, extracted through mathematical modeling/methods procedures. Feature selection has been performed through decision tree algorithm and then Naïve Bayes and penalized (L2) logistic regression were used to evaluate the ability of the selected features to solve the classification problem. Performance has been evaluated in terms of area under the operating receiver characteristics (AUC), classification accuracy (CA), precision, sensitivity, specificity, and F1. Feature selection provided six features, and based on them, classification was performed as follows: AUC of 0.795, 0.831, and 0.884; CA of 0.827, 0.813, and 0.840; precision of 0.830, 0.854, and 0.834; sensitivity of 0.827, 0.813, and 0.840; specificity of 0.700, 0.821, and 0.662; and F1 of 0.828, 0.824, and 0.836 for tree algorithm, Naïve Bayes, and penalized logistic regression, respectively. Fasting glucose, age, and body mass index together with features describing insulin action and secretion may predict the development of T2DM in women with a history of GDM.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/297161

Initial Reference Values of Electrocardiographic Alternans by Enhanced Adaptive Matched Filter
Computing in Cardiology
Autore/i: Marcantoni, I.; Iammarino, E.; Sbrollini, A.; Morettini, M.; Burattini, L.
Editore: IEEE Computer Society
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Electrocardiographic alternans (ECGA) is the ABAB fluctuation of the electrocardiogram (ECG) and may manifest as P-wave/QRS-complex/T-wave alternans (PWA/QRSA/TWA). ECGA is a cardiovascular risk index, and its characterization may depend on the automatic identification method. Normal ranges (needed to define risk conditions) are still not available for the new enhanced adaptive matched filter (EAMF) method. Thus, the present study aims to provide them. EAMF was used to characterize ECGA (in terms of: amplitude, μ V; area, μ V× ms; and duration, number of beats) in 15-lead ECG from 52 healthy subjects (39/13 male/female), from the 'PTB Diagnostic ECG Database'. Median ECGA values over leads and subjects were: 2μ V, 200μ V× ms, and 17 beats for PWA; 1 μ V, 80 μ V× ms, and 8 beats for QRSA; and 7 μ V, 1300μ V× ms, and 49 beats for TWA. ECGA in females (PWA:4 μ V, 350 μ V× ms, and 22 beats; QRSA: 1 μ V, 80 μ V × ms, and 11 beats; TWA: 10 μ V; 2000 μ V× ms, and 49 beats) was higher (∗p < 0.05) than ECGA in males (PWA: 20 μ V∗, 200 μ V× ms∗, and 16 beats∗ QRSA: 1 μ V, 80 μ V× ms, and 7 beats; TWA: 6μ V, 1150 μ V× ms, and 48 beats). Maximum ECGA values were observed in fundamental leads. The observed reference ECGA values seem reliable if comparing with pathological populations but are initial and analysis of wider datasets is needed.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/314451

Mathematical model of insulin kinetics accounting for the amino acids effect during a mixed meal tolerance test
FRONTIERS IN ENDOCRINOLOGY
Autore/i: Morettini, Micaela; Palumbo, Maria Concetta; Göbl, Christian; Burattini, Laura; Karusheva, Yanislava; Roden, Michael; Pacini, Giovanni; Tura, Andrea
Classificazione: 1 Contributo su Rivista
Abstract: Amino acids (AAs) are well known to be involved in the regulation of glucose metabolism and, in particular, of insulin secretion. However, the effects of different AAs on insulin release and kinetics have not been completely elucidated. The aim of this study was to propose a mathematical model that includes the effect of AAs on insulin kinetics during a mixed meal tolerance test. To this aim, five different models were proposed and compared. Validation was performed using average data, derived from the scientific literature, regarding subjects with normal glucose tolerance (CNT) and with type 2 diabetes (T2D). From the average data of the CNT and T2D people, data for two virtual populations (100 for each group) were generated for further model validation. Among the five proposed models, a simple model including one first-order differential equation showed the best results in terms of model performance (best compromise between model structure parsimony, estimated parameters plausibility, and data fit accuracy). With regard to the contribution of AAs to insulin appearance/disappearance (kAA model parameter), model analysis of the average data from the literature yielded 0.0247 (confidence interval, CI: 0.0168 - 0.0325) and -0.0048 (CI: -0.0281 - 0.0185) μU·ml-1/(μmol·l-1·min), for CNT and T2D, respectively. This suggests a positive effect of AAs on insulin secretion in CNT, and negligible effect in T2D. In conclusion, a simple model, including single first-order differential equation, may help to describe the possible AAs effects on insulin kinetics during a physiological metabolic test, and provide parameters that can be assessed in the single individuals.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/306981

Spectral F-wave index for automatic identification of atrial fibrillation in very short electrocardiograms
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Autore/i: Sbrollini, A.; Marcantoni, I.; Morettini, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Micro as well as clinical atrial fibrillation (AF) is associated with both F-wave occurrence and high heart-rate variability (HRV). Automatic AF identification typically relies on HRV evaluation only. However, high HRV is not AF specific and may not be reliably estimated in very short electrocardiograms (ECG). This study presents a new algorithm for automatic AF identification in very short ECG based on computation of a new spectral F-wave index (SFWI). Data consisted of short (9 heartbeats) 12-lead ECG acquired from 6628 subjects divided in assessment dataset and validation dataset. Each lead was independently analyzed so that 12 values of SFWI, indicating the percentage of spectral power in the 4–10 Hz band, were obtained for each ECG. Additionally, a global SFWI value was computed as the median of SFWI distribution over leads. To identify AF, a threshold on SFWI was firstly assessed on the assessment dataset, and then evaluated on the validation dataset by computation of sensitivity (SE), specificity (SP) and accuracy (AC). Results were compared with those of standard HRV-based approaches. AF identification by SFWI was already good when considering a single lead (SE: 84.6%–88.8%, SP: 84.5%–87.0%, AC: 84.5%–87.3%), improved significantly when combining the 12 leads (SE: 89.0%, SP: 87.0%, AC: 88.7%) and, overall, performed better than standard HRV-based approaches (SE: 82.2%, SP: 83.6%, AC: 83.4%). The presented algorithm is a useful tool to automatically identify AF in very short ECG, and thus has the potentiality to be applied for detection of both micro and clinical AF.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/292667

Temporal Patterns of Glucagon and Its Relationships with Glucose and Insulin following Ingestion of Different Classes of Macronutrients
NUTRIENTS
Autore/i: Gobl, C.; Morettini, M.; Salvatori, B.; Alsalim, W.; Kahleova, H.; Ahren, B.; Tura, A.
Classificazione: 1 Contributo su Rivista
Abstract: Background: glucagon secretion and inhibition should be mainly determined by glucose and insulin levels, but the relative relevance of each factor is not clarified, especially following ingestion of different macronutrients. We aimed to investigate the associations between plasma glucagon, glucose, and insulin after ingestion of single macronutrients or mixed-meal. Methods: thirty-six participants underwent four metabolic tests, based on administration of glucose, protein, fat, or mixed-meal. Glucagon, glucose, insulin, and C-peptide were measured at fasting and for 300 min following food ingestion. We analyzed relationships between time samples of glucagon, glucose, and insulin in each individual, as well as between suprabasal area-under-the-curve of the same variables (∆AUCGLUCA, ∆AUCGLU, ∆AUCINS ) over the whole participants’ cohort. Results: in individuals, time samples of glucagon and glucose were related in only 26 cases (18 direct, 8 inverse relationships), whereas relationship with insulin was more frequent (60 and 5, p < 0.0001). The frequency of significant relationships was different among tests, especially for direct relationships (p ≤ 0.006). In the whole cohort, ∆AUCGLUCA was weakly related to ∆AUCGLU (p ≤ 0.02), but not to ∆AUCINS, though basal insulin secretion emerged as possible covariate. Conclusions: glucose and insulin are not general and exclusive determinants of glucagon secretion/inhibition after mixed-meal or macronutrients ingestion.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/295010

Review on Cardiorespiratory Complications after SARS-CoV-2 Infection in Young Adult Healthy Athletes
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
Autore/i: Romagnoli, S.; Sbrollini, A.; Marcantoni, I.; Morettini, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: This review analyzes scientific data published in the first two years of the COVID-19 pandemic with the aim to report the cardiorespiratory complications observed after SARS-CoV-2 infection in young adult healthy athletes. Fifteen studies were selected using PRISMA guidelines. A total of 4725 athletes (3438 males and 1287 females) practicing 19 sports categories were included in the study. Information about symptoms was released by 4379 (93%) athletes; of them, 1433 (33%) declared to be asymptomatic, whereas the remaining 2946 (67%) reported the occurrence of symptoms with mild (1315; 45%), moderate (821; 28%), severe (1; 0%) and unknown (809; 27%) severity. The most common symptoms were anosmia (33%), ageusia (32%) and headache (30%). Cardiac magnetic resonance identified the largest number of cardiorespiratory abnormalities (15.7%). Among the confirmed inflammations, myocarditis was the most common (0.5%). In conclusion, the low degree of symptom severity and the low rate of cardiac abnormalities suggest that the risk of significant cardiorespiratory involvement after SARS-CoV-2 infection in young adult athletes is likely low; however, the long-term physiologic effects of SARS-CoV-2 infection are not established yet. Extensive cardiorespiratory screening seems excessive in most cases, and classical pre-participation cardiovascular screening may be sufficient.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/300334

TyGIS: improved triglyceride-glucose index for the assessment of insulin sensitivity during pregnancy
CARDIOVASCULAR DIABETOLOGY
Autore/i: Salvatori, Benedetta; Linder, Tina; Eppel, Daniel; Morettini, Micaela; Burattini, Laura; Göbl, Christian; Tura, Andrea
Classificazione: 1 Contributo su Rivista
Abstract: Background: The triglyceride-glucose index (TyG) has been proposed as a surrogate marker of insulin resistance, which is a typical trait of pregnancy. However, very few studies analyzed TyG performance as marker of insulin resistance in pregnancy, and they were limited to insulin resistance assessment at fasting rather than in dynamic conditions, i.e., during an oral glucose tolerance test (OGTT), which allows more reliable assessment of the actual insulin sensitivity impairment. Thus, first aim of the study was exploring in pregnancy the relationships between TyG and OGTT-derived insulin sensitivity. In addition, we developed a new version of TyG, for improved performance as marker of insulin resistance in pregnancy. Methods: At early pregnancy, a cohort of 109 women underwent assessment of maternal biometry and blood tests at fasting, for measurements of several variables (visit 1). Subsequently (26 weeks of gestation) all visit 1 analyses were repeated (visit 2), and a subgroup of women (84 selected) received a 2 h-75 g OGTT (30, 60, 90, and 120 min sampling) with measurement of blood glucose, insulin and C-peptide for reliable assessment of insulin sensitivity (PREDIM index) and insulin secretion/beta-cell function. The dataset was randomly split into 70% training set and 30% test set, and by machine learning approach we identified the optimal model, with TyG included, showing the best relationship with PREDIM. For inclusion in the model, we considered only fasting variables, in agreement with TyG definition. Results: The relationship of TyG with PREDIM was weak. Conversely, the improved TyG, called TyGIS, (linear function of TyG, body weight, lean body mass percentage and fasting insulin) resulted much strongly related to PREDIM, in both training and test sets (R2 > 0.64, p < 0.0001). Bland–Altman analysis and equivalence test confirmed the good performance of TyGIS in terms of association with PREDIM. Different further analyses confirmed TyGIS superiority over TyG. Conclusions: We developed an improved version of TyG, as new surrogate marker of insulin sensitivity in pregnancy (TyGIS). Similarly to TyG, TyGIS relies only on fasting variables, but its performances are remarkably improved than those of TyG.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/307450

Initial investigation of athletes’ electrocardiograms acquired by wearable sensors during the pre-exercise phase
THE OPEN BIOMEDICAL ENGINEERING JOURNAL
Autore/i: Romagnoli, S.; Sbrollini, A.; Colaneri, M.; Marcantoni, I.; Morettini, M.; Zitti, G.; Brocchini, M.; Pozzi, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Aim: The aim of this study is to support large-scale prevention programs fighting sport-related sudden cardiac death by providing a set of electrocardiographic features representing a starting point in the development of normal reference values for the pre-exercise phase. Background: In people with underlying, often unknown, cardiovascular abnormalities, increased cardiovascular load during exercise can trigger sport-related sudden cardiac death. Prevention remains the only weapon to contrast sport-related sudden cardiac death. So far, no reference values have been proposed for electrocardiograms of athletes acquired with wearable sensors in the pre-exercise phase, consisting of the few minutes immediately before the beginning of the training session. Objective: To perform an initial investigation of athletes’ electrocardiograms acquired by wearable sensors during the pre-exercise phase. Methods: The analyzed electrocardiograms, acquired through BioHarness 3.0 by Zephyr, belong to 51 athletes (Sport Database and Cycling Database of the Cardiovascular Bioengineering Lab of the Università Politecnica delle Marche, Italy). Preliminary values consist of interquartile ranges of six electrocardiographic features which are heart rate, heart-rate variability, QRS duration, ST level, QT interval, and corrected QT interval. Results: For athletes 35 years old or younger, preliminary values were [72;91]bpm, [26;47]ms, [85;104]ms, [-0.08;0.08]mm, [326;364]ms and [378;422]ms, respectively. For athletes older than 35 years old, preliminary values were [71;94]bpm, [16;65]ms, [85;100]ms, [-0.11;0.07]mm, [330;368]ms and [394;414]ms, respectively. Conclusion: Availability of preliminary reference values could help identify those athletes who, due to electrocardiographic features out of normal ranges, are more likely to develop cardiac complications that may lead to sport-related sudden cardiac death.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/291630

Signal Processing for Athletic Cardiovascular Monitoring with Wearable Sensors: Fully Automatic Detection of Training Phases from Heart Rate Data
Proceedings - 2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021
Autore/i: Romagnoli, S.; Sbrollini, A.; Scalese, A.; Marcantoni, I.; Morettini, M.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Heart rate (HR) recording is a non-invasive, cheap and time-efficient tool for continuous cardiovascular monitoring through wearable technologies in sport applications directly on field. Although, HR measures cannot inform equally on all aspects of cardiac responses to training, given the individual HR kinetic that depends on internal and external influencing factors. Knowledge of the training context is required to correctly compute and interpret HR-derived indices. Training context is characterized by the training phases, their distribution and training load. The aim of this study is to develop an algorithm for automatic detection of training phases in HR series to boost signal processing for athletic cardiovascular monitoring with wearable technologies. The algorithm computes the start and end times of the training phases. It exploits the variance of HR series computed over moving overlapping windows to detect automatically training transition phases. The algorithm was tested on HR series acquired during middle distance running and jogging. The algorithm showed promising results: mean errors were globally lower than 5 s and percentage error did not exceed 5%. Thus, the fully automatic algorithm for detection of training phases can boost HR signal processing for reliable computation and interpretation of HR-derived indices during continuous cardiovascular monitoring with wearable sensors in athletes.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/296401

Cardiac Electrical Alternans in Pregnancy: An Observational Study
Computing in Cardiology
Autore/i: Marcantoni, I.; Assogna, R.; Sbrollini, A.; Morettini, M.; Burattini, L.
Editore: IEEE Computer Society
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In pregnancy, if the woman has a cardiovascular disease, her fetus has an increased risk of inherited cardiac genetic disorders. Aim of this study was to evaluate electrocardiographic alternans (ECGA, mu V) of 23 pregnant women, comparing 12 mothers of fetuses with normal rhythm (MumNRF) and 11 mothers of arrhythmic fetuses (MumArrF). ECGA is a noninvasive cardiac electrical risk marker able to reveal heart electrical instability. ECGA manifests in the ECG as P-wave alternans (PWA), QRS alternans (QRSA) and/or T-wave alternans (TWA). Analysis was performed by the enhanced adaptive matched filter method. ECGA distributions were expressed as: median (interquartile range). Comparisons were performed by the Wilcoxon rank-sum test. Although showing similar heart rate (MumNRF: 85 (19) bpm; MumArrF: 90 (13) bpm), ECGA was higher in MumArrF population than MumNRF one (PWA: 9 (7) mu V vs. 14 (14) mu V; QRSA: 9 (10) mu V vs. 17 (16) mu V, TWA: 12 (14) mu Vvs. 28(17) mu V), but only TWA distributions were statistically different. Moreover, TWA was higher than in a female healthy population (on average 18mu V)in 70% of MumArrF, vs. 33% of MumNRF. Thus, higher TWA in our MumArrF seems to reflect a more unstable heart electrical condition of arrhythmic fetuses' mothers than normal-rhythm fetuses' mothers.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/295901

Ensemble empirical mode decomposition for efficient r-peak detection in electrocardiograms acquired by portable sensors during sport activity
2021 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2021 - Conference Proceedings
Autore/i: Romagnoli, S.; Marcantoni, I.; Campanella, K.; Sbrollini, A.; Morettini, M.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Wearable and portable electrocardiographic devices are revolutionizing athlete's screening through digital health application enabling a continuous monitoring of important cardiac parameters in real-time. Automatic examination of electrocardiogram (ECG) acquired during sport activity is challenging because acquisition conditions often lead to record ECGs with low signal to noise ratio (SNR). The initial issue of automatic ECG analysis is the identification of R peaks. R peaks are fundamental for the estimation of heart rate, which is the primary clinical parameter used by athletes for athletic performance evaluation. Thus, the aim of this research is to propose an R-peak detection algorithm for ECGs acquired during sport activity by portable and wearable sensors dealing with low SNR. The algorithm is based on a noise assisted data analysis method: Ensemble Empirical Mode Decomposition method (EEMD). Localization of R peaks is primarily performed on the first intrinsic mode function extracted by the EEMD. The algorithm was tested on 'Run on indoor treadmill' dataset from Physionet. ECGs were acquired during running/light jogging on an indoor treadmill and present a low SNR (1±7 dB). The developed EEMD-based algorithm showed good performances in terms of positive predicted value (91.08%), sensitivity (92.76%), false discovery rate (8.92), false negative rate (7.24%), cumulative statistical index (83.84%) and mean R-peak position error 1.10 [0.46;1.46]ms. EEMD-based algorithm performs efficiently also in computing heart rate. In conclusion, the developed R-peak detection EEMD-based algorithm showed good level of performances even working on low-SNR ECG acquired during sport activity by portable sensors.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/291911

Comparison of software packages for the analysis of continuous glucose monitoring data
2021 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2021 - Conference Proceedings
Autore/i: Piersanti, A.; Giurato, F.; Burattini, L.; Tura, A.; Morettini, M.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The use of Continuous Glucose Monitoring (CGM) systems in the management of diabetes is rapidly growing and represents an eligible technology to overcome the limitations of self-monitoring of blood glucose. However, not complete standardization of the CGM data analyses methodologies is limiting the potential of these devices. In the last few years, different software solutions have been proposed to find a common pattern for making CGM data analysis results more interpretable and reproducible. The aim of this study was to compare two of the newest open-source software packages available for CGM data analysis, GLU and iglu. To perform the comparison, CGM data of 9 subjects with type 1 diabetes coming from the open D1NAMO dataset have been analyzed with both software. Metrics available both in GLU and iglu have been compared, namely: Area Under the Curve (AUC), Time Above Range (TAR), Time Below Range (TBR), Time in Range (TIR) and Mean Absolute Deviation (MAD). Mean values for GLU and iglu were: AUC (170 ± 23 vs. 165 ± 27 mg•dl-1); TAR (40 ± 17 vs. 38 ± 21 %); TBR (6 ± 7 % in both); TIR (54 ± 18 vs. 60 ± 21 %), MAD (43 ± 20 vs. 67 ± 28 mg•dl-1). Only MAD was found statistically different between GLU and iglu. In conclusion, this comparison provided an overview of the graphical and computational aspects in CGM analysis provided by GLU and iglu software packages, which could be useful to researchers and clinicians to find a transparent and consistent way of interpreting CGM data.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/291910

Electrocardiogram-based index for the assessment of drug-induced hERG potassium channel block
JOURNAL OF ELECTROCARDIOLOGY
Autore/i: Burattini, L.; Sbrollini, A.; Scinocca, L.; Peroni, C.; Marcantoni, I.; Morettini, M.
Classificazione: 1 Contributo su Rivista
Abstract: Introduction: Drug-induced block of the hERG potassium channel could predispose to torsade de pointes, depending on occurrence of concomitant blocks of the calcium and/or sodium channels. Since the hERG potassium channel block affects cardiac repolarization, the aim of this study was to propose a new reliable index for non-invasive assessment of drug-induced hERG potassium channel block based on electrocardiographic T-wave features. Methods: ERD30% (early repolarization duration) and TS/A (down-going T-wave slope to T-wave amplitude ratio) features were measured in 22 healthy subjects who received, in different days, doses of dofetilide, ranolazine, verapamil and quinidine (all being hERG potassium channel blockers and the latter three being also blockers of calcium and/or sodium channels) while undergoing continuous electrocardiographic acquisition from which ERD30% and TS/A were evaluated in fifteen time points during the 24 h following drug administration (“ECG Effects of Ranolazine, Dofetilide, Verapamil, and Quinidine in Healthy Subjects” database by Physionet). A total of 1320 pairs of ERD30% and TS/A measurements, divided in training (50%) and testing (50%) datasets, were obtained. Drug-induced hERG potassium channel block was modelled by the regression equation BECG(%) = a·ERD30% + b·TS/A+ c·ERD30%·TS/A + d; BECG(%) values were compared to plasma-based measurements, BREF(%). Results: Regression coefficients values, obtained on the training dataset, were: a = −561.0 s−1, b = −9.7 s, c = 77.2 and d = 138.9. In the testing dataset, correlation coefficient between BECG(%) and BREF(%) was 0.67 (p < 10−81); estimation error was −11.5 ± 16.7%. Conclusion: BECG(%) is a reliable non-invasive index for the assessment of drug-induced hERG potassium channel block, independently from concomitant blocks of other ions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/293722

Repeated Structuring & Learning Procedure for Detection of Myocardial Ischemia: a Robustness Analysis
Proceedings of the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Autore/i: Sbrollini, A.; Marcantoni, I.; Morettini, M.; Swenne, C. A.; Burattini, L.
Editore: NLM (Medline)
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Myocardial ischemia, consisting in a reduction of blood flow to the heart, may cause sudden cardiac death by myocardial infarction or trigger serious abnormal rhythms. Thus, its timely identification is crucial. The Repeated Structuring and Learning Procedure (RS&LP), an innovative constructive algorithm able to dynamically create neural networks (NN) alternating structuring and learning phases, was previously found potentially useful for myocardial ischemia detection. However, performance of created NN depends on three parameters, the values of which need to be set a priori by the user: maximal number of layers (NL), maximal number of initializations (NI) and maximal number of confirmations (NC). A robustness analysis of RS&LP to varying values of NL, NI and NC is fundamental for clinical applications concerning myocardial ischemia detection but was never performed before; thus, it was the aim the present study. Thirteen serial ECG features were extracted by pairs of ECGs belonging to 84 cases (patients with induced myocardial ischemia) and 398 controls (patients with no myocardial ischemia) and used as inputs to learn (50% of population) and test (50% of population) NNs with varying values of NL (1,2,3,4,10), NI (50,250,500,1000,1500) and NC (2,5,10,20,50). Performance of obtained NNs was compared in terms of area under the curve (AUC) of the receiver operating characteristics. Overall, 13 NNs were considered; 12 (92%) were characterized by AUC≥80% and 4 (31%) by AUC≥85%. Thus, RS&LP proved to be robust when creating NNs for detecting of myocardial ischemia.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/294844

An integrated lumped-parameter model of the cardiovascular system for the simulation of acute ischemic stroke: description of instantaneous changes in hemodynamics
MATHEMATICAL BIOSCIENCES AND ENGINEERING
Autore/i: Civilla, L.; Sbrollini, A.; Burattini, L.; Morettini, M.
Classificazione: 1 Contributo su Rivista
Abstract: Acute Ischemic Stroke (AIS) is defined as the acute condition of occlusion of a cerebral artery and is often caused by a Hypertensive Condition (HC). Due to its sudden occurrence, AIS is not observable the right moment it occurs, thus information about instantaneous changes in hemodynamics is limited. This study aimed to propose an integrated Lumped Parameter (LP) model of the cardiovascular system to simulate an AIS and describe instantaneous changes in hemodynamics. In the integrated LP model of the cardiovascular system, heart chambers have been modelled with elastance systems with controlled pressure inputs; heart valves have been modelled with static open/closed pressure-controlled valves; eventually, the vasculature has been modelled with resistor-inductor-capacitor (RLC) direct circuits and have been linked to the rest of the system through a series connection. After simulating physiological conditions, HC has been simulated by changing pressure inputs and constant RLC parameters. Then, AIS occurring in arteries of different sizes have been simulated by considering time-dependent RLC parameters due to the elimination from the model of the occluding artery; instantaneous changes in hemodynamics have been evaluated by Systemic Arteriolar Flow (Qa) and Systemic Arteriolar Pressure (Pa) drop with respect to those measured in HC. Occlusion of arteries of different sizes leaded to an average Qa drop of 0.38 ml/s per cardiac cycle (with minimum and maximum values of 0.04 ml/s and 1.93 ml/s) and average Pa drop of 0.39 mmHg, (with minimum and maximum values of 0.04 mmHg and 1.98 mmHg). In conclusion, hemodynamic variations due to AIS are very small with respect to HC. A direct relation between the inverse of the length of the artery in which the occlusion occurs and the hemodynamic variations has been highlighted; this may allow to link the severity of AIS to the length of the interested artery.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/290662

Hepatic and extrahepatic insulin clearance in mice with double deletion of glucagon-like peptide-1 and glucose-dependent insulinotropic polypeptide receptors
BIOMEDICINES
Autore/i: Morettini, M.; Piersanti, A.; Burattini, L.; Pacini, G.; Gobl, C.; Ahren, B.; Tura, A.
Classificazione: 1 Contributo su Rivista
Abstract: The aim of this study was to investigate whether incretins, at physiological levels, affect hepatic and/or extrahepatic insulin clearance. Hepatic and extrahepatic insulin clearance was studied in 31 double incretin receptor knockout (DIRKO) and 45 wild-type (WT) mice, which underwent an Intravenous Glucose Tolerance Test (IVGTT). A novel methodology based on mathematical modeling was designed to provide two sets of values (FEL-P1, CLP-P1; FEL-P2, CLP-P2 ) accounting for hepatic and extrahepatic clearance in the IVGTT first and second phases, respectively, plus the respective total clearances, CLT-P1 and CLT-P2 . A statistically significant difference between DIRKO and WT was found in CLT-P1 (0.61 [0.48–0.82] vs. 0.51 [0.46–0.65] (median [interquartile range]); p = 0.02), which was reflected in the peripheral component, CLP-P1 (0.18 [0.13–0.27] vs. 0.15 [0.11–0.22]; p = 0.04), but not in the hepatic component, FEL-P1 (29.7 [26.7–34.9] vs. 28.9 [25.7–32.0]; p = 0.18). No difference was detected between DIRKO and WT in CLT-P2 (1.38 [1.13–1.75] vs. 1.69 [1.48–1.87]; p = 0.10), neither in CLP-P2 (0.72 [0.64–0.81] vs. 0.79 [0.69–0.87]; p = 0.27) nor in FEL-P2 (37.8 [35.1–43.1] vs. 39.8 [35.8–44.2]; p = 0.46). In conclusion, our findings suggest that the higher insulin clearance observed in DIRKO compared with WT during the IVGTT first phase may be due to its extrahepatic component.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/291634

An innovative training based on robotics for older people with subacute stroke: study protocol for a randomized controlled trial
TRIALS
Autore/i: Maranesi, E.; Bevilacqua, R.; Di Rosa, M.; Pelliccioni, G.; Di Donna, V.; Luzi, R.; Morettini, M.; Sbrollini, A.; Casoni, E.; Rinaldi, N.; Baldoni, R.; Lattanzio, F.; Burattini, L.; Riccardi, G. R.
Classificazione: 1 Contributo su Rivista
Abstract: Background: Stroke is a leading cause of disability, injury, and death in elderly people and represents a major public health problem with substantial medical and economic consequences. The incidence of stroke rapidly increases with age, doubling for each decade after age 55 years. Gait impairment is one of the most important problems after stroke, and improving walking function is often a key component of any rehabilitation program. To achieve this goal, a robotic gait trainer seems to be promising. In fact, some studies underline the efficacy of robotic gait training based on end-effector technology, for different diseases, in particular in stroke patients. In this randomized controlled trial, we verify the efficacy of the robotic treatment in terms of improving the gait and reducing the risk of falling and its long-term effects. Methods: In this single-blind randomized controlled trial, we will include 152 elderly subacute stroke patients divided in two groups to receive a traditional rehabilitation program or a robotic rehabilitation using G-EO system, an end-effector device for the gait rehabilitation, in addition to the traditional therapy. Twenty treatment sessions will be conducted, divided into 3 training sessions per week, for 7 weeks. The control group will perform traditional therapy sessions lasting 50 min. The technological intervention group, using the G-EO system, will carry out 30 min of traditional therapy and 20 min of treatment with a robotic system. The primary outcome of the study is the evaluation of the falling risk. Secondary outcomes are the assessment of the gait improvements and the fear of falling. Further evaluations, such as length and asymmetry of the step, walking and functional status, and acceptance of the technology, will be carried. Discussion: The final goal of the present study is to propose a new approach and an innovative therapeutic plan in the post-stroke rehabilitation, focused on the use of a robotic device, in order to obtain the beneficial effects of this treatment. Trial registration: ClinicalTrials.gov NCT04087083. Registered on September 12, 2019
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/290829

Mathematical Model of Glucagon Kinetics for the Assessment of Insulin-Mediated Glucagon Inhibition During an Oral Glucose Tolerance Test
FRONTIERS IN ENDOCRINOLOGY
Autore/i: Morettini, Micaela; Burattini, Laura; Göbl, Christian; Pacini, Giovanni; Ahrén, Bo; Tura, Andrea
Classificazione: 1 Contributo su Rivista
Abstract: Glucagon is secreted from the pancreatic alpha cells and plays an important role in the maintenance of glucose homeostasis, by interacting with insulin. The plasma glucose levels determine whether glucagon secretion or insulin secretion is activated or inhibited. Despite its relevance, some aspects of glucagon secretion and kinetics remain unclear. To gain insight into this, we aimed to develop a mathematical model of the glucagon kinetics during an oral glucose tolerance test, which is sufficiently simple to be used in the clinical practice. The proposed model included two first-order differential equations -one describing glucagon and the other describing C-peptide in a compartment remote from plasma - and yielded a parameter of possible clinical relevance (i.e., SGLUCA(t), glucagon-inhibition sensitivity to glucose-induced insulin secretion). Model was validated on mean glucagon data derived from the scientific literature, yielding values for SGLUCA(t) ranging from -15.03 to 2.75 (ng of glucagon·nmol of C-peptide-1). A further validation on a total of 100 virtual subjects provided reliable results (mean residuals between -1.5 and 1.5 ng·L-1) and a negative significant linear correlation (r = -0.74, p < 0.0001, 95% CI: -0.82 - -0.64) between SGLUCA(t) and the ratio between the areas under the curve of suprabasal remote C-peptide and glucagon. Model reliability was also proven by the ability to capture different patterns in glucagon kinetics. In conclusion, the proposed model reliably reproduces glucagon kinetics and is characterized by sufficient simplicity to be possibly used in the clinical practice, for the estimation in the single individual of some glucagon-related parameters.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/289574

Model-Based Assessment of Hepatic and Extrahepatic Insulin Clearance from Short Insulin-Modified IVGTT in Women with a History of Gestational Diabetes
Proceedings of the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Autore/i: Piersanti, A.; Abdul Rahman, N. H. B.; Gobl, C.; Burattini, L.; Kautzky-Willer, A.; Pacini, G.; Tura, A.; Morettini, M.
Editore: NLM (Medline)
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Insulin clearance is an integral component of insulin metabolism. Yet, little is known about separate contribution of hepatic and extrahepatic insulin clearance in type 2 diabetes and in high-risk populations, such as women who experienced gestational diabetes mellitus (pGDM). A model-based method was recently proposed to assess both contributions from 3-hour insulin-modified intravenous glucose tolerance test (IM-IVGTT); the aim of this study was to assess the reliability of short (1 hour) IM-IVGTT in the application of such model-based method and to evaluate the role of the two contributions in determining insulin clearance in pGDM. A total of 115 pGDM women and 41 who remained healthy during pregnancy (CNT) were analyzed early postpartum and underwent a 3-hour IMIVGTT. Peripheral insulin clearance (CLP), hepatic fractional extraction (FEL) and extrahepatic distribution volume (VP) were estimated by performing a best-fit procedure on insulin IMIVGTT data considering firstly the overall 3-hour duration and then limiting data to 1 hour. Results showed no significant difference in parameter values between the 3-hour and the 1-hour IM-IVGTT. Comparison between pGDM and CNT (1-hour) showed no significant difference in CLp (0.23 [0.29] vs. 0.27 [0.43] L·min-1; p=0.64), FEL (50.2 [15.1] vs. 50.9 [11.7] %; p=0.63) and VP (2.01 [2.99] vs. 2.70 [4.00] L; p=0.92). In conclusion, short IM-IVGTT provides a reliable assessment of hepatic and extrahepatic insulin clearance through such model-based method. Its application to the study of pGDM women showed no alteration in hepatic and extrahepatic contributions with respect to women who had a healthy pregnancy.Clinical Relevance- This study proves the reliability of short (1 hour) IM-IVGTT to assess hepatic and extrahepatic insulin clearance in women who experienced gestational diabetes.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/294845

A Preliminary Validation of a New Surgical Procedure for the Treatment of Primary Bladder Neck Obstruction Using a Computational Modeling Approach
BIOENGINEERING
Autore/i: Serpilli, Michele; Zitti, Gianluca; Dellabella, Marco; Castellani, Daniele; Maranesi, Elvira; Morettini, Micaela; Lenci, Stefano; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: A new surgical procedure for the treatment of primary bladder neck obstruction with maintenance of anterograde ejaculation is proposed. In place of monolateral or bilateral bladder neck incision, associated with a loss of ejaculation rate of up to 30%, the new surgical procedure consists of laser drilling the bladder neck with a number of holes and without muscle fiber disrup- tion. The effect of this novel procedure has been studied numerically, with a simplified two-dimen- sional numerical model of the internal urethral sphincter, varying the position and the number of holes in the fibrotic region of the urethral tissue. Results show an improvement of the urethral sphincter opening by increasing the number of holes, ranging from about 6% to 16% of recovery. Moreover, a non-aligned position of holes positively influences the opening recovery. The concen- trations of maximum principal strain and stress have been registered in the proximity of the inter- face between the physiologic and diseased sphincter, and in those regions where the radial thick- ness is significantly thinner. The effects on the first five patients have been included in the study, showing improvement in micturition, lower urinary tract symptoms, sustained ejaculatory func- tion, and quality of life.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/290912

Adaptive bradycardia assessment in preterm infants
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Autore/i: Sbrollini, A.; Mancinelli, M.; Marcantoni, I.; Morettini, M.; Carnielli, V. P.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: In preterm infants, bradycardias associate to critical health conditions. Standard algorithm for bradycardia identification assumes baseline heart rate (BHR) equal to 150bpm and identifies bradycardias when heart rate (HR) decreases below 100bpm. Since preterm infants show BHR varying from 120bpm to 160bpm, a new adaptive algorithm for real-time bradycardia identification was presented. The adaptive algorithm continuously adjusts BHR by averaging HR over the preceding 10-minute window after eliminating out-of-range HR values, and identifies bradycardias when HR decreases below 67% of BHR. Both standard and adaptive algorithms were evaluated using long-term (20.3–70.3h) electrocardiographic recordings of ten preterm infants (“Preterm Infant Cardio-respiratory Signals” database by Physionet). Bradycardias were characterized in terms of rate (BR, h−1) and depth (BD, bpm). Being also indexes of infants’ health conditions, gestational age at birth (GA, days), birth weight (BW, kg) and HR were used to evaluate performances of the algorithms. Association between BR and BD vs GA, BW and HR was evaluated by computation of the correlation coefficient (ρ). Overall, standard and adaptive algorithms identified 516 and 546 bradycardias, respectively; median BR and BD values were comparable (1.25h−1 and 76bpm vs 1.26h−1 and 70bpm, respectively). However, the adaptive algorithm provided higher BD for HR>150bpm, and vice versa. Significant (p value<0.05) correlations were found between BR and HR (ρ=0.69), BR and BW (ρ=−0.76), and BR and HR (ρ=0.76) only when using the adaptive algorithm. Thus, the adaptive algorithm is superior to the standard algorithm and represents a potentially clinically useful tool for real-time bradycardia assessment in preterm infants.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/290831