389 pubblicazioni classificate nel seguente modo:

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

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

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

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

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

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

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

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

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

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

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

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

Robot Perception through Wearable Sensors: Decoding Grasping for Human-Robot Hand-Over
2022 I-RIM Conference
Autore/i: Bonci, Andrea; Burattini, Laura; Fioretti, Sandro; Giannini, MARIA CRISTINA; Longhi, Sauro; Mengarelli, Alessandro; Tigrini, Andrea; Verdini, Federica
Editore: I-RIM
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Human-robot interaction represents the cornerstone for the full development of Industry 4.0 and 5.0 paradigms, that rely on this cooperation in order to develop more efficient and flexible production lines. In this context, the human-robot handover plays a crucial role and many approaches were introduced to plan and control this task, including the less investigated decoding of human muscles activity. Hence, the design of reliable myoelectric human-robot interfaces is a point of primary interest. This paper investigates the use of a wearable device, i.e. an armband, for achieving a robust detection of several human grasping gestures. An evaluation of the most useful features, belonging to three different computational domains, is also proposed. Outcomes showed that high recognition performance can be achieved with limited computational burden, which is crucial when dealing with real-time demands in collaborative task.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/315772

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

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

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

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

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

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

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

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

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

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

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

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

Editorial: Artificial intelligence in human physiology
FRONTIERS IN PHYSIOLOGY
Autore/i: Ong, Chin Siang; Burattini, Laura; Schena, Stefano
Classificazione: 1 Contributo su Rivista
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/309103

Lung nodule diagnosis and cancer histology classification from computed tomography data by convolutional neural networks: A survey
COMPUTERS IN BIOLOGY AND MEDICINE
Autore/i: Tomassini, Selene; Falcionelli, Nicola; Sernani, Paolo; Burattini, Laura; Dragoni, Aldo Franco
Classificazione: 1 Contributo su Rivista
Abstract: Lung cancer is among the deadliest cancers. Besides lung nodule classification and diagnosis, developing non-invasive systems to classify lung cancer histological types/subtypes may help clinicians to make targeted treatment decisions timely, having a positive impact on patients' comfort and survival rate. As convolutional neural networks have proven to be responsible for the significant improvement of the accuracy in lung cancer diagnosis, with this survey we intend to: show the contribution of convolutional neural networks not only in identifying malignant lung nodules but also in classifying lung cancer histological types/subtypes directly from computed tomography data; point out the strengths and weaknesses of slice-based and scan-based approaches employing convolutional neural networks; and highlight the challenges and prospective solutions to successfully apply convolutional neural networks for such classification tasks. To this aim, we conducted a comprehensive analysis of relevant Scopus-indexed studies involved in lung nodule diagnosis and cancer histology classification up to January 2022, dividing the investigation in convolutional neural network-based approaches fed with planar or volumetric computed tomography data. Despite the application of convolutional neural networks in lung nodule diagnosis and cancer histology classification is a valid strategy, some challenges raised, mainly including the lack of publicly-accessible annotated data, together with the lack of reproducibility and clinical interpretability. We believe that this survey will be helpful for future studies involved in lung nodule diagnosis and cancer histology classification prior to lung biopsy by means of convolutional neural networks.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/304482

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

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

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

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

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

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

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

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

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

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

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

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

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

Enhanced adaptive matched filter for automated identification and measurement of electrocardiographic alternans
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Autore/i: Marcantoni, I.; Sbrollini, A.; Morettini, M.; Swenne, C. A.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Electrocardiographic alternans, consisting of P-wave alternans (PWA), QRS-complex alternans (QRSA) and T-wave alternans (TWA), is an index of cardiac risk. However, only automated TWA measurement methods have been proposed so far. Here, we presented the enhanced adaptive matched filter (EAMF) method and tested its reliability in both simulated and experimental conditions. Our methodological novelty consists in the introduction of a signal enhancement procedure according to which all sections of the electrocardiogram (ECG) but the wave of interest are set to baseline, and in the extraction of the alternans area (AAr) in addition to the standard alternans amplitude (AAm). Simulated data consisted of 27 simulated ECGs representing all combinations of PWA, QRSA and TWA of low (10 μV) and high (100 μV) amplitude. Experimental data consisted of exercise 12-lead ECGs from 266 heart failure patients with an implanted cardioverter defibrillator for primary prevention. EAMF was able to accurately identify and measure all kinds of simulated alternans (absolute maximum error equal to 2%). Moreover, different alternans kinds were simultaneously present in the experimental data and EAMF was able to identify and measure all of them (AAr: 545 μV × ms, 762 μV × ms and 1382 μV × ms; AAm: 5 μV, 9 μV and 7 μV; for PWA, QRSA and TWA, respectively) and to discriminate TWA as the prevalent one (with the highest AAr). EAMF accurately identifies and measures all kinds of electrocardiographic alternans. EAMF may support determination of incremental clinical utility of PWA and QRSA with respect to TWA only.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/289895

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

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

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

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

Real-Time Smart Monitoring System for Atrial Fibrillation Pathology
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
Autore/i: Pierleoni, Paola; Belli, Alberto; Gentili, Andrea; Incipini, Lorenzo; Palma, Lorenzo; Raggiunto, Sara; Sbrollini, Agnese; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Atrial Fibrillation (AF) is a common cardiac pathology and, due to its unpredictability, it sometimes remains not detected. Aim of this work is to present a new version of the already published eHealth system, that includes a new real-time Android application for AF detection and monitoring. The proposed eHealth system is composed of a commercial wearable sensor device (Bioharness 3.0 by Zephyr) for cardiac monitoring and a specially developed Android smartphone application. This application is able to real-time processing the raw data sensed from the wearable sensor, providing stress detection, calories consumption estimation, sinus arrhythmia detection, sinus rhythm classification, and apnea detection. As novelty, the new smartphone application also implemented a SVM-based algorithm designed to detect AF episodes by handling electrocardiogram and the heart-rate sequence of the subjects. The performance of the new SVM-based algorithm implemented in eHealth was tested on AF recordings and evaluated in term of sensitivity and specificity. The results show a sensitivity of 78% and a specificity of 66%, making this version of eHealth system suitable for real-time monitoring of AF events.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272283

Classifying various brain activities by exploiting deep learning techniques and genetic algorithm fusion method
TEST
Autore/i: Mohamedsheet AL-Hatab, Marwa; Al-Nima, Raid Rafi Omar; Marcantoni, Ilaria; Porcaro, Camillo; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: The scan of functional Magnetic Resonance Imaging (fMRI) can provide three views for brain activities. These views are basically the X_axis (sagittal Plane), Y_axis (coronal plane) and Z_axis (axial plane). To the best of the obtained knowledge, studying brain activities for all of these views has not been considered before together with Deep Learning (DL) techniques. In this paper, various DL models named the X_axis Classification Model (XCM), Y_axis Classification Model (YCM) and Z_axis Classification Model (ZCM) are proposed. Each of these models is able to classify between the vision, movement and forward brain activities. Extensive experiments are performed for examining their parameters. The designed models have the capability to automatically detect the important features without any human supervision. In addition, they can provide intelligent decisions or classifications. Furthermore, effective combination method is suggested based on the Genetic Algorithm (GA) and Genetic Weighted Summation (GWS) rule, where high performances of outcomes can be achieved. After extensive experiments, the accuracies of 91.67%, 89.88% and 91.67% have been obtained for the XCM, YCM and ZCM, respectively. In addition, the accuracy has been raised to 97.22% by applying the suggested fusion method.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354976

Comparison study between three axis views of vision, motor and pre-frontal brain activities
JOURNAL OF CRITICAL REVIEWS
Autore/i: MohamedSheet AL-Hatab, Marwa; Al-Nima, Raid Rafi Omar; Marcantoni, Ilaria; Porcaro, Camillo; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: The brain is the main controller of the vital processes and functional studies. The Functional Magnetic Resonance Imaging (fMRI) can provide useful indications to explain the functional activities of brain. Especially with utilizing the three image views of X_axis (Sagittal Plane) split the brain into left and right segment, Y_axis (Coronal plane) split the brain into back and front segment and Z_axis (Axial plane) split the brain into top and down segment. In this study, we proposevarious deep learning models namely the X_axis Classification Model (XCM), Y_axis Classification Model (YCM) and Z_axis Classification Model (ZCM) for classify three tasks of vision, movement and pre-frontal brain activities.In addition of presenting comparisonsbetween different network modelsforall of the three views. After extensive experiments and comparisons even with state-of-the-art studies, promising accuracies of 91.67%, 89.88% and 91.67% have successfully been obtained for the XCM, YCM and ZCM, respectively.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/354975

Electrocardiographic Alternans in Hemodialysis: A Case Report
Convegno Nazionale di Bioingegneria
Autore/i: Marcantoni, I.; Di Monte, J.; Leoni, C.; Mansour, Z.; Sbrollini, A.; Morettini, M.; Burattini, L.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Hemodialysis (HD) is a clinical procedure used to treat patients suffering of chronic kidney failure. Unfortunately, HD patients are at a high risk of sudden cardiac death (SCD). To evaluate SCD risk, it is useful to analyze the electrocardiographic signal (ECG). One of the most popular indexes to investigate SCD is T-wave alternans (TWA), related to the ventricular repolarization segment of the ECG. Electrocardiographic alternans (ECGA), i.e. the prevalent nature of electrical alternans, though, represents a more complete analysis of the cardiac electrical activity, including also the possible presence of alternans on P wave (PWA) and QRS (QRSA), related to atrial depolarization and repolarization phases, respectively. Aim of this study was to obtain a complete evaluation of ECGA on a HD patient during a HD day, by means of the Heart-Rate Adaptive Match filter (HRAMF) method. HRAMF was applied for ECGA analysis on a continuous Holter ECG recording. Considering four macro-time periods PRE-HD, IN-HD, POST-HD and NT-HD (before, during, after HD and during the night, respectively), ECGA was identified as TWA and presented high values (>15µV) in PRE-HD (51 µV) and IN-HD (53 µV), highlighting how these periods are characterized by a higher SCD risk. Two hours after the end of HD, ECGA decreased due to the treatment, able to rebalance electrolytes concentrations. Statistical differences were found between PRE-HD and POST-HD, and PRE-HD and NT-HD (p<10-3). The study suggested a higher cardiac risk (mostly affecting ventricular repolarization) in HD patients; this risk is lower after the end of HD session.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/312348

Model-based assessment of incretin effect from OGTT data in healthy subjects
Convegno Nazionale di Bioingegneria
Autore/i: Morettini, M.; Creato, E.; Di Monte, J.; Ilari, L.; Burattini, L.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The incretin effect is a phenomenon in which insulin response to an Oral Glucose Tolerance Test (OGTT) is higher with respect to the insulin response to a matched isoglycaemic intravenous glucose infusion (I-IGI). The aim of this study was to simplify our previous model describing glucose-insulin regulatory system to allow assessment of the incretin effect in healthy subjects from OGTT glucose and insulin data, without using I-IGI data. The proposed model is characterized by four free parameters and was tested on mean data of two groups of healthy subjects. Free model parameters were estimated with a good precision (CV%<22) and provided values for the incretin effect very similar to the experimental ones (64.2 vs. 63 in the first group of subject and 77.7 vs. 78.1 in the second group). Thus, the proposed model seems to be promising, for the sake of a patient-oriented approach, to assess the incretin effect in healthy subjects only using OGTT glucose and insulin data.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/312349

Novel recurrence features for prefall and fall detection in backward and forward fall types
Convegno Nazionale di Bioingegneria
Autore/i: Nasim, A.; Nchekwube, D. C.; Khorasani, E.; Van der Maaden, N. E.; Morettini, M.; Burattini, L.
Editore: Patron Editore S.r.l.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Injuries caused by different types of falls are one of the vital health threats to the elder community living independent or otherwise. Characterization and detection of a fall event can trigger an alert and minimize the damage. This work presents recurrence quantification parameters as novel features for characterization of a fall event in case of backward and forward types of falls using data acquired through wearable sensors. Computing cross recurrence plots and recurrence parameters; recurrence rate (RR), determinism (DET) and line entropy (ENT) for pre-fall, fall and post-fall phases, the level of signal stability and non-stability is quantified. The recurrence parameters show a stable behaviour in case of pre-fall (RR=0.74, DET=0.85, ENT=4.36) and chaotic behaviour in case of fall (RR=0.39 DET=0.80, ENT=3.13). To assess the discriminating capability of novel recurrence features, a support vector machine (SVM) is used to perform binary classification for prefall and fall classes. The SVM results in overall accuracy of 76% with a positive prediction of 82% for fall and 70% for pre-fall events. The results indicate that recurrence metrics are successfully able to characterize a sudden fall event and could be used in designing fall detection algorithms using wearable sensors.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/312347

Preface
Innovative Technologies and Signal Processing in Perinatal Medicine: Volume 1
Autore/i: Pani, D.; Rabotti, C.; Signorini, M. G.; Burattini, L.
Editore: Springer International Publishing
Classificazione: 2 Contributo in Volume
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/312109

AdvFPCG-Delineator: Advanced delineator for fetal phonocardiography
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Autore/i: Tomassini, S.; Sbrollini, A.; Strazza, A.; Sameni, R.; Marcantoni, I.; Morettini, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Fetal phonocardiogram (FPCG) consists in the recording of fetal heart sounds by means of a sensor placed on the mother's abdominal surface. Usually, FPCG includes two major sounds for each fetal cardiac cycle: S1, produced by the sudden closure of mitral and tricuspid valves, and S2 produced by the closure of aortic and pulmonary valves. The aim of the present study was to propose AdvFPCG-Delineator for automatic fetal S1 and S2 identification and to demonstrate its reliability in different clinical conditions. The method consists of a wavelet-based filtering procedure followed by the computation of the scalogram, from which S1 and S2 were identified using a threshold-based algorithm. AdvFPCG-Delineator was tested on the “Simulated Fetal PCGs database” (37 FPCG signals) and on the experimental “Shiraz University fetal heart sounds database” (119 FPCG signals), both available at PhysioNet (https://physionet.org). Manual S1 and S2 annotations and simultaneously acquired cardiotocographic recordings were used to compute reference fetal heart rate (FHR) for the simulated and experimental databases, respectively. No statistically significant difference was observed between estimated vs reference FHR (140 bpm vs 140 bpm, respectively) for the simulated database, for which AdvFPCG-Delineator was also able to track beat-to-beat variability (correlation over 92%). Additionally, no statistically significant difference was observed between estimated vs reference FHR (141 bpm vs 140 bpm, respectively) for the experimental database, even when stratifying by clinical conditions (maternal age, gestational age, etc.). In conclusion, AdvFPCG-Delineator proved to be a reliable method to automatically identify S1 and S2 from fetal phonocardiograms.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/282806

Postural data from Stargardt's syndrome patients
DATA IN BRIEF
Autore/i: Sbrollini, A.; Agostini, V.; Cavallini, C.; Burattini, L.; Knaflitz, M.
Classificazione: 1 Contributo su Rivista
Abstract: The database is a collection of postural data acquired from 10 patients affected by the rare Stargardt's syndrome, all having the ABCA4 gene mutation, and from 10 control healthy subjects. Specifically, the database includes a file (.xlxs) called SubjectsData and 20 datasets (MATLAB structures) containing postural signals. Each subject performed a total of 15 postural tests, 5 postural tests for 3 different conditions (‘C’: eyes-closed; ‘O’: eyes-open, still target fixation; ‘M’: eyes-open, moving target tracking). For each postural test, 11 postural derived signals (the anterior-posterior force, the medio-lateral force, the vertical force, the plate moment about x axis, the plate moment about y axis, the plate moment about z axis, the plate moment about top plate surface about x axis, the plate moment about top plat surface about y axis, the x-coordinate of the center of pressure, the y-coordinate of the center of pressure, and the free moment about z axis) were computed from 8 raw signals, acquired at the Ophthalmic Hospital of Turin, Italy, through an 8-channel Kistler 9286A force platform connected to a Step32 system. Thus, a total of 285 postural signals (120 raw and 165 derived) are available for each subject. The database may be useful to: (1) investigate postural adaptations of patients affected by Stargardt's syndrome; (2) support definition of rehabilitative procedures to reduce postural instability of patients affected by Stargardt's syndrome; and (3) support investigation on visual control of balance in the general population.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/276464

Model-Based Estimation of Electrocardiographic QT Interval from Phonocardiographic Heart Sounds in Healthy Subjects
Computing in Cardiology
Autore/i: Sbrollini, A.; Morettini, M.; Marcantoni, I.; Burattini, L.
Editore: IEEE Computer Society
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The electrocardiographic QT interval is an index of cardiac risk commonly used in clinics. Accurate QT measure is challenging, especially in noisy conditions, when acquisitions of phonocardiograms (PCGs) may be more reliable than acquisitions of electrocardiograms (ECGs). However, PCG features are less used in clinics. Thus, aim of the study was to propose a model for indirectly measuring the electrocardiographic QT interval from the phonocardiographic heart sounds in healthy subjects. To this aim, simultaneously acquired PCGs and ECGs of 99 healthy subjects were processed to obtain median PCG and ECG beats. Beat length, S1 onset and S2 onset were identified from the median PCG beat, while QT interval (QT) was measured from the median ECG beat. Then, a regression model was formulated by regression analysis to obtain PCG-based QT estimation (QT) and validated by leave-one-out cross-validation. Correlation coefficient (p) and estimation error were also computed. QT and QT did not differ significantly (model formulation: 362ms vs 358ms; model validation:360ms vs 358ms, respectively; P>0.5) and were significantly correlated (model formulation: p=0.7, p<10-13; model validation: p=0.6, P<10-10); median error is 1 ms (<0.5 in %). Thus, the proposed model provides a reliable estimation of QT interval from PCG heart sounds in healthy subjects.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/288228

Electrocardiographic Alternans in Myocardial Bridge: A Case Report
Computing in Cardiology
Autore/i: Marcantoni, I.; Di Menna, A.; Rossini, F.; Turco, F.; Morettini, M.; Sbrollini, A.; Bianco, F.; Pozzi, M.; Burattini, L.
Editore: IEEE Computer Society
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Myocardial bridge (MB) is a congenital heart condition in which a 'bridge' of myocardium is overlying a 'tunneled' coronary artery. MB can be associated with a series of critical cardiac events. Aim of this study was to evaluate electrocardiographic alternans (ECGA) on a MB patient, being ECGA a cardiac electrical risk index defined as beat-to-beat alternation of electrocardiographic P-wave, QRS-complex and T-wave morphology at stable heart rate. ECGA analysis was performed in a 1-hour 12-lead electrocardiographic recording of a 54 years-old MB male patient at rest by application of the heart-rate adaptive match filter method. Areas of P-wave, QRS and T-wave alternans (PWAA, QRSAA, TWAA) were measured, evaluating also the prevalent among the three. Results showed the prevalent alternans was T-wave alternans, being TWAA on average equal to 6.3 µV×s (PWAA=4.7 µV×s, QRSAA=4.3 µV×s); TWAA prevalence occurrence rate was 94% (PWAA: 5%, QRSAA:1%). TWAA was also found to be significantly correlated (p=0.72, p<10-2) with heart rate. Eventually, TWAA was at least twice higher than in previously analyzed male healthy subjects. Thus, MB seems to be associated to a higher cardiac electrical risk, possibly especially while performing physical activity at high heart rate.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/288230

Artificial neural network for atrial fibrillation identification in portable devices
SENSORS
Autore/i: Marinucci, D.; Sbrollini, A.; Marcantoni, I.; Morettini, M.; Swenne, C. A.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Atrial fibrillation (AF) is a common cardiac disorder that can cause severe complications. AF diagnosis is typically based on the electrocardiogram (ECG) evaluation in hospitals or in clinical facilities. The aim of the present work is to propose a new artificial neural network for reliable AF identification in ECGs acquired through portable devices. A supervised fully connected artificial neural network (RSL_ANN), receiving 19 ECG features (11 morphological, 4 on F waves and 4 on heart-rate variability (HRV)) in input and discriminating between AF and non-AF classes in output, was created using the repeated structuring and learning (RSL) procedure. RSL_ANN was created and tested on 8028 (training: 4493; validation: 1125; testing: 2410) annotated ECGs belonging to the “AF Classification from a Short Single Lead ECG Recording” database and acquired with the portable KARDIA device by AliveCor. RSL_ANN performance was evaluated in terms of area under the curve (AUC) and confidence intervals (CIs) of the received operating characteristic. RSL_ANN performance was very good and very similar in training, validation and testing datasets. AUC was 91.1% (CI: 89.1%–93.0%), 90.2% (CI: 86.2%–94.3%) and 90.8% (CI: 88.1%–93.5%) for the training, validation and testing datasets, respectively. Thus, RSL_ANN is a promising tool for reliable identification of AF in ECGs acquired by portable devices.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/282883

A functional source separation algorithm to enhance error-related potentials monitoring in noninvasive brain-computer interface
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
Autore/i: Ferracuti, F.; Casadei, V.; Marcantoni, I.; Iarlori, S.; Burattini, L.; Monteriu, A.; Porcaro, C.
Classificazione: 1 Contributo su Rivista
Abstract: Background and objectives: An Error related Potential (ErrP) can be noninvasively and directly measured from the scalp through electroencephalography (EEG), as response, when a person realizes they are making an error during a task (as a consequence of a cognitive error performed from the user). It has been shown that ErrPs can be automatically detected with time-discrete feedback tasks, which are widely applied in the Brain-Computer Interface (BCI) field for error correction or adaptation. In this work, a semi-supervised algorithm, namely the Functional Source Separation (FSS), is proposed to estimate a spatial filter for learning the ErrPs and to enhance the evoked potentials. Methods: EEG data recorded on six subjects were used to evaluate the proposed method based on FFS algorithm in comparison with the xDAWN algorithm. FSS- and xDAWN-based methods were compared also to the Cz and FCz single channel. Single-trial classification was considered to evaluate the performances of the approaches. (Both the approaches were evaluated on single-trial classification of EEGs.) Results: The results presented using the Bayesian Linear Discriminant Analysis (BLDA) classifier, show that FSS (accuracy 0.92, sensitivity 0.95, specificity 0.81, F1-score 0.95) overcomes the other methods (Cz - accuracy 0.72, sensitivity 0.74, specificity 0.63, F1-score 0.74; FCz - accuracy 0.72, sensitivity 0.75, specificity 0.61, F1-score 0.75; xDAWN - accuracy 0.75, sensitivity 0.79, specificity 0.61, F1-score 0.79) in terms of single-trial classification. Conclusions: The proposed FSS-based method increases the single-trial detection accuracy of ErrPs with respect to both single channel (Cz, FCz) and xDAWN spatial filter.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/275324

T-Wave Alternans in Nonpathological Preterm Infants
ANNALS OF NONINVASIVE ELECTROCARDIOLOGY
Autore/i: Marcantoni, I.; Sbrollini, A.; Agostinelli, G.; Surace, F. C.; Colaneri, M.; Morettini, M.; Pozzi, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Background: Sudden infant death syndrome is more frequent in preterm infants (PTI) than term infants and may be due to cardiac repolarization instability, which may manifest as T-wave alternans (TWA) on the electrocardiogram (ECG). Therefore, the aim of the present work was to analyze TWA in nonpathological PTI and to open an issue on its physiological interpretation. Methods: Clinical population consisted of ten nonpathological PTI (gestational age ranging from 293/7 to 342/7 weeks; birth weight ranging from 0.84 to 2.10 kg) from whom ECG recordings were obtained (“Preterm infant cardio-respiratory signals database” by Physionet). TWA was identified through the heart-rate adapting match filter method and characterized in terms of mean amplitude values (TWAA). TWA correlation with several other clinical and ECG features, among which gestational age–birth weight ratio, RR interval, heart-rate variability, and QT interval, was also performed. Results: TWA was variable among infants (TWAA = 26 ± 11 µV). Significant correlations were found between TWAA versus birth weight (ρ = −0.72, p =.02), TWAA versus gestational age–birth weight ratio (ρ = 0.76, p =.02) and TWAA versus heart-rate variability (ρ = −0.71, p =.02). Conclusions: Our preliminary retrospective study suggests that nonpathological PTI show TWA of few tens of µV, the interpretation of which is still an open issue but could indicate a condition of cardiac risk possibly related to the low development status of the infant. Further investigations are needed to solve this issue.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/273413

Innovative technologies and signal processing in perinatal medicine: Volume 1
Innovative Technologies and Signal Processing in Perinatal Medicine: Volume 1
Autore/i: Pani, D.; Rabotti, C.; Signorini, M. G.; Burattini, L.
Editore: Springer International Publishing
Classificazione: 2 Contributo in Volume
Abstract: Pregnancy is a critical time for the health of the mother and the fetus, with important potential risks for both. Tools for antenatal diagnosis and pregnancy monitoring can support prevention and management of potential risks and complications. In particular, the perinatal period, spanning from the third trimester of pregnancy up to one month after birth, is the most critical for the baby. For this reason, in the last decades, biomedical engineering supported and fostered the scientific research towards the identification of new models, parameters, algorithms, and tools that can improve the quality of fetal monitoring, predict the outcomes and allow physicians to intervene in an appropriate manner to ensure a healthy future for the baby. This book follows the First International Summer School on Technologies and Signal Processing in Perinatal Medicine and reflects some of its most important master lectures. It represents a valuable guide for students and young researchers approaching this topic for the first time, as well as experienced researchers and practitioners looking for a clear representation of the themes and techniques presented by recognized experts in the field.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/325878

T-wave alternans identification in direct and indirect fetal electrocardiography
Innovative Technologies and Signal Processing in Perinatal Medicine: Volume 1
Autore/i: Burattini, L.; Marcantoni, I.; Nasim, A.; Burattini, L.; Morettini, M.; Sbrollini, A.
Editore: Springer International Publishing
Classificazione: 2 Contributo in Volume
Abstract: The fetal electrocardiogram (FECG) is the recording of the electrical activity of the fetal heart. Morphologically, FECG shows the standard P-QRS-TU electrocardiographic pattern and a heart rate (HR) of 120-160 bpm. There are two techniques to acquire FECG: the direct one (DI-FECG), with a spiral wire electrode located on the fetal scalp; and the indirect one (IN-FECG), with electrodes located on the mother's abdomen. Fetal T-wave alternans (TWA) represents a possible cause of unexplained fetal deaths; its investigation, however, is challenging. This chapter discusses about this scientific and clinical problem, and proposes a procedure to identify TWA from both DI-FECG and IN-FECG. The procedure includes the following 3 steps: (1) automatic identification of fetal R peaks, performed through the improved fetal Pan-Tompkins Algorithm; (2) FECG filtering, performed through linear filtering and the segmented-beat modulation method; and (3) automatic TWA identification, performed through the heart-rate adaptive match filter. Application of this procedure to 5 DI-FECG and 20 IN-FECG from 5 fetuses confirmed its goodness for fetal applications and suggested that fetuses show TWA even when healthy. Moreover, TWA detected in DI-FECG was comparable to that in IN-FECG, suggesting that TWA identification was reliable also in IN-FECG, which is much more affected by artifacts and interferences than DI-FECG.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/312108

COVID-19 in Italy: Dataset of the Italian Civil Protection Department
DATA IN BRIEF
Autore/i: Italian Civil Protection, Department; Morettini, M.; Sbrollini, A.; Marcantoni, I.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: The database here described contains data of integrated surveillance for the “Coronavirus disease 2019” (abbreviated as COVID-19 by the World Health Organization) in Italy, caused by the novel coronavirus SARS-CoV-2. The database, included in a main folder called COVID-19, has been designed and created by the Italian Civil Protection Department, which currently manages it. The database consists of six folders called ‘aree’ (containing charts of geographical areas interested by containment measures), ‘dati-andamento-nazionale’ (containing data relating to the national trend of SARS-CoV-2 spread), ‘dati-json’ (containing data that summarize the national, provincial and regional trends of SARS-CoV-2 spread), ‘dati-province’ (containing data relating to the provincial trend of SARS-CoV-2 spread), ‘dati-regioni’ (containing data relating to the regional trend of SARS-CoV-2 spread) and ‘schede-riepilogative’ (containing summary sheets relating to the provincial and regional trends of SARS-CoV-2 spread). The Italian Civil Protection Department daily receives data by the Italian Ministry of Health, analyzes them and updates the database. Thus, the database is subject to daily updates and integrations. The database is freely accessible (CC-BY-4.0 license) at https://github.com/pcm-dpc/COVID-19. This database is useful to provide insight on the spread mechanism of SARS-CoV-2, to support organizations in the evaluation of the efficiency of current prevention and control measures, and to support governments in the future prevention decisions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/277055

Extended segmented beat modulation method for cardiac beat classification and electrocardiogram denoising
ELECTRONICS
Autore/i: Nasim, A.; Sbrollini, A.; Morettini, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Beat classification and denoising are two challenging and fundamental operations when processing digital electrocardiograms (ECG). This paper proposes the extended segmented beat modulation method (ESBMM) as a tool for automatic beat classification and ECG denoising. ESBMM includes four main steps: (1) beat identification and segmentation into PQRS and TU segments; (2) wavelet-based time-frequency feature extraction; (3) convolutional neural network-based classification to discriminate among normal (N), supraventricular (S), and ventricular (V) beats; and (4) a template-based denoising procedure. ESBMM was tested using the MIT–BIH arrhythmia database available at Physionet. Overall, the classification accuracy was 91.5% while the positive predictive values were 92.8%, 95.6%, and 83.6%, for N, S, and V classes, respectively. The signal-to-noise ratio improvement after filtering was between 0.15 dB and 2.66 dB, with a median value equal to 0.99 dB, which is significantly higher than 0 (p < 0.05). Thus, ESBMM proved to be a reliable tool to classify cardiac beats into N, S, and V classes and to denoise ECG tracings.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/283394

Annotation dataset of the cardiotocographic recordings constituting the “CTU-CHB intra-partum CTG database”
DATA IN BRIEF
Autore/i: Romagnoli, S.; Sbrollini, A.; Burattini, L.; Marcantoni, I.; Morettini, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: The proposed dataset provides annotations for the 552 cardiotocographic (CTG) recordings included in the publicly available “CTU-CHB intra-partum CTG database” from Physionet (https://physionet.org/content/ctu-uhb-ctgdb/1.0.0/). Each CTG recording is composed by two simultaneously acquired signals: i) the fetal heart rate (FHR) and ii) the maternal tocogram (representing uterine activity). Annotations consist in the detection of starting and ending points of specific CTG events on both FHR signal and maternal tocogram. Annotated events for the FHR signal are the bradycardia, tachycardia, acceleration and deceleration episodes. Annotated events for the maternal tocogram are the uterine contractions. The dataset also reports classification of each deceleration as early, late, variable or prolonged, in relation to the presence of a uterine contraction. Annotations were obtained by an expert gynecologist with the support of CTG Analyzer, a dedicated software application for automatic analysis of digital CTG recordings. These annotations can be useful in the development, testing and comparison of algorithms for the automatic analysis of digital CTG recordings, which can make CTG interpretation more objective and independent from clinician's experience.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/281117

Insulin clearance is altered in women with a history of gestational diabetes progressing to type 2 diabetes
NMCD. NUTRITION METABOLISM AND CARDIOVASCULAR DISEASES
Autore/i: Tura, A.; Gobl, C.; Morettini, M.; Burattini, L.; Kautzky-Willer, A.; Pacini, G.
Classificazione: 1 Contributo su Rivista
Abstract: Background and aims: Insulin clearance is a relevant process in glucose homeostasis. In this observational study, we aimed to assess insulin clearance (ClINS) in women with former gestational diabetes (fGDM) both early after delivery and after a follow-up. Methods and results: We analysed 59 fGDM women, and 16 women not developing GDM (CNT). All women underwent an oral glucose tolerance test (OGTT) yearly, and an insulin-modified intravenous glucose tolerance test (IVGTT) at baseline and at follow-up end (until 7 years). Both IVGTT and OGTT ClINS was assessed as insulin secretion to plasma insulin ratio. We also defined IVGTT first (0–10 min) and second phase (10–180 min) ClINS. We found that 14 fGDM women progressed to type 2 diabetes (PROG), whereas 45 women remained diabetes-free (NONPROG). At baseline, IVGTT ClINS showed alterations in PROG, especially in second phase (0.88 ± 0.10 l·min−1 in PROG, 0.60 ± 0.06 in NONPROG, 0.54 ± 0.07 in CNT, p ≤ 0.03). Differences in ClINS were not found from OGTT. Cox regression analysis showed second phase ClINS as significant type 2 diabetes predictor (hazard ratio = 1.90, 95% confidence interval 1.09–3.30, p = 0.02). Conclusion: This study showed that insulin clearance derived from an insulin-modified IVGTT is notably altered in women with history of GDM progressing towards type 2 diabetes.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/282420

Early temporal prediction of Type 2 Diabetes Risk Condition from a General Practitioner Electronic Health Record: A Multiple Instance Boosting Approach
ARTIFICIAL INTELLIGENCE IN MEDICINE
Autore/i: Bernardini, M.; Morettini, M.; Romeo, L.; Frontoni, E.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Early prediction of target patients at high risk of developing Type 2 diabetes (T2D) plays a significant role in preventing the onset of overt disease and its associated comorbidities. Although fundamental in early phases of T2D natural history, insulin resistance is not usually quantified by General Practitioners (GPs). Triglyceride-glucose (TyG) index has been proven useful in clinical studies for quantifying insulin resistance and for the early identification of individuals at T2D risk but still not applied by GPs for diagnostic purposes. The aim of this study is to propose a multiple instance learning boosting algorithm (MIL-Boost) for creating a predictive model capable of early prediction of worsening insulin resistance (low vs high T2D risk) in terms of TyG index. The MIL-Boost is applied to past electronic health record (EHR) patients’ information stored by a single GP. The proposed MIL-Boost algorithm proved to be effective in dealing with this task, by performing better than the other state-of-the-art ML competitors (Recall from 0.70 and up to 0.83). The proposed MIL-based approach is able to extract hidden patterns from past EHR temporal data, even not directly exploiting triglycerides and glucose measurements. The major advantages of our method can be found in its ability to model the temporal evolution of longitudinal EHR data while dealing with small sample size and variability in the observations (e.g., a small variable number of prescriptions for non-hospitalized patients). The proposed algorithm may represent the main core of a clinical decision support system.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/280099

Fifty Years of Biomedical Engineering: From Origin to Smart Technologies
The First Outstanding 50 Years of "Università Politecnica delle Marche"
Autore/i: Burattini, Laura; Di Nardo, Francesco; Morettini, Micaela; Verdini, Federica; Fioretti, Sandro
Classificazione: 2 Contributo in Volume
Abstract: In Italy, the Bioengineering Community was founded in 1980. The kick-off meeting was held in Montesicuro, a little village near Ancona and organized by Prof. Tommaso Leo from the then-named “Università degli Studi di Ancona” (now Università Politecnica delle Marche, UNIVPM) in cooperation with the nascent National Group of Bioengineering. This chapter aims to produce a brief review of the main results in Biomedical Engineering by UNIVPM during the first 50 years useful to understand the present and to track future contributions for the next 50 years. It is also an occasion to recall the pioneering work on the Bioengineering of the Neuromuscular, Cardiovascular and Metabolic systems performed by our leading colleagues Tommaso Leo, Paolo Mancini and Roberto Burattini, as well as to describe significant research achievements obtained by professors, researchers, post-doc fellows and PhD students who worked and/or are currently working at the UNVPM. Though mainly focusing on research findings in the above cited physiological systems, it is also worth mentioning in this chapter that UNIVPM has also an educational mission, provided by the two Biomedical Engineering courses currently active at the Engineering Faculty: the three-year Bachelor and the two-year Master (in English) courses.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/278101

Former gestational diabetes: Mathematical modeling of intravenous glucose tolerance test for the assessment of insulin clearance and its determinants
MATHEMATICAL BIOSCIENCES AND ENGINEERING
Autore/i: Morettini, Micaela; Göbl, Christian; Kautzky-Willer, Alexandra; Pacini, Giovanni; Tura, Andrea; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Women with a previous history of gestational diabetes mellitus (GDM) have increased risk of developing GDM in future pregnancies (i.e. recurrent GDM) and also Type 2 Diabetes (T2D). Insulin clearance represents one of the processes regulating glucose tolerance but has been scarcely investigated for its possible impairment in high-risk subjects. The aim of this study was to identify possible determinants of insulin clearance in women with a previous history of GDM. A detailed model-based analysis of a regular 3-hour, insulin-modified intravenous glucose tolerance test (IM-IVGTT) has been performed in women with a previous history of GDM (pGDM, n = 115) and in women who had a healthy pregnancy (CNT, n = 41) to assess total, first-phase and second-phase insulin clearance (ClINS-TOT, ClINS-FP and ClINS-SP) and other metabolic parameters (insulin sensitivity SI, glucose effectiveness SG, beta-cell function and disposition index DI). CLINS-SP was found increased in pGDM with respect to CNT and was found significantly inversely linearly correlated with SG (r = -0.20, p = 0.03, slope: -16.2, 95% CI -30.9 to -1.4, intercept: 1.1, 95% CI 0.7-1.4) and also with DI (r = -0.22, p = 0.02, slope: -10.0, 95% CI -18.5 to -1.6, intercept: 0.9, 95% CI 0.7-1.3). Disposition index, accounting for the combined contribution of insulin sensitivity and beta-cell function, and glucose effectiveness were identified as possible determinants of insulin clearance in women with a previous history of GDM. This may be of relevance for more accurate estimation and prevention of the risk for recurrent GDM and T2D.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272776

Digital cardiotocography: What is the optimal sampling frequency?
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Autore/i: Romagnoli, Sofia; Sbrollini, Agnese; Burattini, Luca; Marcantoni, Ilaria; Morettini, Micaela; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Cardiotocography (CTG) is the most popular prenatal diagnostic test for establishing fetal health and consists in simultaneous recording of fetal heart rate (FHR, bpm) and maternal uterine contraction (UC, mmHg) traces. Typically, FHR and UC traces are visually analyzed and interpreted by clinicians. Recently, software applications like CTG Analyzer have been developed to support visual CTG interpretation by making it more objective and independent from clinician’s experience. Automatic CTG analysis requires CTG-traces digitalization and thus assessment of a correct sampling frequency (SF). Thus, this paper aims to investigate dependency of automatic CTG analysis on SF in order to identify optimal SF (OSF) for FHR and UC traces that minimizes computational efforts without jeopardizing CTG interpretation. To this aim, the “CTU-CHB intra-partum CTG database” was considered and visually annotated by an expert gynecologist. FHR and UC traces, originally sampled at 4 Hz, were down sampled at 2 Hz, 1 Hz, 0.4 Hz and 0.2 Hz, and automatically analyzed using CTG Analyzer. Eventually, results obtained through automatic analysis were compared to visual annotations, which were taken as reference. A cumulative statistical index (CSI), ranging from 0.00% to 100.00%, was defined as a linear combination of positive-predictive value, sensitivity, false-positive rate and false-negative rate. OSF was defined as the one that maximizes CSI. If CSI was showing the same value for more than one SF, the lowest SF was selected as the optimal since minimizing computational efforts. Results indicate that OSF for FHR is 2 Hz (CSI ≥ 85.41%), whereas OSF for UC is 0.2 Hz (CSI = 75.21%).
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/264306

A dataset for the development and optimization of fall detection algorithms based on wearable sensors
DATA IN BRIEF
Autore/i: Cotechini, Valentina; Belli, Alberto; Palma, Lorenzo; Morettini, Micaela; Burattini, Laura; Pierleoni, Paola
Classificazione: 1 Contributo su Rivista
Abstract: This paper describes a dataset acquired on 8 subjects while simulating 13 types of falls and 5 types of Activities of Daily Living (ADL), each repeated 3 times. In details, data includes 4 simulated falls forward (falling on knees ending up lying, ending in lateral position, ending up lying, ending up lying with recovery), 4 backward (falling sitting ending up lying, ending in lateral position, ending up lying, ending up lying with recovery), 2 lateral right (ending up lying, ending up lying with recovery), 2 lateral left (ending up lying, ending up lying with recovery), and 1 syncope. Simulated ADL are: lying on a bed then standing; walking a few meters; sitting on a chair then standing; go up or down three steps; and standing after picking something. Data were acquired using a MARG sensor, a wearable multisensory device tied to the subject's waist, that recorded time-variations of the subject's acceleration and orientation (expressed through the yaw, pitch and roll angles). These data can be useful in the development and test of algorithms to automatically identify and classify fall events. Fall detection systems are particularly useful when a subject is alone and not able to stand up after a fall, since an automatic alarm can be sent remotely to receive proper help.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/264666

Electrocardiographic Alternans: A New Approach
IFMBE Proceedings
Autore/i: Marcantoni, I.; Calabrese, D.; Chiriatti, G.; Melchionda, R.; Pambianco, B.; Rafaiani, G.; Scardecchia, E.; Sbrollini, A.; Morettini, M.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Alternans is an electrophysiological phenomenon consisting in a beat-to-beat variation of the morphology of an electrocardiographic (ECG) waveform. Literature has particularly studied T-wave alternans (TWA) because it has been widely recognized as a noninvasive and clinically useful index to predict occurrence of malignant ventricular arrhythmias and, eventually, sudden cardiac death. Historically, alternans of other segments of ECG, like P wave (PWA), or QRS complex (QRSA) gained less interest than TWA, but this is an incomplete vision of the action potential (AP). AP is influenced by electrical activity of all myocardial cells, so it is reasonable that all ECG waveforms could be affected by alternans phenomenon. ECG alternans (ECGA) can be intended as the prevalent nature of alternans. This study aimed to use the heart-rate adaptive match filter (AMF) method, previously applied for TWA applications, to detect ECGA. AMF effectiveness was tested on simulated alternating ECG (alternans-amplitude range: 10 µV–200 µV), characterized by single- and multiple-wave alternans (always of the same amplitude and morphology). AMF method proved to be specific, being able to recognize ECGA absence, and particularly sensitive to TWA. In general, in case of singular-wave alternans, AMF correctly identified the type of alternans and correctly determined its amplitude (mean error: 0%). When TWA was combined to PWA or QRSA, only TWA was identified with an overestimation of its amplitude (mean error: 23%). In conclusion, overall AMF proved its effectiveness and specificity in revealing and discriminating ECGA.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272508

Insulin clearance in women with a history of gestational diabetes assessed by mathematical model analyses of intravenous glucose tolerance test
IFMBE Proceedings
Autore/i: Morettini, M.; Gobl, C.; Kautzky-Willer, A.; Pacini, G.; Tura, A.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Circulating concentrations of insulin are determined by a balance between the secretion rate of insulin from pancreatic beta-cells and insulin degradation (“clearance”). However, limited attention has been devoted to the study of insulin clearance in women with former gestational diabetes mellitus (GDM), which are known to be at increased type 2 diabetes risk. The aim of this study was to provide a detailed analysis of insulin clearance in women with former GDM. A population of 156 white Caucasian women, was analyzed early postpartum (4–6 months after delivery) and classified in two groups: women with previous GDM (pGDM, n = 115) and women that remain healthy during pregnancy (CNT, n = 41). All women underwent a 3-hour Insulin-Modified Intravenous Glucose Tolerance Test (IM-IVGTT). Insulin clearance temporal patterns were derived by mathematical modelling of IM-IVGTT data; average insulin clearance values were also considered during the whole test, and in the first - (0–10 min) and second phase (10–180 min). Insulin clearance temporal patterns were found to be different between CNT and pGDM group (p < 0.0001). Average insulin clearance was found different over the second phase of the test (p = 0.04), being equal to 0.54 [0.41] and 0.59 [0.41] l·min−1 in CNT and pGDM group, respectively. In conclusion, some abnormalities in former GDM women, compared to a group of healthy women were detected. This may be of relevance for more accurate estimation of type 2 diabetes risk.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272506

An interactive tool for the analysis of muscular recruitment during walking task
COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING: IMAGING & VISUALIZATION
Autore/i: Mengarelli, Alessandro; Cardarelli, Stefano; DI NARDO, Francesco; Burattini, Laura; Verdini, Federica; Fioretti, Sandro
Classificazione: 1 Contributo su Rivista
Abstract: The present work proposes an interactive software tool for surface electromyography signal processing and analysis, focused on the assessment of muscular activations during walking and easy-to-use also for users without signal treatment knowledge. The tool is based on two logical steps: first, an automatic detection of muscle activations is provided; then, the user can tune the value of each processing parameter, with a real-time visual feedback. A stride-to-stride evaluation of muscular recruitment and a co-contraction recognition are available, together with the computation of an average myoelectric activation pattern. The tunable signal processing tailors the analysis to any considered application, allowing to extract information from low-quality signals. A muscle activity characterisation from the single stride to the whole walking trial is also provided. Beyond gait analysis and muscles activation timing identification, this tool could be valuable also in an educational scenario, considering the interactive characteristics of the graphical user interface.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/260812

Self-Monitoring of Cardiac Risk while Running Around Ancona
2019 IEEE 23rd International Symposium on Consumer Technologies, ISCT 2019
Autore/i: Sbrollini, A.; Caraceni, G.; Nasim, A.; Marcantoni, I.; Morettini, M.; Belli, A.; Pierleoni, P.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Running is the most common physical activity. Being an aerobic activity, it can act as a trigger for critical cardiac events that may degenerate in sport-related sudden cardiac death. Nowadays, smartphone applications combined with wearable sensors are typically used to monitor runner's performance during training, but almost never to evaluate their cardiac risk conditions. Thus, aim of this study was to propose CaRiSMA as a useful Android application for self-monitoring of cardiac activity of runners while wearing a cardiac sensor and running by strictly following a route around the city of Ancona (6.1 Km). Cardiac data from 10 young runners were recorded and transferred to a smartphone to be analyzed by CaRiSMA, an Android application that provides two traffic lights as output, relative to cardiac health status of the runner and correctness of training intensity. The first traffic light was green in all cases but one for which it was yellow, indicating no risk and increased risk conditions, respectively. The second traffic light was yellow in all cases, suggesting a reduction of the training intensity. In conclusion, CaRiSMA demonstrated to be a potentially useful Android application for self-monitoring of cardiac activity of runners while wearing a cardiac sensor.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272430

PCG-Decompositor: A New Method for Fetal Phonocardiogram Filtering Based on Wavelet Transform Multi-level Decomposition
IFMBE Proceedings
Autore/i: Strazza, A.; Sbrollini, A.; Olivastrelli, M.; Piersanti, A.; Tomassini, S.; Marcantoni, I.; Morettini, M.; Fioretti, S.; Burattini, L.
Editore: Springer
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Fetal phonocardiography (FPCG) is a non-invasive acoustic recording of fetal heart sounds (fHS). The fHS auscultation plays an important diagnostic role in assessing fetal wellbeing. Typically, FPCG is a non-stationary signal corrupted by the presence of noise. Thus, high-amplitude noise makes detection of FPCG waveforms challenging. Thus, appropriate filtering procedures have to be applied in order to make FPCG clinically usable. In the recent years, Wavelet transformation (WT) filtering has been proposed. In particular, aim of this study is to propose a new method based on WT multi-level decomposition filtering: PCG-Decompositor. To this aim, PCG-Decompositor based on Coiflets mother Wavelet (4th order, 9 levels of decomposition) was applied to 119 real FPCG tracings, all available in Physionet. PCG-Decompositor is a dependent thresholding technique based on FPCG multi-level decomposition analysis. Performances of PCG-Decompositor are computed against soft-thresholding denoising technique (STDT) in terms of Root Mean Square Error (RMSE) and fetal heart rate (fHR). In terms of fHR, PCG-Decompositor and STDT are compared between themselves and also with the so-called annotations, given by the average fHR using a simultaneous cardiotocography analysis. Original signal to noise ratio (SNR) values ranged from 7.1 dB to 24.4 dB; after application of PCG-Decompositor, SNR increased significantly, ranging from 9.7 dB to 26.9 dB (P < 10−7). Moreover, PCG-Decompositor showed a lower dispersion than STDT (RMSE: 0.7 dB vs. 1.2 dB), introduced no FPCG signal delay and left fHR unaltered. Thus, PCG-Decompositor could be a suitable and robust technique to denoise FPCG signals.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272507

Dofetilide-Induced Microvolt T-Wave Alternans
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Marcantoni, I.; Laratta, R.; Mascia, G.; Ricciardi, L.; Sbrollini, A.; Nasim, A.; Morettini, M.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Dofetilide is an antiarrhythmic drug that selectively inhibits the rapid component of the delayed rectifier potassium current. The administration of dofetilide may cause ventricular arrhythmias and torsade de pointes. Electrocardiographic (ECG) microvolt T-wave alternans (TWA), an electrophysiologic phenomenon consisting in the beat-to-beat alternation of the T-wave amplitude requiring computerized algorithms to be detected, has also been associated to malignant ventricular arrhythmias. Aim of the present study was to evaluate if dofetilide induces TWA during the 24 hours following administration. The study population consisted of 22 healthy subjects ("ECG Effects of Ranolazine, Dofetilide, Verapamil, and Quinidine in Healthy Subjects" database by Physionet) to whom a 500 μg-dose of dofetilide was administered. For each subject, 10 s ECG were acquired at baseline (0.5 hour before dofetilide administration) and at 15 time points during the 24 hours following the drug administration. ECG were then processed for automatic TWA detection by correlation method. In 21 subjects out of 22, after dofetilide administration, TWA significantly increased to a peak value (median TWA values went from 6 μV at baseline to a max 32 μV; p<0.05), on average after 5 hours, to then come back to values closer to baseline. Thus, in healthy subjects, dofetilide increases occurrence and levels (6 times baseline value on average) of TWA in the hours following its administration.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/273187

Compressed Segmented Beat Modulation Method using Discrete Cosine Transform
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Autore/i: Nasim, A.; Sbrollini, A.; Marcantoni, I.; Morettini, M.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Currently used 24-hour electrocardiogram (ECG) monitors have been shown to skip detecting arrhythmias that may not occur frequently or during standardized ECG test. Hence, online ECG processing and wearable sensing applications have been becoming increasingly popular in the past few years to solve a continuous and long-term ECG monitoring problem. With the increase in the usage of online platforms and wearable devices, there arises a need for increased storage capacity to store and transmit lengthy ECG recordings, offline and over the cloud for continuous monitoring by clinicians. In this work, a discrete cosine transform (DCT) compressed segmented beat modulation method (SBMM) is proposed and its applicability in case of ambulatory ECG monitoring is tested using Massachusetts Institute of Technology-Beth Israel Deaconess Medical Center (MIT-BIH) ECG Compression Test Database containing Holter tape normal sinus rhythm ECG recordings. The method is evaluated using signal-to-noise (SNR) and compression ratio (CR) considering varying levels of signal energy in the reconstructed ECG signal. For denoising, an average SNR of 4.56 dB was achieved representing an average overall decline of 1.68 dBs (37.9%) as compared to the uncompressed signal processing while 95 % of signal energy is intact and quantized at 6 bits for signal storage (CR=2) compared to the original 12 bits, hence resulting in 50% reduction in storage size.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/273186

Model-based assessment of sex differences in glucose effectiveness and its components
IFMBE Proceedings
Autore/i: Morettini, M.; Ilari, L.; Gobl, C.; Kautzky-Willer, A.; Tura, A.; Pacini, G.; Burattini, L.
Editore: Springer
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Sex differences may assume a key role in condition of impaired glucose metabolism and progression to type 2 diabetes, affecting insulin-dependent processes. However, the presence of sex differences in non-insulin-dependent processes (i.e. glucose effectiveness) has been scarcely investigated. The aim of this study was to detect the presence of sex differences in glucose effectiveness (SG), as assessed by minimal model analysis, in subjects with different degrees of glucose metabolism impairment. Two groups of subjects ranging from normal (NGR, n = 57, males/females: 31/26) to abnormal glucose regulation (AGR, n = 115, males/females 42/73) underwent a 3-h frequently sampled intravenous glucose tolerance test. Minimal model analysis provided SG and its components at zero (GEZI) and at basal (BIE) insulin. Values for SG were 2.52 ± 0.98 10−2 min−1 and 2.81 ± 1.07 10−2 min−1 for males and females in the NGR group, and 2.08 ± 1.21 10−2 min−1 and 2.09 ± 0.98 10−2 min−1 for males and females in the AGR group. No statistically significant difference was found between males and females in both NGR (p = 0.29) and AGR (p = 0.94) groups. Sex differences were not detected for GEZI, which provided the major contribution to SGeither in NGR or AGR group. In conclusion, glucose effectiveness and its components seem to be not affected by sex differences in all glucose tolerance conditions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272505

Recurrence Quantification Analysis for Motion Artifacts in Wearable ECG Sensors
2019 IEEE 23rd International Symposium on Consumer Technologies, ISCT 2019
Autore/i: Nasim, A.; Marcantoni, I.; Sbrollini, A.; Morettini, M.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Recurrence quantification analysis (RQA) allows the measurement of signal's regular and chaotic states using recurrence plots instead of deriving information purely from visual analysis. The current study presents RQA of multiple ECG time series simultaneously recorded through different electrodes and depicts the effect of motion artifacts through electrode synchronization and non-synchronization. The ECG data is acquired from a healthy 25-year-old male performing different exercise activities such as standing, walking and jumping. Also, the electrode in every recorded signal is placed at angle offset of 0°, 45° and 90°. The RQA analysis measures recurrence rate (RR), line entropy (ENT) and average diagonal length (L) reveal a highly stable and least chaotic signal in case of standing (RR=0.73, ENT=4.94, L=106.12), somewhat stable and a bit chaotic in case of walking (RR=0.75, ENT=5.35, L=129.13) and least stable and most chaotic in case of subject performing a jump (RR=0.61, ENT=5.07, L=99.16). Secondly, highest and second highest disturbances with respect to exercise movements are observed for electrode combinations (3, 4) and (1, 4). Distinguishing values for RQA-based measures for different exercise movements suggest that RQA is a powerful tool for differentiation of regular and irregular states occurring due to motion artifacts in the temporal patterns of ECG.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272428

Recurrence Analysis of Human Body Movements during Activities of Daily Living
2019 IEEE 23rd International Symposium on Consumer Technologies, ISCT 2019
Autore/i: Nasim, A.; Morettini, M.; Marcantoni, I.; Sbrollini, A.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Recurrence quantification analysis (RQA) is used to differentiate and analyze the regular and irregular parts of a time-series signal using recurrence plots and quantification measures. This work presents RQA for human body movements during routine activities of daily life (ADL) using parameters recorded using a wearable sensor attached to the test subjects waist. The current research uses data from 8 subjects performing 5 different daily life activities, lying and stand, pick and stand, sitting and stand, step up and down, and walking. Simulating the RQA plots for activity and non-activity phases for squared vector magnitude parameter for each of the record we quantify the level of signal stability and disruption in terms of RQA analysis measures recurrence rate (RR), determinism (DET) and line entropy (ENT). The RQA parameters reveal a chaotic behavior in case of activity (RR=0.249, DET=0.510, ENT=0.732), and a stable or least chaotic behavior in case of non-activity (RR=0.466, DET=0.726, ENT=1.205) regions of time. Distinguishing values for RQA-based measures for different human body movements taking place during daily life activities might be used for human activity monitoring, fall detection for elderly and body movement modelling and analysis alaorithms.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272431

TWA Identifier for Cardiac Risk Self-Monitoring during Hemodialysis: A Case Report
2019 IEEE 23rd International Symposium on Consumer Technologies, ISCT 2019
Autore/i: Leoni, C.; Marcantoni, I.; Sbrollini, A.; Morettini, M.; Burattini, L.
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Rate of sudden cardiac death (SCD) is increased in hemodialysis (HD) patients. Cardiac risk can be evaluated in terms of electrocardiographic (ECG) T-wave alternans (TWA). Aim of the present study was to propose TWA Identifier as a software application for cardiac risk self-monitoring based on the TWA index, and to test it on a patient while performing a HD session. TWA Identifier can be installed on any portable device and may analyze real-time ECG data acquired by wearable sensors. Core of TWA Identifier is the well-established heart-rate adaptive match filter method for TWA identification. TWA Identifier quantified TWA from a continuous 24-hours ECG acquired using a wearable Holter ECG recorder in a HD patient during a HD day. The recording was divided into macro-time periods, one prior, one contemporary and two following the HD session. On average, TWA values were higher than normal, ranged from 35 μV to 78 μV, and were particularly high during the HD session, while decreased afterwards. Thus, the HD patient was at increased SCD risk, especially during the treatment. In conclusion, TWA Identifier represents a useful tool for real-time cardiac risk self-monitoring during HD.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272429

Serial electrocardiography to detect newly emerging or aggravating cardiac pathology: a deep-learning approach
BIOMEDICAL ENGINEERING ONLINE
Autore/i: Sbrollini, Agnese; De Jongh, Marjolein C.; Ter Haar, C Cato; Treskes, Roderick W.; Man, Sumche; Burattini, Laura; Swenne, Cees A.
Classificazione: 1 Contributo su Rivista
Abstract: Background: Serial electrocardiography aims to contribute to electrocardiogram (ECG) diagnosis by comparing the ECG under consideration with a previously made ECG in the same individual. Here, we present a novel algorithm to construct dedicated deep-learning neural networks (NNs) that are specialized in detecting newly emerging or aggravating existing cardiac pathology in serial ECGs. Methods: We developed a novel deep-learning method for serial ECG analysis and tested its performance in detection of heart failure in post-infarction patients, and in the detection of ischemia in patients who underwent elective percutaneous coronary intervention. Core of the method is the repeated structuring and learning procedure that, when fed with 13 serial ECG difference features (intra-individual differences in: QRS duration; QT interval; QRS maximum; T-wave maximum; QRS integral; T-wave integral; QRS complexity; T-wave complexity; ventricular gradient; QRS-T spatial angle; heart rate; J-point amplitude; and T-wave symmetry), dynamically creates a NN of at most three hidden layers. An optimization process reduces the possibility of obtaining an inefficient NN due to adverse initialization. Results: Application of our method to the two clinical ECG databases yielded 3-layer NN architectures, both showing high testing performances (areas under the receiver operating curves were 84% and 83%, respectively). Conclusions: Our method was successful in two different clinical serial ECG applications. Further studies will investigate if other problem-specific NNs can successfully be constructed, and even if it will be possible to construct a universal NN to detect any pathologic ECG change.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/263849

Glucose Effectiveness from Short Insulin-Modified IVGTT and Its Application to the Study of Women with Previous Gestational Diabetes Mellitus
DIABETES & METABOLISM JOURNAL
Autore/i: Morettini, M.; Castriota, C.; Gobl, C.; Kautzky-Willer, A.; Pacini, G.; Burattini, L.; Tura, A.
Classificazione: 1 Contributo su Rivista
Abstract: Background: This study aimed to design a simple surrogate marker (i.e., predictor) of the minimal model glucose effectiveness (SG), namely calculated SG (CSG), from a short insulin-modified intravenous glucose tolerance test (IM-IVGTT), and then to apply it to study women with previous gestational diabetes mellitus (pGDM). Methods: CSG was designed using the stepwise model selection approach on a population of subjects (n=181) ranging from normal tolerance to type 2 diabetes mellitus (T2DM). CSG was then tested on a population of women with pGDM (n=57). Each subject underwent a 3-hour IM-IVGTT; women with pGDM were observed early postpartum and after a follow-up period of up to 7 years and classified as progressors (PROG) or non-progressors (NONPROG) to T2DM. The minimal model analysis provided a reference SG. Results: CSG was described as CSG=1.06×10-2+5.71×10-2×KG/Gpeak, KG being the mean slope (absolute value) of loge glucose in 10-25- A nd 25-50-minute intervals, and Gpeak being the maximum of the glucose curve. Good agreement between CSG and SG in the general population and in the pGDM group, both at baseline and follow-up (even in PROG and NONPROG subgroups), was shown by the Bland-Altman plots (<5% observations outside limits of agreement), and by the test for equivalence (equivalence margin not higher than one standard deviation). At baseline, the PROG subgroup showed significantly lower SG and CSG values compared to the NONPROG subgroup (P<0.03). Conclusion: CSG is a valid SG predictor. In the pGDM group, glucose effectiveness appeared to be impaired in women progressing to T2DM.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/277943

Electrocardiogram-Derived Respiratory Signal in Sleep Apnea by Segmented Beat Modulation Method
2019 IEEE 23rd International Symposium on Consumer Technologies, ISCT 2019
Autore/i: Sbrollini, A.; Marcantoni, I.; Nasim, A.; Morettini, M.; Burattini, L.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The most common sleep disorder is sleep apnea, whose manifestations are long breathing pauses. Sleep apnea assessment is usually performed by polysomnography. During this long-term monitoring, patient respiration and other biosignals are recorded by many sensors, causing a high level of discomfort. Thus, methods able to indirectly estimate the biosignal of interest from the others measured should be preferred. Respiration indirectly measured from electrocardiogram (ECG) is called ECG-derived respiratory (EDR) signal. Recently, Segmented Beat Modulation Method (SBMM) was proposed as a good method for EDR signal estimation in normal breathing. Thus, the aim of this study was to assess the quality of EDR signal estimation by SBMM in pathological events of sleep apnea. With this purpose, sixteen long term polysomnographic recordings from MITBIH Polysomnographic Database were considered. After standard preprocessing, respiration and ECG signals were divided in 30s windows and, in order to match to provided annotations, each window was classified into Normal or Apnea. EDR signal was estimated by SBMM procedure from each ECG window. Respiration and EDR signals were then processed by Fourier analysis to extract respiration frequencies. Respiration frequencies computed from respiration and EDR signals were compared in term of error. Results confirmed the good quality of the estimated EDR signal. Respiration frequency extracted from EDR signal in both Normal (16[13;19]cpm) and Apnea windows (18[15;21]cpm) are equal to those extracted from respiration signal (Normal: 16 [13;19]cpm and Apnea: 18 [15;21]cpm), providing null error distributions. In conclusion, SBMM proved to be a promising tool for EDR signal estimation.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272432

Solution of Linear and Non-Linear Boundary Value Problems Using Population-Distributed Parallel Differential Evolution
JOURNAL OF ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING RESEARCH
Autore/i: Nasim, Amnah; Burattini, Laura; Fateh, Muhammad Faisal; Zameer, Aneela
Classificazione: 1 Contributo su Rivista
Abstract: Cases where the derivative of a boundary value problem does not exist or is constantly changing, traditional derivative can easily get stuck in the local optima or does not factually represent a constantly changing solution. Hence the need for evolutionary algorithms becomes evident. However, evolutionary algorithms are compute-intensive since they scan the entire solution space for an optimal solution. Larger populations and smaller step sizes allow for improved quality solution but results in an increase in the complexity of the optimization process. In this research a population-distributed implementation for differential evolution algorithm is presented for solving systems of 2 nd -order, 2-point boundary value problems (BVPs). In this technique, the system is formulated as an optimization problem by the direct minimization of the overall individual residual error subject to the given constraint boundary conditions and is then solved using differential evolution in the sense that each of the derivatives is replaced by an appropriate difference quotient approximation. Four benchmark BVPs are solved using the proposed parallel framework for differential evolution to observe the speedup in the execution time. Meanwhile, the statistical analysis is provided to discover the effect of parametric changes such as an increase in population individuals and nodes representing features on the quality and behavior of the solutions found by differential evolution. The numerical results demonstrate that the algorithm is quite accurate and efficient for solving 2 nd -order, 2-point BVPs.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/266684

Extraction of digital cardiotocographic signals from digital cardiotocographic images: Robustness of eCTG procedure
ELECTRONICS
Autore/i: Sbrollini, A.; Brini, L.; Di Tillo, M.; Marcantoni, I.; Morettini, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: A recently developed software application, eCTG, extracts cardiotocographic (CTG) signals from digital CTG images, possibly obtained by scanning paper CTG reports. The aim of this study was to evaluate eCTG robustness across varying image formats, resolution and screw. Using 552 digital CTG signals from the “CTU-UHB Intrapartum Cardiotocography Database” of Physionet, seven sets of digital CTG images were created, differing in format (.TIFF, .PNG and .JPEG), resolution(96 dpi, 300 dpi and 600 dpi) and screw (0.0◦, 0.5◦, and 1.0◦). All created images were submitted to eCTG for CTG signals extraction. Quality of extracted signals was statistically evaluated based 1) on signal morphology, by computation of the correlation coefficient (ρ) and of the mean signal error percent (MSE%), and 2) on signal clinical content, by assessment of 18 standard CTG variables.For all sets of images, ρ was high (ρ ≥ 0.81) and MSE% was small (MSE% ≤ 2%). However, significant changes occurred in median values of four, four and five standard CTG variables in image sets with 96 dpi resolution, 0.5◦ screw and 1.0◦ screw, respectively. In conclusion, for an optimal eCTG performance, digital images should be saved in lossless formats, have a resolution of at least 300 dpi and not be affected by screw.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/271089

Classification of drug-induced hERG potassium-channel block from electrocardiographic T-wave features using artificial neural networks
ANNALS OF NONINVASIVE ELECTROCARDIOLOGY
Autore/i: Morettini, M.; Peroni, C.; Sbrollini, A.; Marcantoni, I.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Background: Human ether‐à‐go‐go‐related gene (hERG) potassium‐channel block represents a harmful side effect of drug therapy that may cause torsade de pointes (TdP). Analysis of ventricular repolarization through electrocardiographic T‐wave features represents a noninvasive way to accurately evaluate the TdP risk in drug‐safety studies. This study proposes an artificial neural network (ANN) for noninvasive electrocardiography‐ based classification of the hERG potassium‐channel block. Methods: The data were taken from the “ECG Effects of Ranolazine, Dofetilide, Verapamil, and Quinidine in Healthy Subjects” Physionet database; they consisted of median vector magnitude (VM) beats of 22 healthy subjects receiving a single 500 μg dose of dofetilide. Fourteen VM beats were considered for each subject, relative to time‐points ranging from 0.5 hr before to 14.0 hr after dofetilide administration. For each VM, changes in two indexes accounting for the early and the late phases of repolarization, ΔERD30% and ΔTS/A, respectively, were computed as difference between values at each postdose time‐point and the predose time‐point. Thus, the dataset contained 286 ΔERD30%‐ΔTS/A pairs, partitioned into training, validation, and test sets (114, 29, and 143 pairs, respectively) and used as inputs of a two‐layer feedforward ANN with two target classes: high block (HB) and low block (LB). Optimal ANN (OANN) was identified using the training and validation sets and tested on the test set. Results: Test set area under the receiver operating characteristic was 0.91; sensitivity, specificity, accuracy, and precision were 0.93, 0.83, 0.92, and 0.96, respectively. Conclusion: OANN represents a reliable tool for noninvasive assessment of the hERG potassium‐channel block.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/271789

An initial exploration of subtraction electrocardiography to detect myocardial ischemia in the prehospital setting
ANNALS OF NONINVASIVE ELECTROCARDIOLOGY
Autore/i: ter Haar, C. C.; Peters, R. J. G.; Bosch, J.; Sbrollini, A.; Gripenstedt, S.; Adams, R.; Bleijenberg, E.; Kirchhof, C. J. H. J.; Alizadeh Dehnavi, R.; Burattini, L.; de Winter, R. J.; Macfarlane, P. W.; Postema, P. G.; Man, S.; Scherptong, R. W. C.; Schalij, M. J.; Maan, A. C.; Swenne, C. A.
Classificazione: 1 Contributo su Rivista
Abstract: Background: In the prehospital triage of patients presenting with symptoms suggestive of acute myocardial ischemia, reliable myocardial ischemia detection in the electrocardiogram (ECG) is pivotal. Due to large interindividual variability and overlap between ischemic and nonischemic ECG‐patterns, incorporation of a previous elective (reference) ECG may improve accuracy. The aim of the current study was to explore the potential value of serial ECG analysis using subtraction electrocardiography. Methods: SUBTRACT is a multicenter retrospective observational study, including patients who were prehospitally evaluated for acute myocardial ischemia. For each patient, an elective previously recorded reference ECG was subtracted from the ambulance ECG. Patients were classified as myocardial ischemia cases or controls, based on the in‐hospital diagnosis. The diagnostic performance of subtraction electrocardiography was tested using logistic regression of 28 variables describing the differences between the reference and ambulance ECGs. The Uni‐G ECG Analysis Program was used for state‐of‐the‐art single‐ECG interpretation of the ambulance ECG. Results: In 1,229 patients, the mean area‐under‐the‐curve of subtraction electrocardiography was 0.80 (95%CI: 0.77–0.82). The performance of our new method was comparable to single‐ECG analysis using the Uni‐G algorithm: sensitivities were 66% versus 67% (p‐value > .05), respectively; specificities were 80% versus 81% (pvalue > .05), respectively. Conclusions: In our initial exploration, the diagnostic performance of subtraction electrocardiography for the detection of acute myocardial ischemia proved equal to that of state‐of‐the‐art automated single‐ECG analysis by the Uni‐G algorithm. Possibly, refinement of both algorithms, or even integration of the two, could surpass current electrocardiographic myocardial ischemia detection.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272261

Simultaneously acquired data from contactless and wearable devices for direct and indirect heart-rate measurement
DATA IN BRIEF
Autore/i: Pierleoni, P.; Gambi, E.; Ricciuti, M.; Sbrollini, A.; Palma, L.; Belli, A.; Morettini, M.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: The proposed dataset provides a complete set of simultaneously acquired data from contactless and wearable devices for direct and indirect heart-rate measurement. Data were acquired on a total of 20 healthy white Caucasian subjects wearing no makeup (10 males and 10 females; age: 22.50 ± 1.57 years; height: 173 ± 10 cm; weight: 62.80 ± 9.52 kg) and consisted of: i) videos of the subject's face acquired by a RGB-D (Red, Green, Blue and Depth) camera (Microsoft Kinect v2), which is a contactless device; ii) electrocardiographic (ECG) recordings acquired by a clinical Holter ECG recorder (Global Instrumentation's M12R Holter), which is a wearable device; and iii) heart-rate measurements acquired from a commercial smartwatch (Moto 360 smartwatch by Motorola), which is also a wearable device. ECG recordings were processed to extract the R-peaks position and obtain a reference indirect measurement of the heart rate. A direct measurement of the heart rate was provided by the commercial smartwatch. The dataset here presented could be useful to develop new algorithms for heart-rate detection from contactless devices and to validate contactless heart-rate estimation in comparison to reference heart rate from clinical wearable devices and to heart rate from commercial wearable devices.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/269568

Wavelet filtering of fetal phonocardiography: A comparative analysis
MATHEMATICAL BIOSCIENCES AND ENGINEERING
Autore/i: Tomassini, S.; Strazza, A.; Sbrollini, A.; Marcantoni, I.; Morettini, M.; Fioretti, S.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Fetal heart rate (FHR) monitoring can serve as a benchmark to identify high-risk fetuses. Fetal phonocardiogram (FPCG) is the recording of the fetal heart sounds (FHS) by means of a small acoustic sensor placed on maternal abdomen. Being heavily contaminated by noise, FPCG processing implies mandatory filtering to make FPCG clinically usable. Aim of the present study was to perform a comparative analysis of filters based on Wavelet transform (WT) characterized by different combinations of mothers Wavelet and thresholding settings. By combining three mothers Wavelet (4th-order Coiflet, 4th-order Daubechies and 8th-order Symlet), two thresholding rules (Soft and Hard) and three thresholding algorithms (Universal, Rigorous and Minimax), 18 different WT-based filters were obtained and applied to 37 simulated and 119 experimental FPCG data (PhysioNet/PhysioBank). Filters performance was evaluated in terms of reliability in FHR estimation from filtered FPCG and noise reduction quantified by the signal-to-noise ratio (SNR). The filter obtained by combining the 4th-order Coiflet mother Wavelet with the Soft thresholding rule and the Universal thresholding algorithm was found to be optimal in both simulated and experimental FPCG data, since able to maintain FHR with respect to reference (138.7[137.7; 140.8] bpm vs. 140.2[139.7; 140.7] bpm, P > 0.05, in simulated FPCG data; 139.6[113.4; 144.2] bpm vs. 140.5[135.2; 146.3] bpm, P > 0.05, in experimental FPCG data) while strongly incrementing SNR (25.9[20.4; 31.3] dB vs. 0.7[−0.2; 2.9] dB, P < 10-14, in simulated FPCG data; 22.9[20.1; 25.7] dB vs. 15.6[13.8; 16.7] dB, P < 10-37, in experimental FPCG data). In conclusion, the WT-based filter obtained combining the 4th-order Coiflet mother Wavelet with the thresholding settings constituted by the Soft rule and the Universal algorithm provides the optimal WT-based filter for FPCG filtering according to evaluation criteria based on both noise and clinical features.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/269344

Sport Database: Cardiorespiratory data acquired through wearable sensors while practicing sports
DATA IN BRIEF
Autore/i: Sbrollini, A.; Morettini, M.; Maranesi, E.; Marcantoni, I.; Nasim, A.; Bevilacqua, R.; Riccardi, G. R.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Sport Database is a collection of 126 cardiorespiratory data, acquired through wearable sensors from 81 subjects while practicing 10 different sports. Each cardiorespiratory dataset consists of demographic info (gender, age, weight, height, smoking habit, alcohol consumption and weekly training rate), cardiorespiratory signals (electrocardiogram, heart-rate series, RR-interval series and breathing-rate series) and training notes. Demographic info was collected by survey. Cardiorespiratory signals were acquired through the chest strap BioHarness 3.0 by Zephyr. Eventually, training notes including the sport-dependent training protocol, were manually annotated. Sport Database may be useful to support: 1) the investigation of cardiorespiratory system adaptations to different types of physical exercise; 2) the development of automatic algorithms finalized to real-time health monitoring of athletes and preventive identification of subjects at increased risk of sport-related sudden cardiac death; and, 3) clinical testing of the BioHarness 3.0 by Zephyr. Further acquisitions could involve other sports, other cardiovascular signals and/or parameters, data from different biological systems, and other acquisition devices.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272255

Glucose effectiveness and its components in relation to body mass index
EUROPEAN JOURNAL OF CLINICAL INVESTIGATION
Autore/i: Morettini, M.; Di Nardo, F.; Ingrillini, Laura; Fioretti, S.; Gobl, C.; Kautzky-Willer, A.; Tura, Andrea; Pacini, Giovanni; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Background: Obesity is known to induce a deterioration of insulin sensitivity (SI), one of the insulin-dependent components of glucose tolerance. However, few studies investigated whether obesity affects also the insulin-independent component, that is glucose effectiveness (SG). This cross-sectional study aimed to analyse SG and its components in different body mass index (BMI) categories. Materials and methods: Three groups of subjects spanning different BMI (kg m−2) categories underwent a 3-h frequently sampled intravenous glucose tolerance test: Lean (LE; 18.5 ≤ BMI < 25, n = 73), Overweight (OW; 25 ≤ BMI < 30, n = 90), and Obese (OB; BMI ≥ 30, n = 41). OB has been further divided into two subgroups, namely Obese I (OB-I; 30 ≤ BMI < 35, n = 27) and Morbidly Obese (OB-M; BMI ≥ 35, n = 14). Minimal model analysis provided SG and its components at zero (GEZI) and at basal (BIE) insulin. Results: Values for SG were 1.98 ± 1.30 × 10−2·min−1 in all subjects grouped and 2.38 ± 1.23, 1.84 ± 0.82, 1.59 ± 0.61 10−2·min−1 in LE, OW and OB, respectively. In all subjects grouped, a significant inverse linear correlation was found between the log-transformed values of SG and BMI (r = −0.3, P < 0.0001). SG was significantly reduced in OW and OB with respect to LE (P < 0.001) but no significant difference was detected between OB and OW (P = 0.35) and between OB-I and OB-M (P = 0.25). Similar results were found for GEZI. BIE was not significantly different among NW, OW and OB (P = 0.11) and between OB-I and OB-M (P ≥ 0.07). Conclusions: SG and its major component GEZI deteriorate in overweight individuals compared to those in the normal BMI range, without further deterioration when BMI increases above 30 kg m−2.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/267129

TyG-er: An ensemble Regression Forest approach for identification of clinical factors related to insulin resistance condition using Electronic Health Records
COMPUTERS IN BIOLOGY AND MEDICINE
Autore/i: Bernardini, M.; Morettini, M.; Romeo, L.; Frontoni, E.; Burattini, L.
Classificazione: 1 Contributo su Rivista
Abstract: Insulin resistance is an early-stage deterioration of Type 2 diabetes. Identification and quantification of insulin resistance requires specific blood tests; however, the triglyceride-glucose (TyG) index can provide a surrogate assessment from routine Electronic Health Record (EHR) data. Since insulin resistance is a multi-factorial condition, to improve its characterisation, this study aims to discover non-trivial clinical factors in EHR data to determine where the insulin-resistance condition is encoded.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/269259

Bradycardia Assessment in Preterm Infants
IFMBE Proceedings
Autore/i: Sbrollini, A.; Mancinelli, M.; Marcantoni, I.; Morettini, M.; Burattini, L.
Editore: Springer
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Prematurity is a severe condition, usually correlated with critical outcomes. One of the major diseases in preterm infants is bradycardia, defined as the heart rate decreasing under 100 bpm for at least two heartbeats in duration. Usually, bradycardia is considered as a manifestation of immature cardiorespiratory control, but no studies investigated its nature in relation to the different clinical features of preterm infants. Thus, aim of this work is to assess the relation between bradycardia features and the main preterm infant clinical features, weight and gestational age. Ten preterm infants were considered, classified according with three criteria: the weight classification, the gestational age classification and the birth size assessment (that combined the two previous classifications). For each preterm infant, bradycardias are automatically identified and characterized in term of bradycardia features: amplitude, duration and area. Moreover, bradycardia events are classified according with their severity. Finally, bradycardia feature distributions of classes that belong to the same classification criterion were compared. Results seems suggesting that bradycardia features differences are more relevant in preterm infants with different weights than in those with different gestational age, contrary to what expected. Anyway, the best results in term of classification were obtained in the birth size assessment; thus, a combined approach that considers both weight and gestational age is preferable. Moreover, a combined evaluation of amplitude and duration for bradycardia characterization can better assess the severity of this arrhythmia and of the preterm infant clinical status.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/272504

Surface electromyography low-frequency content: Assessment in isometric conditions after electrocardiogram cancellation by the Segmented-Beat Modulation Method
INFORMATICS IN MEDICINE UNLOCKED
Autore/i: Sbrollini, Agnese; Strazza, Annachiara; Candelaresi, Silvia; Marcantoni, Ilaria; Morettini, Micaela; Fioretti, Sandro; Di Nardo, Francesco; Burattini, Laura
Classificazione: 1 Contributo su Rivista
Abstract: Background: Surface electromyography (SEMG) is widely used in clinics for assessing muscle functionality. All procedures proposed for noise reduction alter SEMG spectrum, especially in the low-frequency band (below 30 Hz). Indeed, low-frequency band is generally addressed to motion artifacts and electrocardiogram (ECG) interference without any further investigation on the possibility of SEMG having significant spectral content. The aim of the present study was evaluating SEMG frequency content to understand if low-frequency spectral content is negligible or, on the contrary, represents a significant SEMG portion potentially providing relevant clinical information. Method: Isometric recordings of five muscles (sternocleidomastoideus, erectores spinae at L4, rectus abdominis, rectus femoris and tibialis anterior) were acquired in 10 young healthy voluntary subjects. These recordings were not affected by motion artifacts by construction and were pre-processed by the Segmented-Beat Modulation Method for ECG deletion before performing spectral analysis. Results: Results indicated that SEMG frequency content is muscle and subject dependent. Overall, the 50th[25th;75th] percentiles spectrum median frequency and spectral power below 30 Hz were 74[54; 87] Hz and 18[10; 31] % of total (0–450 Hz) spectral power. Conclusions: Low-frequency spectral content represents a significant SEMG portion and should not be neglected.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/262204

Serial ECG Analysis: Absolute Rather Than Signed Changes in the Spatial QRS-T Angle Should Be Used to Detect Emerging Cardiac Pathology
Computing in Cardiology
Autore/i: Sbrollini, Agnese; de Jongh, Marjolein; Cato ter Haar, C.; W Treskes, Roderick; Man, Sumche; Burattini, Laura; A. Swenne, Cees
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Background. Larger one-time values of spatial QRS-T angle (SA) are associated with risk. However, experience how serial changes in SA (ΔSA) should be interpreted is lacking. Even within normal limits, any ΔSA likely signifies electrical remodeling. This study aimed to assess the impact of choosing either ΔSA or |ΔSA| as one of a set of serial ECG difference features that constitute the input for our deep learning serial-ECG classifier (DLSEC). Methods. DLSEC was trained and tested to detect emerging pathology in two serial ECG databases: a heart failure database and an acute ischemia database. Either ΔSA or |ΔSA| were among 13 features of serial-ECG differences. DLSEC was dynamically generated during learning, and testing area under the curve (AUC) of the receiver operating characteristic was computed. Results. The DLSECs performed well in emerging heart failure as well as in acute ischemia: testing AUCs were 72% and 84% for the heart failure database and 77% and 83% for the ischemia database, for ΔSA or |ΔSA| among the features, respectively. Conclusion. |ΔSA| among the features was superior to ΔSA in discriminating cases and controls. Our study supports the concept that any ΔSA, irrespective of its sign, indicates a worsening clinical condition. Further corroboration requires studies in other clinical situations.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/264733

A sliding mode control model for perturbed upright stance in healthy subjects
IFMBE Proceedings
Autore/i: Mengarelli, Alessandro; Fioretti, Sandro; Orlando, Giuseppe; Cardarelli, Stefano; Ismaele, Fioretti; Marco Paci, Gian; Burattini, Laura; DI NARDO, Francesco; Strazza, Annachiara; Verdini, Federica
Editore: Springer Verlag
Classificazione: 2 Contributo in Volume
Abstract: Human upright stance and balance maintenance in quiet conditions have been extensively evaluated throughout the years. However, relatively less information is available on how the central nervous system (CNS) acts to maintain balance after sudden perturbations of stance. Here, a sliding mode control (SMC) model for the characterization of balance maintenance after external perturbations is proposed. Human stance was modeled as an inverted pendulum (IP), which describes kinematics in the sagittal plane; the choice of a SMC allowed to avoid model linearization, commonly employed when using a single-link IP for bipedal stance modeling, thus providing a more accurate description of the human-stance system dynamics. Model was applied on experimental data obtained from perturbed stance trials consisting of a series of disruptions of the same magnitude. This experimental condition was able to elicit a well-known feature called “habituation rate”, which refers to the subject capacity to self-adapt his/her responses to identical perturbations. SMC parameters were identified through a robust optimization procedure. Results showed limited tracking errors for center of mass displacement. One of the SMC parameters exhibited a clear trend from the first to the last trial, appearing able to quantify the habituation rate effect. The application of such a control model to the non-quiet stance can provide additional information in understanding how the CNS tailors balance responses in different conditions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/260810

Automatic Identification of Atrial Fibrillation by Spectral Analysis of Fibrillatory Waves
Computing in Cardiology
Autore/i: Sbrollini, Agnese; Cicchetti, Krizia; DE MARTINIS, Alessia; Marcantoni, Ilaria; Morettini, Micaela; Burattini, Laura
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: A heart affected by atrial fibrillation (AF) presents atrial cells that depolarize in many sites, generating a chaotic electrical activity. On the electrocardiogram (ECG), this activity reflects in the appearance of fibrillatory (F) waves, consisting of low-amplitude oscillations at 4-10 Hz. Aim of the present study is to propose an automatic AF identification method based on F-wave frequency analysis in 10 s ECGs. To this aim, 10 s ECG from 90 healthy subjects (HSs) and 50 AF patients (AFPs) were considered. ECGs were processed by the segmented beat modulation method to reduce components in the F-wave band. Then, the power spectral density (PSD) was computed and the F-wave frequency ratio (FWFR), defined as the ratio between the spectral area in the F-wave frequency band and the total spectral area, was computed. FWFR ability to discriminate AFPs from HSs was evaluated by analyzing the area under the curve (AUC) of the receiver operating characteristic, and by computation of sensitivity, specificity and accuracy. FWFR values were higher in AFPs than in HSs (P<10-11). AUC was at least 85%, whereas sensitivity, specificity and accuracy were at least 84%, 69% and 81%, respectively. In conclusion, F-wave frequency evaluation by FWFR represents a promising clinical tool to automatically identify AF.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/264734