Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662749
Achal Dixit, Soumili Chattopadhyay
Treating Heart Failure (HF) patients with mid-range Ejection Fraction (HFmrEF) is a challenging task due to prognostic uncertainty and transitional behaviour of HFmrEF, often referred to as “grey-area”. In this study, we address the uncertainty of HFmrEF through Machine Learning (ML) by classifying it into two well studied phenotypes: HF with preserved Ejection Fraction and HF with reduced Ejection Fraction, using the data from clinical attributes. We propose a semi-supervised Active Learning based model that uses significantly lesser data to tackle the need of supervised label validation and performs on-par with supervised ML models developed for comparison. We believe the use of proposed ML models can enable experts in making informed data-driven decisions leading to the accurate prognosis of HF patients.
{"title":"Demystifying Heart Failure with Mid-Range Ejection Fraction Using Machine Learning","authors":"Achal Dixit, Soumili Chattopadhyay","doi":"10.23919/cinc53138.2021.9662749","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662749","url":null,"abstract":"Treating Heart Failure (HF) patients with mid-range Ejection Fraction (HFmrEF) is a challenging task due to prognostic uncertainty and transitional behaviour of HFmrEF, often referred to as “grey-area”. In this study, we address the uncertainty of HFmrEF through Machine Learning (ML) by classifying it into two well studied phenotypes: HF with preserved Ejection Fraction and HF with reduced Ejection Fraction, using the data from clinical attributes. We propose a semi-supervised Active Learning based model that uses significantly lesser data to tackle the need of supervised label validation and performs on-par with supervised ML models developed for comparison. We believe the use of proposed ML models can enable experts in making informed data-driven decisions leading to the accurate prognosis of HF patients.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"1119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116070328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662723
P. Nejedly, Adam Ivora, R. Smíšek, I. Viscor, Zuzana Koscova, P. Jurák, F. Plesinger
This paper introduces a winning solution (team ISIBrno-AIMT) to the PhysioNet Challenge 2021. The method is based on the ResNet deep neural network architecture with a multi-head attention mechanism for ECG classification into 26 independent groups. The model is optimized using a mixture of loss functions, i.e., binary cross-entropy, custom challenge score loss function, and sparsity loss function. Probability thresholds for each classification class are estimated using the evolutionary optimization method. The final model consists of three submodels forming a majority voting classification ensemble. The proposed method classifies ECGs with a variable number of leads, e.g., 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead. The algorithm was validated and tested on the external hidden datasets (CPSC, G12EC, undisclosed set, UMich), achieving a challenge score 0.58 for all tested lead configurations. The total training time was approximately 27 hours, i.e., 9 hours per model. The presented solution was ranked first across all 39 teams in all categories.
{"title":"Classification of ECG Using Ensemble of Residual CNNs with Attention Mechanism","authors":"P. Nejedly, Adam Ivora, R. Smíšek, I. Viscor, Zuzana Koscova, P. Jurák, F. Plesinger","doi":"10.23919/cinc53138.2021.9662723","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662723","url":null,"abstract":"This paper introduces a winning solution (team ISIBrno-AIMT) to the PhysioNet Challenge 2021. The method is based on the ResNet deep neural network architecture with a multi-head attention mechanism for ECG classification into 26 independent groups. The model is optimized using a mixture of loss functions, i.e., binary cross-entropy, custom challenge score loss function, and sparsity loss function. Probability thresholds for each classification class are estimated using the evolutionary optimization method. The final model consists of three submodels forming a majority voting classification ensemble. The proposed method classifies ECGs with a variable number of leads, e.g., 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead. The algorithm was validated and tested on the external hidden datasets (CPSC, G12EC, undisclosed set, UMich), achieving a challenge score 0.58 for all tested lead configurations. The total training time was approximately 27 hours, i.e., 9 hours per model. The presented solution was ranked first across all 39 teams in all categories.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124879801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662820
J. Lyle, M. Nandi, P. Aston
The electrocardiogram (ECG) appears highly individual in nature. By applying the Symmetric Projection Attractor Reconstruction (SPAR) method, we obtain a unique visualisation of an individual's ECG and show how the subtle inter- and intra-individual differences observed may be quantified. This preliminary study supports further development of the novel SPAR approach for patient stratification and monitoring.
{"title":"Symmetric Projection Attractor Reconstruction: Inter-Individual Differences in the ECG","authors":"J. Lyle, M. Nandi, P. Aston","doi":"10.23919/cinc53138.2021.9662820","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662820","url":null,"abstract":"The electrocardiogram (ECG) appears highly individual in nature. By applying the Symmetric Projection Attractor Reconstruction (SPAR) method, we obtain a unique visualisation of an individual's ECG and show how the subtle inter- and intra-individual differences observed may be quantified. This preliminary study supports further development of the novel SPAR approach for patient stratification and monitoring.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131575528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662804
M. Pérez-Zabalza, L. García-Mendívil, Kostantinos A Mountris, N. Smisdom, José M. Vallejo-Gil, Pedro C. Fresneda-Roldán, Javier Fañanás-Mastral, Marta Matamala-Adell, Fernando Sorribas-Berjón, Manuel Vázquez-Sancho, Javier André Bellido-Morales, Francisco Javier Mancebón-Sierra, Alexánder Sebastián Vaca-Núñez, C. Ballester-Cuenca, A. Oliván-Viguera, L. Ordovás, Emilio L. Pueyo
Aging is known to involve alterations in the composition and organization of the extracellular matrix, which have an impact on heart function. However, there is not a comprehensive description of how collagen characteristics vary with age in the human left ventricle (LV) and its impact on electrophysiological properties. Here, we quantified the amount and spatial organization of collagen from human LV second harmonic generation (SHG) microscopy images of middle-age and elderly individuals. The results were input to in silico models of human LV tissues and numerical simulations were conducted to characterize the effects on electrical conduction and repolarization. Results from SHG image processing showed an increase in the amount of collagen and in its clustering in LV tissues with age. The increase in the amount of fibrosis induced a clear decrease in conduction velocity (CV), whereas increased clustering did not impact CV in our simulated tissues. In terms of ventricular repolarization, we observed a remarkable reduction in action potential duration (APD) as the percentage of fibrosis increased and a slighter reduction with increasing clustering. Importantly, more clustered fibrosis had a major effect on the enhancement of spatial APD dispersion, which was, however, diminished with increased fibrosis percentage. As a conclusion, both the amount and spatial organization offibrosis in human LV tissues have a relevant role in electrophysiological properties.
{"title":"Age-associated changes in fibrosis amount and spatial organization and its effects on human ventricular electrophysiology","authors":"M. Pérez-Zabalza, L. García-Mendívil, Kostantinos A Mountris, N. Smisdom, José M. Vallejo-Gil, Pedro C. Fresneda-Roldán, Javier Fañanás-Mastral, Marta Matamala-Adell, Fernando Sorribas-Berjón, Manuel Vázquez-Sancho, Javier André Bellido-Morales, Francisco Javier Mancebón-Sierra, Alexánder Sebastián Vaca-Núñez, C. Ballester-Cuenca, A. Oliván-Viguera, L. Ordovás, Emilio L. Pueyo","doi":"10.23919/cinc53138.2021.9662804","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662804","url":null,"abstract":"Aging is known to involve alterations in the composition and organization of the extracellular matrix, which have an impact on heart function. However, there is not a comprehensive description of how collagen characteristics vary with age in the human left ventricle (LV) and its impact on electrophysiological properties. Here, we quantified the amount and spatial organization of collagen from human LV second harmonic generation (SHG) microscopy images of middle-age and elderly individuals. The results were input to in silico models of human LV tissues and numerical simulations were conducted to characterize the effects on electrical conduction and repolarization. Results from SHG image processing showed an increase in the amount of collagen and in its clustering in LV tissues with age. The increase in the amount of fibrosis induced a clear decrease in conduction velocity (CV), whereas increased clustering did not impact CV in our simulated tissues. In terms of ventricular repolarization, we observed a remarkable reduction in action potential duration (APD) as the percentage of fibrosis increased and a slighter reduction with increasing clustering. Importantly, more clustered fibrosis had a major effect on the enhancement of spatial APD dispersion, which was, however, diminished with increased fibrosis percentage. As a conclusion, both the amount and spatial organization offibrosis in human LV tissues have a relevant role in electrophysiological properties.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127676994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662800
Mohamadamin Forouzandehmehr, C. Bartolucci, J. Hyttinen, Jussi T. Koivumäki, M. Paci
Myocardial acute ischemia is due to a reduced or suppressed blood supply to the heart. It heavily impacts the electrical and mechanical functionality of cardiomyocytes (CMs), up to cell necrosis. We evaluate the effects of the three main consequences of acute ischemia (hypoxia, acidosis, and hyperkalemia) on the recent Bartolucci-Passini-Severi (BPS2020) model of human adult ventricular CM. We run a sensitivity analysis considering different ischemia severity, mechanisms, and formulations of the ATP-sensitive K+ current (IKATP), initially not included in BPS2020. We further compare our results with other in silico and in vitro data and evaluate the BPS2020 capability to simulate alternans in ischemia. Hyperkalemia remarkably depolarized the resting membrane potential and reduced the maximum upstroke velocity. Acidosis slightly shortened the action potential (AP) duration. Hypoxia mainly reduced the AP duration and its peak. Our results agree with simulations performed with other in silico models. Finally, the full ischemia model produced alternans at fast pacing. Our sensitivity analysis demonstrates that the BPS2020 model correctly recapitulates the acute ischemia effects, and it is suitable for more advanced simulations.
{"title":"Sensitivity of the Human Ventricular BPS2020 Action Potential Model to the In Silico Mechanisms of Ischemia","authors":"Mohamadamin Forouzandehmehr, C. Bartolucci, J. Hyttinen, Jussi T. Koivumäki, M. Paci","doi":"10.23919/cinc53138.2021.9662800","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662800","url":null,"abstract":"Myocardial acute ischemia is due to a reduced or suppressed blood supply to the heart. It heavily impacts the electrical and mechanical functionality of cardiomyocytes (CMs), up to cell necrosis. We evaluate the effects of the three main consequences of acute ischemia (hypoxia, acidosis, and hyperkalemia) on the recent Bartolucci-Passini-Severi (BPS2020) model of human adult ventricular CM. We run a sensitivity analysis considering different ischemia severity, mechanisms, and formulations of the ATP-sensitive K+ current (IKATP), initially not included in BPS2020. We further compare our results with other in silico and in vitro data and evaluate the BPS2020 capability to simulate alternans in ischemia. Hyperkalemia remarkably depolarized the resting membrane potential and reduced the maximum upstroke velocity. Acidosis slightly shortened the action potential (AP) duration. Hypoxia mainly reduced the AP duration and its peak. Our results agree with simulations performed with other in silico models. Finally, the full ischemia model produced alternans at fast pacing. Our sensitivity analysis demonstrates that the BPS2020 model correctly recapitulates the acute ischemia effects, and it is suitable for more advanced simulations.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133465721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662785
Matteo Falanga, A. Masci, A. Chiaravalloti, F. Ansaloni, C. Tomasi, C. Corsi
Atrial Fibrillation (AF) is associated with a five-fold increase in the risk of cerebrovascular events. Recent studies suggest that a computational fluid-dynamics (CFD) approach could provide insights on AF mechanisms thus potentially allowing a quantitative assessment of cardioembolic risk. The goal of this study was to use a previously developed patient specific CFD model of the left atrium (LA) to enhance differences in blood flow in AF patients and normal subjects. In this study we computed LA blood flow and derived parameters in normal subjects (NL), patients affected by paroxysmal AF (PAR-AF) and patients affected by persistent AF (PER-AF). Results showed mean peak velocities continuously decreasing from NL to PER-AF groups. In agreement, a lower number of vortex structures was observed in PER-AF with respect to PAR-AF and NL, thus limiting an effective washout of the LA and the left atrial appendage (LAA). Velocities at the LAA ostium and inside the LAA were also strongly reduced showing a limited washout effect as confirmed by blood stasis in terms of number of particles still present after five cardiac cycles (NL: 5±2, PAR-AF: 18±3, PER-AF: 41±10). The developed approach quantifies differences in LA hemodynamic between AF patients and NL.
{"title":"Left Atrium Hemodynamic in Atrial Fibrillation and Normal Subjects","authors":"Matteo Falanga, A. Masci, A. Chiaravalloti, F. Ansaloni, C. Tomasi, C. Corsi","doi":"10.23919/cinc53138.2021.9662785","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662785","url":null,"abstract":"Atrial Fibrillation (AF) is associated with a five-fold increase in the risk of cerebrovascular events. Recent studies suggest that a computational fluid-dynamics (CFD) approach could provide insights on AF mechanisms thus potentially allowing a quantitative assessment of cardioembolic risk. The goal of this study was to use a previously developed patient specific CFD model of the left atrium (LA) to enhance differences in blood flow in AF patients and normal subjects. In this study we computed LA blood flow and derived parameters in normal subjects (NL), patients affected by paroxysmal AF (PAR-AF) and patients affected by persistent AF (PER-AF). Results showed mean peak velocities continuously decreasing from NL to PER-AF groups. In agreement, a lower number of vortex structures was observed in PER-AF with respect to PAR-AF and NL, thus limiting an effective washout of the LA and the left atrial appendage (LAA). Velocities at the LAA ostium and inside the LAA were also strongly reduced showing a limited washout effect as confirmed by blood stasis in terms of number of particles still present after five cardiac cycles (NL: 5±2, PAR-AF: 18±3, PER-AF: 41±10). The developed approach quantifies differences in LA hemodynamic between AF patients and NL.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133614442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662675
P. Priya, Srinivasan Jayaraman
The interaction mechanisms of Hydroxychloroquine (HCQ) in a COVID-19 infected ventricle and its vulnerability to arrhythmogenesis for different dosage levels is not clearly understood. To address this, a 2D transmural anisotropic ventricular tissue model consisting of endocardial, midmyocardial and epicardial myocytes are config-uredfor mild and severe COVID-19 conditions as well as for three dosage levels of HCQ $1 mu M, 10 mu M$ and 100 $mu M)$. Results show that under control and mild COVID conditions, increasing the dosage of HCQ prolongs the QT interval as well as QRS duration, although under severe COVID-19 conditions, inverted T-waves are observed. In addition, on pacing with premature beats (PBs), it is observed that under all condition, premature ventricular complexes (PVCs) are created at $1 mu M$ and $10 mu M$ HCQ. However, the PVCs are sustained for a longer duration in presence of $10 mu M$ HCQ. ST elevation is observed under mild COVID-19 conditions and $1 mu M$ HCQ and reentrant arrhythmic activity is generated in severe COVID-19 conditions and $10 mu M$ HCQ dosage. Under all conditions, $100 mu M$ HCQ doesn't generate arrhythmia or PVCs in presence of PBs. This in-silico ventricular model indicates that the dosage of HCQ as well as pacing sequence influences the appearance of arrhythmic activity and could help in guiding HCQ therapy.
{"title":"Influence of Hydroxychloroquine Dosage on the Occurrence of Arrhythmia in COVID-19 Infected Ventricle","authors":"P. Priya, Srinivasan Jayaraman","doi":"10.23919/cinc53138.2021.9662675","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662675","url":null,"abstract":"The interaction mechanisms of Hydroxychloroquine (HCQ) in a COVID-19 infected ventricle and its vulnerability to arrhythmogenesis for different dosage levels is not clearly understood. To address this, a 2D transmural anisotropic ventricular tissue model consisting of endocardial, midmyocardial and epicardial myocytes are config-uredfor mild and severe COVID-19 conditions as well as for three dosage levels of HCQ $1 mu M, 10 mu M$ and 100 $mu M)$. Results show that under control and mild COVID conditions, increasing the dosage of HCQ prolongs the QT interval as well as QRS duration, although under severe COVID-19 conditions, inverted T-waves are observed. In addition, on pacing with premature beats (PBs), it is observed that under all condition, premature ventricular complexes (PVCs) are created at $1 mu M$ and $10 mu M$ HCQ. However, the PVCs are sustained for a longer duration in presence of $10 mu M$ HCQ. ST elevation is observed under mild COVID-19 conditions and $1 mu M$ HCQ and reentrant arrhythmic activity is generated in severe COVID-19 conditions and $10 mu M$ HCQ dosage. Under all conditions, $100 mu M$ HCQ doesn't generate arrhythmia or PVCs in presence of PBs. This in-silico ventricular model indicates that the dosage of HCQ as well as pacing sequence influences the appearance of arrhythmic activity and could help in guiding HCQ therapy.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"108 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114026631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662849
G. Luongo, S. Schuler, M. Rivolta, O. Dössel, R. Sassi, A. Loewe
Atrial flutter (AFl) is a common heart rhythm disorder driven by different self-sustaining electrophysiological atrial mechanisms. In this work, we tried to automatically distinguish the macro-mechanism sustaining the arrhythmia in an individual patient using the non-invasive 12-lead electrocardiogram (ECG). We implemented a concurrent clustering and classification algorithm (CCC) to discriminate the clinical classes and look for potential similarities between patient features in each class, thus suggesting that these patients would require a similar treatment. The CCC performance was then compared to a standard supervised technique (K-nearest neighbor, KNN). 3-class classification (macro-reentry right atrium, macro-reentry left atrium, and others) achieved 48.3% and 72.0% CCC and KNN accuracy, respectively. 4-class classification (tri-cuspidal reentry, mitral reentry, fig-8 macro-reentry, and others) achieved 41.6% and 71.2% CCC and KNN accuracy, respectively. Our results show that a clustering approach does not improve the performance of AFl classification because the semi-supervised method leads to clusters that are strongly overlapping between the different ground truth classes. In contrast, the supervised learning approach shows potential for the classification, although constrained by the complexity and the multiple variables that influence the underlying mechanisms.
{"title":"Semi-Supervised vs. Supervised Learning for Discriminating Atrial Flutter Mechanisms Using the 12-lead ECG","authors":"G. Luongo, S. Schuler, M. Rivolta, O. Dössel, R. Sassi, A. Loewe","doi":"10.23919/cinc53138.2021.9662849","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662849","url":null,"abstract":"Atrial flutter (AFl) is a common heart rhythm disorder driven by different self-sustaining electrophysiological atrial mechanisms. In this work, we tried to automatically distinguish the macro-mechanism sustaining the arrhythmia in an individual patient using the non-invasive 12-lead electrocardiogram (ECG). We implemented a concurrent clustering and classification algorithm (CCC) to discriminate the clinical classes and look for potential similarities between patient features in each class, thus suggesting that these patients would require a similar treatment. The CCC performance was then compared to a standard supervised technique (K-nearest neighbor, KNN). 3-class classification (macro-reentry right atrium, macro-reentry left atrium, and others) achieved 48.3% and 72.0% CCC and KNN accuracy, respectively. 4-class classification (tri-cuspidal reentry, mitral reentry, fig-8 macro-reentry, and others) achieved 41.6% and 71.2% CCC and KNN accuracy, respectively. Our results show that a clustering approach does not improve the performance of AFl classification because the semi-supervised method leads to clusters that are strongly overlapping between the different ground truth classes. In contrast, the supervised learning approach shows potential for the classification, although constrained by the complexity and the multiple variables that influence the underlying mechanisms.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114499751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662740
B. Puszkarski, K. Hryniów, G. Sarwas
Introduction: Recurrent Neural Networks are useful tools for the prediction and classification of ECG problems. The most commonly used network for such a solution is Long Short-Term Memory (LSTM) architecture. This study aims to assess if another state-of-the-art solution, Neural Basis Expansion Analysis for Interpretable Time Series (N-BEATS), can be adopted to diagnose the same cardiac problems. In addition, a comparison is conducted for a different number of electrocardiogram leads. Methods: Two architectures were tested for performance and dimension reduction problems, both in variants consisting of blended branches, allowing retaining accuracy while reducing the computational capacity needed. Results: Our team's (WEAIT) entry was scored incorrectly due to unexpected formatting in outputs; hence only results from cross-validation are presented. LSTM outperforms N-BEATS in terms of multi-label classification, data set resilience, and obtained challenge metrics. Still, N-BEATS can obtain acceptable results and outperforms LSTM in terms of complexity and speed. Conclusions: This paper features a novel approach of using the N-BEATS, which was previously used only for forecasting, to classify ECG signals with success. While N-BEATS multi-label classification capacity is lower than LSTM, its speed allows it to be used on wearable devices.
{"title":"N-BEATS for Heart Dysfunction Classification","authors":"B. Puszkarski, K. Hryniów, G. Sarwas","doi":"10.23919/cinc53138.2021.9662740","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662740","url":null,"abstract":"Introduction: Recurrent Neural Networks are useful tools for the prediction and classification of ECG problems. The most commonly used network for such a solution is Long Short-Term Memory (LSTM) architecture. This study aims to assess if another state-of-the-art solution, Neural Basis Expansion Analysis for Interpretable Time Series (N-BEATS), can be adopted to diagnose the same cardiac problems. In addition, a comparison is conducted for a different number of electrocardiogram leads. Methods: Two architectures were tested for performance and dimension reduction problems, both in variants consisting of blended branches, allowing retaining accuracy while reducing the computational capacity needed. Results: Our team's (WEAIT) entry was scored incorrectly due to unexpected formatting in outputs; hence only results from cross-validation are presented. LSTM outperforms N-BEATS in terms of multi-label classification, data set resilience, and obtained challenge metrics. Still, N-BEATS can obtain acceptable results and outperforms LSTM in terms of complexity and speed. Conclusions: This paper features a novel approach of using the N-BEATS, which was previously used only for forecasting, to classify ECG signals with success. While N-BEATS multi-label classification capacity is lower than LSTM, its speed allows it to be used on wearable devices.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"68 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114793592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662795
P. Jurák, P. Leinveber, F. Plesinger, K. Čurila, I. Viscor, V. Vondra, M. Matejkova, L. Znojilova, R. Smíšek, J. Lipoldova, F. Prinzen, J. Halámek
Background: We introduce a new technology that uses the ultra-high-frequency components (150–1000 Hz) of the electrocardiogram (UHF-ECG). Method: The UHF-ECG components represent weak signals generated by the depolarization of myocardial cells. The amplitude of UHF oscillations decreases with distance from the source. This property and the different timing of depolarization in the ventricles' volume enable mapping of the ventricular activation from the chest ECG leads. Because of a low signal-to-noise ratio of UHF oscillations, averaging must be performed. Single recording thus lasts 30 seconds and more. Results: UHF-ECG defines the time-spatial distribution of myocardial electrical activity. Corresponding numerical parameters are electrical dyssynchrony (e-DYS) and the duration of local depolarization (Vd). UHF ventricular depolarization maps present details of electrical activation. Conclusion: The UHF-ECG uses a new source of information originating in ventricular volumes that is different from the standard ECG. It provides information about the volumetric electrical activation associated with mechanical contraction. Its primary clinical utilization is in cardiac resynchronization, pacing optimization, and conduction system pacing.
{"title":"Ultra-High-Frequency Electrocardiography","authors":"P. Jurák, P. Leinveber, F. Plesinger, K. Čurila, I. Viscor, V. Vondra, M. Matejkova, L. Znojilova, R. Smíšek, J. Lipoldova, F. Prinzen, J. Halámek","doi":"10.23919/cinc53138.2021.9662795","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662795","url":null,"abstract":"Background: We introduce a new technology that uses the ultra-high-frequency components (150–1000 Hz) of the electrocardiogram (UHF-ECG). Method: The UHF-ECG components represent weak signals generated by the depolarization of myocardial cells. The amplitude of UHF oscillations decreases with distance from the source. This property and the different timing of depolarization in the ventricles' volume enable mapping of the ventricular activation from the chest ECG leads. Because of a low signal-to-noise ratio of UHF oscillations, averaging must be performed. Single recording thus lasts 30 seconds and more. Results: UHF-ECG defines the time-spatial distribution of myocardial electrical activity. Corresponding numerical parameters are electrical dyssynchrony (e-DYS) and the duration of local depolarization (Vd). UHF ventricular depolarization maps present details of electrical activation. Conclusion: The UHF-ECG uses a new source of information originating in ventricular volumes that is different from the standard ECG. It provides information about the volumetric electrical activation associated with mechanical contraction. Its primary clinical utilization is in cardiac resynchronization, pacing optimization, and conduction system pacing.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123731580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：