K. Gillette, M. Gsell, S. Kurath-Koller, M. Manninger, A. Prassl, D. Scherr, G. Plank
Introduction: The location of the accessory pathway $(AP)$ in Wolff-Parkinson-White $(WPW)$ may serve as a bio-marker for patient morbidity. We therefore aimed to investigate the influence of the location of a typical $AV$ bypass tract on the 12 lead ECG using a physiologically-detailed whole heart model of electrophysiology $(EP)$ that is capable of providing in-depth information on the underlying electrical mechanisms of $WPW$ Methods: In previous work, a physiologically-detailed model of whole heart $EP$ was built and personalized for a single subject to generate a realistic normal sinus rhythm. Locations of APs used were automatically inserted within the heart using universal ventricular coordinates (UVCs) to model a typical AV bypass tract. For every location, cardiac sources and 12 lead ECGs were computed using an efficient cardiac simulator. 12 lead ECGs were evaluated for clinical markers of $WPW$ Electrical mechanisms are explored for two locations exhibiting highest and lowest morphological differences in the 12 lead $ECG$. Results: Retrograde activation of the His-Purkinje System (HPS) that later merges with the wave-front stemming from normal activation of the $HPS$ is observed. Not all $APs$ resulted in 12 lead ECGs exhibiting morphological markers for $WPW$ under clinical evaluation. This may be due to the representation of the $AP$ or inherent dynamics of $WPW$
{"title":"Exploring Role of Accessory Pathway Location in Wolff-Parkinson-White Syndrome in a Model of Whole Heart Electrophysiology","authors":"K. Gillette, M. Gsell, S. Kurath-Koller, M. Manninger, A. Prassl, D. Scherr, G. Plank","doi":"10.22489/CinC.2022.057","DOIUrl":"https://doi.org/10.22489/CinC.2022.057","url":null,"abstract":"Introduction: The location of the accessory pathway $(AP)$ in Wolff-Parkinson-White $(WPW)$ may serve as a bio-marker for patient morbidity. We therefore aimed to investigate the influence of the location of a typical $AV$ bypass tract on the 12 lead ECG using a physiologically-detailed whole heart model of electrophysiology $(EP)$ that is capable of providing in-depth information on the underlying electrical mechanisms of $WPW$ Methods: In previous work, a physiologically-detailed model of whole heart $EP$ was built and personalized for a single subject to generate a realistic normal sinus rhythm. Locations of APs used were automatically inserted within the heart using universal ventricular coordinates (UVCs) to model a typical AV bypass tract. For every location, cardiac sources and 12 lead ECGs were computed using an efficient cardiac simulator. 12 lead ECGs were evaluated for clinical markers of $WPW$ Electrical mechanisms are explored for two locations exhibiting highest and lowest morphological differences in the 12 lead $ECG$. Results: Retrograde activation of the His-Purkinje System (HPS) that later merges with the wave-front stemming from normal activation of the $HPS$ is observed. Not all $APs$ resulted in 12 lead ECGs exhibiting morphological markers for $WPW$ under clinical evaluation. This may be due to the representation of the $AP$ or inherent dynamics of $WPW$","PeriodicalId":117840,"journal":{"name":"2022 Computing in Cardiology (CinC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122569305","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}
Maria Gordeeva, I. Serdiukova, A. Krasichkov, E. Parmon
The aim of the study was to investigate the relationship between a left ventricular ejection fraction $(EF)$ and $ECG$ patterns associated with structural changes of the myocardium (pathological $Q$ wave, fragmentated $QRS$ complex $(fQRS)$, early repolarization pattern $(ERP). The$ study included 148. According to the level of $EF$, patients were divided into three groups: Group 1 - patients with low $EF(lEF)$ (less than 40%), group 2 - patients with mildly reduced $EF(mrEF)$ (40-49%); group 3 - patients with preserved $EF(pEF)$ (more than 50%). In the 1st group $(EF)fQRS$ was registered in 16 (51.6%) patients, in the mrEF - in 16 (18.2%). Pathological $Q$ wave was detected in $lEF$ in 20 (65%), in $mrEF$ in 10 (35%), 15 (18%), in $pEF$ in 15 (18%). The $fQRS$ has been found to be more important in identifying patients with $mrEF$, In $lEF$ in 2 (6.5%) patients, in mrEF - in 2 (6.9%), in pEF - in 11 (12.5%). There was no relationship between $ERP$ and $EF$.
{"title":"Relationship Between ECG-pattern of Depolarization Abnormalities and an Mildly Reduced Ejection Fraction","authors":"Maria Gordeeva, I. Serdiukova, A. Krasichkov, E. Parmon","doi":"10.22489/CinC.2022.204","DOIUrl":"https://doi.org/10.22489/CinC.2022.204","url":null,"abstract":"The aim of the study was to investigate the relationship between a left ventricular ejection fraction <tex>$(EF)$</tex> and <tex>$ECG$</tex> patterns associated with structural changes of the myocardium (pathological <tex>$Q$</tex> wave, fragmentated <tex>$QRS$</tex> complex <tex>$(fQRS)$</tex>, early repolarization pattern <tex>$(ERP). The$</tex> study included 148. According to the level of <tex>$EF$</tex>, patients were divided into three groups: Group 1 - patients with low <tex>$EF(lEF)$</tex> (less than 40%), group 2 - patients with mildly reduced <tex>$EF(mrEF)$</tex> (40-49%); group 3 - patients with preserved <tex>$EF(pEF)$</tex> (more than 50%). In the 1st group <tex>$(EF)fQRS$</tex> was registered in 16 (51.6%) patients, in the mrEF - in 16 (18.2%). Pathological <tex>$Q$</tex> wave was detected in <tex>$lEF$</tex> in 20 (65%), in <tex>$mrEF$</tex> in 10 (35%), 15 (18%), in <tex>$pEF$</tex> in 15 (18%). The <tex>$fQRS$</tex> has been found to be more important in identifying patients with <tex>$mrEF$</tex>, In <tex>$lEF$</tex> in 2 (6.5%) patients, in mrEF - in 2 (6.9%), in pEF - in 11 (12.5%). There was no relationship between <tex>$ERP$</tex> and <tex>$EF$</tex>.","PeriodicalId":117840,"journal":{"name":"2022 Computing in Cardiology (CinC)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123086631","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}
R. Molero, J. Reventós-Presmanes, I. Roca, L. Mont, A. Climent, M. Guillem
Electrocardiographic Imaging (ECGI) allows computing the electrical activity in the epicardium by inverting the electrical propagation matrix, which can be solved by regularizing this ill-posed problem. The objective of this study is to evaluate the effects of noise on the signals in the selection of the regularization parameter $(lambda)$ by zero-order Tikhonov and L-curve optimization. Fourteen atrial fibrillation (AF) simulations were used for computing the ECGI with different noise levels (3, 10, 20, 30, and 40dB). Signals of real cardiac rhythms were also used to compute the $ECGI(3 AF, 2$ atrial flutters, 3 atrial pacing, 3 atrial sinus rhythm and 3 ventricular tachycardia). For simulations and patients, maximum L-curve curvature and $lambda$ were obtained and compared. The maximum curvature of the L-curve, noise level and optimal $lambda$ correlated for ${A}F$ simulations. Higher levels of noise resulted in smaller curvatures of the L-curve and the selection of higher values $of lambda$, reducing the amplification of noise when computing ECGI. Real cardiac signals of AF presented similar results in curvature and $lambda$ as the higher values of noise explored in simulations $(3dB, lambda > 10^{-6}$, curvature $< 1$). The noise of the signal proportionally affects to the reconstruction of ECGI. The given results show a methodology to obtain trustable ECGI maps based on the shape of the L-curve optimization.
{"title":"Impact of Noise on Electrocardiographic Imaging Resolution with Zero Order Tikhonov Regularization and L-Curve Optimization","authors":"R. Molero, J. Reventós-Presmanes, I. Roca, L. Mont, A. Climent, M. Guillem","doi":"10.22489/CinC.2022.214","DOIUrl":"https://doi.org/10.22489/CinC.2022.214","url":null,"abstract":"Electrocardiographic Imaging (ECGI) allows computing the electrical activity in the epicardium by inverting the electrical propagation matrix, which can be solved by regularizing this ill-posed problem. The objective of this study is to evaluate the effects of noise on the signals in the selection of the regularization parameter $(lambda)$ by zero-order Tikhonov and L-curve optimization. Fourteen atrial fibrillation (AF) simulations were used for computing the ECGI with different noise levels (3, 10, 20, 30, and 40dB). Signals of real cardiac rhythms were also used to compute the $ECGI(3 AF, 2$ atrial flutters, 3 atrial pacing, 3 atrial sinus rhythm and 3 ventricular tachycardia). For simulations and patients, maximum L-curve curvature and $lambda$ were obtained and compared. The maximum curvature of the L-curve, noise level and optimal $lambda$ correlated for ${A}F$ simulations. Higher levels of noise resulted in smaller curvatures of the L-curve and the selection of higher values $of lambda$, reducing the amplification of noise when computing ECGI. Real cardiac signals of AF presented similar results in curvature and $lambda$ as the higher values of noise explored in simulations $(3dB, lambda > 10^{-6}$, curvature $< 1$). The noise of the signal proportionally affects to the reconstruction of ECGI. The given results show a methodology to obtain trustable ECGI maps based on the shape of the L-curve optimization.","PeriodicalId":117840,"journal":{"name":"2022 Computing in Cardiology (CinC)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124574283","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}
This paper aims to find out the difference of human photoplehysmography (PPG) morphological parameter K between in normal oxygen concentration regions and in low oxygen level environments. We implemented an experiment with a normobaric hypoxic chamber which generalized low oxygen level environment of 13.4% (equivalent to the altitude of 3600 m). The experiment contained two sections-10 minutes short exposure and a night of sleep. Fingertip PPG signal was recorded in the whole process. We carried out a comparative analysis for each subject in normal and hypoxic conditions. Result showed that the average K values in normoxic environment and hypoxic conditions for short exposure were 0.3456 and 0.3861 respectively, and for sleep were 0.3081 and 0.3419 respectively. Significance level p were both less than 0.05. Variations of PPG waveform parameter K reflect the changed peripheral vascular resistance. In hypoxic environment, the raised K value tallied with the physiological mechanism that hypoxic exposure increases peripheral vascular resistance. And this phenomenon happened since the beginning of hypoxia and could last for at least a night.
{"title":"Effect of Oxygen Concentration Reduction on Photoplethysmographic Waveform Characteristics","authors":"Yang Li, Jianqing Li, Zhengtao Cao, Chengyu Liu","doi":"10.22489/CinC.2022.120","DOIUrl":"https://doi.org/10.22489/CinC.2022.120","url":null,"abstract":"This paper aims to find out the difference of human photoplehysmography (PPG) morphological parameter K between in normal oxygen concentration regions and in low oxygen level environments. We implemented an experiment with a normobaric hypoxic chamber which generalized low oxygen level environment of 13.4% (equivalent to the altitude of 3600 m). The experiment contained two sections-10 minutes short exposure and a night of sleep. Fingertip PPG signal was recorded in the whole process. We carried out a comparative analysis for each subject in normal and hypoxic conditions. Result showed that the average K values in normoxic environment and hypoxic conditions for short exposure were 0.3456 and 0.3861 respectively, and for sleep were 0.3081 and 0.3419 respectively. Significance level p were both less than 0.05. Variations of PPG waveform parameter K reflect the changed peripheral vascular resistance. In hypoxic environment, the raised K value tallied with the physiological mechanism that hypoxic exposure increases peripheral vascular resistance. And this phenomenon happened since the beginning of hypoxia and could last for at least a night.","PeriodicalId":117840,"journal":{"name":"2022 Computing in Cardiology (CinC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128543209","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}
Beatrice De Maria, V. Bari, B. Cairo, F. Gelpi, D. Lucini, M. Pagani, M. Malacarne, A. Catai, Mariana de Oliveira Gois, F. Perego, L. Vecchia, A. Porta
In the last years there is increasing interest in the study of the effects of physical activity on the cardiovascular control of athletes by heart period (HP) and QT interval (QT) variability analysis. However, the relation between HP and QT variability in athletes has been poorly investigated. Therefore, we aimed at estimate transfer function gain (TFG) to typify the relationship between HP and QT variability in athletes. We acquired electrocardiogram in 18 half-marathon runners while supine (REST) and during active standing (STAND) at baseline (B) and at a 10-year follow up (FU). The TFG was computed as the ratio between the modulus of the cross-spectral density between HP and QT divided by the power spectral density of HP in low frequency (LF, 0.04-0.15 Hz, TFGLF) and high frequency (HF, 0.15-0.4 Hz, TFGHF) bands. We found that TFGHF was lower at FU compared to B both at REST and during STAND. TFGLF increased during STAND compared to REST only at FU. The present work supports the use of the linear approach in the frequency domain to typify the cardiac control of athletes. In addition, the findings suggest that a moderate and regular physical activity through the years is beneficial as it favors a decrease of the cardiac sympathetic modulation.
{"title":"Transfer Function Gain Between Heart Period and QT Interval Variability Decreases at a 10-Year Follow-up in Half-Marathon Runners","authors":"Beatrice De Maria, V. Bari, B. Cairo, F. Gelpi, D. Lucini, M. Pagani, M. Malacarne, A. Catai, Mariana de Oliveira Gois, F. Perego, L. Vecchia, A. Porta","doi":"10.22489/CinC.2022.303","DOIUrl":"https://doi.org/10.22489/CinC.2022.303","url":null,"abstract":"In the last years there is increasing interest in the study of the effects of physical activity on the cardiovascular control of athletes by heart period (HP) and QT interval (QT) variability analysis. However, the relation between HP and QT variability in athletes has been poorly investigated. Therefore, we aimed at estimate transfer function gain (TFG) to typify the relationship between HP and QT variability in athletes. We acquired electrocardiogram in 18 half-marathon runners while supine (REST) and during active standing (STAND) at baseline (B) and at a 10-year follow up (FU). The TFG was computed as the ratio between the modulus of the cross-spectral density between HP and QT divided by the power spectral density of HP in low frequency (LF, 0.04-0.15 Hz, TFGLF) and high frequency (HF, 0.15-0.4 Hz, TFGHF) bands. We found that TFGHF was lower at FU compared to B both at REST and during STAND. TFGLF increased during STAND compared to REST only at FU. The present work supports the use of the linear approach in the frequency domain to typify the cardiac control of athletes. In addition, the findings suggest that a moderate and regular physical activity through the years is beneficial as it favors a decrease of the cardiac sympathetic modulation.","PeriodicalId":117840,"journal":{"name":"2022 Computing in Cardiology (CinC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115662324","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}
Non-invasive fetal ECG (fECG) is a promising technique that could allow low-cost and risk-free diagnosis, and long-term monitoring of fetal cardiac wellbeing. However, the low quality of the fECG extracted from non-invasive abdominal recordings hampers its adoption in clinical practice. In this work, a new algorithm for the recovery of clean and morphologically preserved fECG signals from multi-channel trans-abdominal recordings is presented. The proposed method exploits optimal shrinkage and nonlocal median algorithms, along with a de-shape short-time Fourier transform-based detection, to recover high-quality fECG traces from a morphological perspective, while ensuring very high performance also in terms of fetal QRS detection. On a small dataset, composed of three real 20 min-long four-channel abdominal ECG recordings, a preliminary performance assessment of the proposed fECG extraction method in terms of fetal QRS detection capabilities revealed a median accuracy of 95.8% and F1 score of 97.9%. The obtained results suggest the possibility of successfully applying this approach for an effective non-invasive fECG extraction, deserving further investigations on larger real and synthetic datasets.
{"title":"Extraction Algorithm for Morphologically Preserved Non-Invasive Multi-Channel Fetal ECG","authors":"Giulia Baldazzi, D. Pani, Hau‐Tieng Wu","doi":"10.22489/CinC.2022.373","DOIUrl":"https://doi.org/10.22489/CinC.2022.373","url":null,"abstract":"Non-invasive fetal ECG (fECG) is a promising technique that could allow low-cost and risk-free diagnosis, and long-term monitoring of fetal cardiac wellbeing. However, the low quality of the fECG extracted from non-invasive abdominal recordings hampers its adoption in clinical practice. In this work, a new algorithm for the recovery of clean and morphologically preserved fECG signals from multi-channel trans-abdominal recordings is presented. The proposed method exploits optimal shrinkage and nonlocal median algorithms, along with a de-shape short-time Fourier transform-based detection, to recover high-quality fECG traces from a morphological perspective, while ensuring very high performance also in terms of fetal QRS detection. On a small dataset, composed of three real 20 min-long four-channel abdominal ECG recordings, a preliminary performance assessment of the proposed fECG extraction method in terms of fetal QRS detection capabilities revealed a median accuracy of 95.8% and F1 score of 97.9%. The obtained results suggest the possibility of successfully applying this approach for an effective non-invasive fECG extraction, deserving further investigations on larger real and synthetic datasets.","PeriodicalId":117840,"journal":{"name":"2022 Computing in Cardiology (CinC)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114380864","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}
Daniele Padovano, A. Martínez-Rodrigo, J. M. Pastor, J. J. Rieta, R. Alcaraz
Obstructive sleep apnea (OSA) is a respiratory disorder highly correlated with multiple cardiovascular diseases. In the last two decades, several alternatives have been proposed to palliate the limitations of polysomnography, the current gold standard for OSA diagnosis. Such alternatives were mainly based on the heart rate variability in combination with machine learning (ML) techniques, obtaining promising results. However, the majority of these works used a cross-validation approach for the validation of the proposed methods, and rarely tested them on external sources of newly added data. Hence, some of the most common algorithms found in the state of the art have been evaluated with cross-validation and external validation in this work. The obtained results have raised important concerns on the real performance shown by the typical ML-based OSA detection methods in more realistic scenarios.
{"title":"Hidden Hazards Beneath Cross-Validation Methods in Machine Learning-Based Sleep Apnea Detection","authors":"Daniele Padovano, A. Martínez-Rodrigo, J. M. Pastor, J. J. Rieta, R. Alcaraz","doi":"10.22489/CinC.2022.086","DOIUrl":"https://doi.org/10.22489/CinC.2022.086","url":null,"abstract":"Obstructive sleep apnea (OSA) is a respiratory disorder highly correlated with multiple cardiovascular diseases. In the last two decades, several alternatives have been proposed to palliate the limitations of polysomnography, the current gold standard for OSA diagnosis. Such alternatives were mainly based on the heart rate variability in combination with machine learning (ML) techniques, obtaining promising results. However, the majority of these works used a cross-validation approach for the validation of the proposed methods, and rarely tested them on external sources of newly added data. Hence, some of the most common algorithms found in the state of the art have been evaluated with cross-validation and external validation in this work. The obtained results have raised important concerns on the real performance shown by the typical ML-based OSA detection methods in more realistic scenarios.","PeriodicalId":117840,"journal":{"name":"2022 Computing in Cardiology (CinC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114662524","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}
Q. B. Soares, R. Monteiro, F. Jatene, M. A. Gutierrez
Continuous rhythm monitoring using wearable devices is a potential tool for early identification of atrial fibril-lation (AF), the most frequent cardiac arrhythmia (with 0,51% worldwide prevalence, increasing with time), and is also a tool for remote monitoring patients after cardiac surgery. However, AF detection directly through wearable devices is limited by the computational complexity of the classifier model. In this work we propose a lightweight AF classifier model based on the VGG-11 architecture (Lite VGG-11), focusing on reducing the number of parameters and nu-merical operations. Using a low number of filters, depth-wise separable convolution, and global pooling, this model has only 20,454 parameters and needs 6.9 MFLOP to make an inference for an input of 10 seconds of the ECG leads I and II, sampled at 200 Hz. To test its effectiveness for AF detection we used the PhysioNet/CinC Challenge 2021 public dataset, stratifying the classes into sinus rhythm, AF, and other rhythms. After 10 Monte Carlo cross-validation splits, with 24,260 unbalanced samples for training and 1,536 balanced samples for validation and testing, the observed met-rics (mean±standard deviation) were: Se 94.1±0.1%; Sp 91.9±0.8%; F1-Score 89.50.7±%; and AUC 96.1±0.6%.
{"title":"A Lightweight Unidimensional Deep Learning Model for Atrial Fibrillation Detection","authors":"Q. B. Soares, R. Monteiro, F. Jatene, M. A. Gutierrez","doi":"10.22489/CinC.2022.220","DOIUrl":"https://doi.org/10.22489/CinC.2022.220","url":null,"abstract":"Continuous rhythm monitoring using wearable devices is a potential tool for early identification of atrial fibril-lation (AF), the most frequent cardiac arrhythmia (with 0,51% worldwide prevalence, increasing with time), and is also a tool for remote monitoring patients after cardiac surgery. However, AF detection directly through wearable devices is limited by the computational complexity of the classifier model. In this work we propose a lightweight AF classifier model based on the VGG-11 architecture (Lite VGG-11), focusing on reducing the number of parameters and nu-merical operations. Using a low number of filters, depth-wise separable convolution, and global pooling, this model has only 20,454 parameters and needs 6.9 MFLOP to make an inference for an input of 10 seconds of the ECG leads I and II, sampled at 200 Hz. To test its effectiveness for AF detection we used the PhysioNet/CinC Challenge 2021 public dataset, stratifying the classes into sinus rhythm, AF, and other rhythms. After 10 Monte Carlo cross-validation splits, with 24,260 unbalanced samples for training and 1,536 balanced samples for validation and testing, the observed met-rics (mean±standard deviation) were: Se 94.1±0.1%; Sp 91.9±0.8%; F1-Score 89.50.7±%; and AUC 96.1±0.6%.","PeriodicalId":117840,"journal":{"name":"2022 Computing in Cardiology (CinC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125689671","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}
Hibba Yousef, A. Khandoker, Samuel F. Feng, M. Tarvainen, H. F. Jelinek
Oxidative stress (OS) has been shown to have a negative effect on the autonomic nervous system (ANS) and on ANS modulation of heart rate. Mitochondrial ATP production is the main source of reactive oxygen species (ROS) and hence the regulation of ROS becomes an important issue in maintaining optimal ANS functionality. Humanin (HN), a mitochondrial-derived peptide, plays an important role in lowering OS. Sympathovagal balance was assessed in 124 healthy participants through heart rate variability (HRV) analysis and compared across changes in HN concentrations divided into quintiles, with values of HN ranging from 64.6 to 343.2 pg/mL. Significant differences included various frequency domain and nonlinear HRV parameters, particularly between first and fourth HN quintiles with p values < 0.001 for recurrence plot analysis (RPA), detrended fluctuation analysis (DFA) al and Poincaré plot ratio SD1/SD2. The results revealed non-monotonic relationships between measures of HRV and HN concentration. A mitohormetic type of relationship was observed with HRV features increasing and then decreasing with increasing HN concentration. These results are consistent with previous findings of the importance of HN levels in regulating OS and extend these by revealing a concomitant effect on the modulation of cardiac rhythm by the ANS.
{"title":"Heart Rate Variability Analysis Reveals a Non-monotonic Relationship Between Humanin Concentration and Cardiac Autonomic Regulation","authors":"Hibba Yousef, A. Khandoker, Samuel F. Feng, M. Tarvainen, H. F. Jelinek","doi":"10.22489/CinC.2022.223","DOIUrl":"https://doi.org/10.22489/CinC.2022.223","url":null,"abstract":"Oxidative stress (OS) has been shown to have a negative effect on the autonomic nervous system (ANS) and on ANS modulation of heart rate. Mitochondrial ATP production is the main source of reactive oxygen species (ROS) and hence the regulation of ROS becomes an important issue in maintaining optimal ANS functionality. Humanin (HN), a mitochondrial-derived peptide, plays an important role in lowering OS. Sympathovagal balance was assessed in 124 healthy participants through heart rate variability (HRV) analysis and compared across changes in HN concentrations divided into quintiles, with values of HN ranging from 64.6 to 343.2 pg/mL. Significant differences included various frequency domain and nonlinear HRV parameters, particularly between first and fourth HN quintiles with p values < 0.001 for recurrence plot analysis (RPA), detrended fluctuation analysis (DFA) al and Poincaré plot ratio SD1/SD2. The results revealed non-monotonic relationships between measures of HRV and HN concentration. A mitohormetic type of relationship was observed with HRV features increasing and then decreasing with increasing HN concentration. These results are consistent with previous findings of the importance of HN levels in regulating OS and extend these by revealing a concomitant effect on the modulation of cardiac rhythm by the ANS.","PeriodicalId":117840,"journal":{"name":"2022 Computing in Cardiology (CinC)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127087271","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}
J. Siles, J. Salinet, C. Crowley, F. Fenton, N. Bhatia, Shahriar Iravanian, I. Uzelac
This study investigates the effects of radiofrequency ablation $(RFA)$ - created lesions on an explanted human heart in wedge preparation by simultaneous endo and sub-endo optical mapping. The heart in Langendorff perfusion was ablated under 40 W. The ventricle was stained with $Vm$ sensitive dye Di-4-ANBDQPQ and two excitation light bands of different penetration depths were used $(red= {it 660} nm$, green $=525nm$) to perform a conduction velocity $(CV)$ difference analysis for identification of $CV$ alternans. The relative change in fluorescence $(Delta F/F)$ traces were analyzed before and after ablation. Local activation time $(LAT)$ was determined by the 50% approach. Local $CV$ was obtained using the circle method, and $RFA$ created lesions were characterized by examining the $CV$ alternans correlated with transmural heterogeneities. The presence of $CV$ alternans results from reduced excitability in a non-homogeneous lesion consisting of excitable and non-excitable cells. The absence of $CV$ alternans in optical mapping with green light and their presence with deep-red light illustrates incomplete ablation across the ventricular wall or non-homogeneous ablation in the mid-myocardial layer. The presence of an intramural scar impairs the efficacy of the $RFA$ procedure, suggesting $a$ need for alternative ablations strategies.
{"title":"Cell Unexcitability and Electrotonic Coupling Phenomenon Analysis of Ablation-Created Lesions: A Study Case with Ablated Explanted Human Heart","authors":"J. Siles, J. Salinet, C. Crowley, F. Fenton, N. Bhatia, Shahriar Iravanian, I. Uzelac","doi":"10.22489/CinC.2022.405","DOIUrl":"https://doi.org/10.22489/CinC.2022.405","url":null,"abstract":"This study investigates the effects of radiofrequency ablation <tex>$(RFA)$</tex> - created lesions on an explanted human heart in wedge preparation by simultaneous endo and sub-endo optical mapping. The heart in Langendorff perfusion was ablated under 40 W. The ventricle was stained with <tex>$Vm$</tex> sensitive dye Di-4-ANBDQPQ and two excitation light bands of different penetration depths were used <tex>$(red= {it 660} nm$</tex>, green <tex>$=525nm$</tex>) to perform a conduction velocity <tex>$(CV)$</tex> difference analysis for identification of <tex>$CV$</tex> alternans. The relative change in fluorescence <tex>$(Delta F/F)$</tex> traces were analyzed before and after ablation. Local activation time <tex>$(LAT)$</tex> was determined by the 50% approach. Local <tex>$CV$</tex> was obtained using the circle method, and <tex>$RFA$</tex> created lesions were characterized by examining the <tex>$CV$</tex> alternans correlated with transmural heterogeneities. The presence of <tex>$CV$</tex> alternans results from reduced excitability in a non-homogeneous lesion consisting of excitable and non-excitable cells. The absence of <tex>$CV$</tex> alternans in optical mapping with green light and their presence with deep-red light illustrates incomplete ablation across the ventricular wall or non-homogeneous ablation in the mid-myocardial layer. The presence of an intramural scar impairs the efficacy of the <tex>$RFA$</tex> procedure, suggesting <tex>$a$</tex> need for alternative ablations strategies.","PeriodicalId":117840,"journal":{"name":"2022 Computing in Cardiology (CinC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125127290","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：