Hewon Jung, Jacob P. Kimball, Timothy Receveur, Eric Agdeppa, O. Inan
{"title":"Quantification of Posture-Induced Changes in Bed-Based Ballistocardiogram","authors":"Hewon Jung, Jacob P. Kimball, Timothy Receveur, Eric Agdeppa, O. Inan","doi":"10.22489/CinC.2020.060","DOIUrl":"https://doi.org/10.22489/CinC.2020.060","url":null,"abstract":"The ballistocardiogram (BCG), a measurement of cardiogenic whole body movements, is a technique that enables non-invasive cardiovascular monitoring. A main challenge of the BCG signal is that its morphology and amplitude are sensitive to the posture of the subject during the recording period. This work elucidates effects of posture on bed-based BCG recordings by (1) creating templates for standing BCG signals obtained from subjects in a prior study, and (2) quantifying the distance between these templates and BCG waveforms obtained in different body postures on the bed for a new set of subjects. The signal quality index (SQI), defined in previous work and corresponding to the inverse of the distance to the templates, was the highest for the supine posture and the lowest for the lateral postures. A previously-reported system identification approach to correct for distortions in the lateral, prone, and seated postures was further validated. The system identification algorithm significantly improved the signal quality and correlation to the reference morphology - the supine and standing BCG. This work has implications for robust signal processing that allows for accurate physiological interpretation of the BCG obtained in a variety of postures from a subject in bed.","PeriodicalId":407282,"journal":{"name":"2020 Computing in Cardiology","volume":"77 52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131121117","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}
{"title":"A Novel Convolutional Neural Network for Arrhythmia Detection From 12-lead Electrocardiograms","authors":"Zhengling He, Pengfei Zhang, Lirui Xu, Zhongrui Bai, Hao Zhang, Weisong Li, Pan Xia, Xianxiang Chen","doi":"10.22489/CinC.2020.196","DOIUrl":"https://doi.org/10.22489/CinC.2020.196","url":null,"abstract":"Electrocardiogram (ECG) is a widely medical tool used in the clinical diagnosis of arrhythmia, numerous algorithms based on deep learning have been proposed to achieve automatic arrhythmia detection. In PhysioNetlComputing in Cardiology Challenge 2020, inspired by the deep residual learning and attention mechanism, we proposed a novel neural network to accomplish this classification task. The backbone of the network is a carefully designed 2-D convolutional neural network (CNN) with residual connection and attention mechanism, and it can adapt to multi-lead ECG signals as input. The first 10 seconds of records from all leads are extracted and preprocessed as input for end-to-end training, and the prediction probabilities of 27 categories are output. The proposed algorithm was firstly verified and adjusted via 5-fold cross-validation on officially published datasets from 4 multiple sources. Finally, our team (MetaHeart) achieved a challenge validation score of 0.616 and full test score of 0.370, but were not ranked due to omissions in the submission.","PeriodicalId":407282,"journal":{"name":"2020 Computing in Cardiology","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121805348","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}
{"title":"Comparison of Two Equivalent Dipole Layer Based Inverse Electrocardiography Techniques for the Non-Invasive Estimation of His-Purkinje Mediated Ventricular Activation","authors":"M. Boonstra, R. Roudijk, P. Loh, P. V. Dam","doi":"10.22489/CinC.2020.354","DOIUrl":"https://doi.org/10.22489/CinC.2020.354","url":null,"abstract":"Non-invasive estimation of the cardiac activation sequence through inverse electrocardiography (iECG) based on the equivalent double layer becomes increasingly difficult for multiple activation waves through the myocardium. Earlier studies simulated the effect of the His-Purkinje system through a multi-focal search, which does not completely take into account the effect of multiple near simultaneous activation waves initiated by the His-Purkinje system. In this study, the iECG initial estimation of the cardiac activation sequence was modified to include electro-anatomical structures associated with the His-Purkinje system to provide a physiologically robust initial estimate. The performance of two iECG techniques for the estimation of different His-Purkinje mediated ventricular activation sequences were tested, i. e. normal activation and left and right bundle branch block activation.","PeriodicalId":407282,"journal":{"name":"2020 Computing in Cardiology","volume":"127 5-6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120909615","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}
Zheheng Jiang, T. Almeida, F. Schlindwein, G. Ng, Huiyu Zhou, Xin Li
{"title":"Diagnostic of Multiple Cardiac Disorders from 12-lead ECGs Using Graph Convolutional Network Based Multi-label Classification","authors":"Zheheng Jiang, T. Almeida, F. Schlindwein, G. Ng, Huiyu Zhou, Xin Li","doi":"10.22489/CinC.2020.135","DOIUrl":"https://doi.org/10.22489/CinC.2020.135","url":null,"abstract":"Automated detection and classification of clinical electrocardiogram (ECG) play a critical role in the analysis of cardiac disorders. Deep learning is effective for automated feature extraction and has shown promising results in ECG classification. Most of these methods, however, assume that multiple cardiac disorders are mutually exclusive. In this work, we have created and trained a novel deep learning architecture for addressing the multi-label classification of 12-lead ECGs. It contains an ECG representation work for extracting features from raw ECG recordings and a Graph Convolutional Network (GCN)for modelling and capturing label dependencies. In the Phy-sioNet/Computing in Cardiology Challenge 2020 [1], our team, Leicester-Fox, reached a challenge validation score of 0.395, and full test score of −0.012, placing us 34 out of 41 in the official ranking.","PeriodicalId":407282,"journal":{"name":"2020 Computing in Cardiology","volume":"04 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127195324","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}
T. Gerach, S. Schuler, E. Kovacheva, O. Dössel, A. Loewe
{"title":"Consequences of Using an Orthotropic Stress Tensor for Left Ventricular Systole","authors":"T. Gerach, S. Schuler, E. Kovacheva, O. Dössel, A. Loewe","doi":"10.22489/CinC.2020.246","DOIUrl":"https://doi.org/10.22489/CinC.2020.246","url":null,"abstract":"A variety of biophysical and phenomenological active tension models has been proposed during the last decade that show physiological behaviour on a cellular level. However, applying these models in a whole heart finite element simulation framework yields either unphysiological values of stress and strain or an insufficient deformation pattern compared to magnetic resonance imaging data. In this study, we evaluate how introducing an orthotropic active stress tensor affects the deformation pattern by conducting a sensitivity analysis regarding the active tension at resting length Tref and three orthotropic activation parameters Kss,Ksn and Knn). Deformation of left ventricular contraction is evaluated on a truncated ellipsoid using four features: wall thickening (WT), longitudinal shortening (LS), torsion (Θ) and ejection fraction (EF). We show that EF, WT and LS are positively correlated with the parameters Tref and Knn while Kss reduces all of the four observed features. Introducing shear stress to the model has little to no effect on EF, WT and LS, although it reduces torsion by up to 3°. We find that added stress in the normal direction can support healthy deformation patterns. However, the twisting motion, which has been shown to be important for cardiac function, reduces by up to 20°.","PeriodicalId":407282,"journal":{"name":"2020 Computing in Cardiology","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125763233","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}
Janna Ruisch, M. Boonstra, R. Roudijk, P. V. Dam, C. Slump, P. Loh
{"title":"Disease-Specific Electrocardiographic Lead Positioning for Early Detection of Arrhythmogenic Right Ventricular Cardiomyopathy","authors":"Janna Ruisch, M. Boonstra, R. Roudijk, P. V. Dam, C. Slump, P. Loh","doi":"10.22489/CinC.2020.334","DOIUrl":"https://doi.org/10.22489/CinC.2020.334","url":null,"abstract":"Arrhythmogenic right ventricular cardiomyopathy (ARVC) is characterized by replacement of cardiomyocytes by fibrofatty tissue which can lead to ventricular arrhythmias, heart failure or sudden cardiac death. Genetic defects in desmosomal proteins, as plakophilin-2 (PKP2), are known to contribute to disease development. Current electrocardiographic (ECG) criteria for ARVC diagnosis only focus on right precordial leads, but sensitivity of current depolarization criteria is limited. This study aimed to identify additional depolarization criteria with most optimal lead configurations for early detection of ARVC in PKP2 pathogenic mutation carriers. In PKP2-positive ARVC patients (n=7), PKP2 pathogenic variant carriers (n=16) and control subjects without structural heart disease (n=9), 67-lead body surface potential maps (BSPM) were obtained. Terminal QRS-integrals were determined and quantitatively compared to controls using departure mapping. Significantly different terminal QRS-integrals were identified in lead 34 (conventional V3), 40 and 41 (conventional V4). To conclude, a clear distinction between ARVC patients, asymptomatic mutation carriers and healthy controls was observed.","PeriodicalId":407282,"journal":{"name":"2020 Computing in Cardiology","volume":"GE-20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126565735","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}
{"title":"Unobtrusive Monitoring of ECG and EEG During Mild Stress Stimuli","authors":"V. C. Zuccalà, R. Favilla, G. Coppini","doi":"10.22489/CinC.2020.049","DOIUrl":"https://doi.org/10.22489/CinC.2020.049","url":null,"abstract":"This study is part of a research project aiming to build a model for quantifying an individual wellness status through unobtrusive measurements of psychophysical parameters and self-reported data. In particular, we focus on the evaluation of the individual response to mild stress stimuli. The experimental setup included: EG05000 Medlab Five Channel Module, Gigabit Ethernet camera, BioHarness 3 Zephyr chest belt, and Muse 2 Headband. Experimental results show increased heart rate and respiration rate, and changes of the brain activity in the stress condition. This is consistent with a “fight or flight” response in accordance with literature. Therefore, the methodology applied in this study can be used to monitor the individual wellness status in conditions of mild stress stimuli.","PeriodicalId":407282,"journal":{"name":"2020 Computing in Cardiology","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126236843","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}
B. D. Maria, V. Bari, B. Cairo, A. Catai, A. Takahashi, L. Carnevali, A. Sgoifo, F. Perego, L. Vecchia, A. Porta
{"title":"QT-RR Relation Is Different in Humans and Rats","authors":"B. D. Maria, V. Bari, B. Cairo, A. Catai, A. Takahashi, L. Carnevali, A. Sgoifo, F. Perego, L. Vecchia, A. Porta","doi":"10.22489/CinC.2020.068","DOIUrl":"https://doi.org/10.22489/CinC.2020.068","url":null,"abstract":"The QT interval (QT) variability has been recently computed to infer cardiac control of rats. It has been suggested that QT variability markers in rats have the same physiological meaning as in humans. However, some evidences indicate a different dependence of QT on the previous RR interval (RR). Thus, the aim of this study was to compare the relation of the QT to the preceding RR in humans and in rats. Electrocardiogram was recorded in supine position (REST) and during tilt test (T90) in 23 healthy subjects and in 9 Wistar (WI) and 14 wild-type Groningen (WT) rats during the dark period. Pearson product moment correlation coefficient r computed between RR and QT was calculated for each subject or animal within each experimental condition. In humans we found that r was positive and decreased from REST to T90. Conversely, r was negative in rats and did not differ between WI and WT. The r absolute value was significantly higher in humans than in rats. Our results showed that trends toward longer RRs lead to longer QTs in humans but shorter QTs in rats and that the strength of the QT-RR association is lower in rats. We conclude that attention should be paid when using the rat model in translational studies assessing the QT-RR relation.","PeriodicalId":407282,"journal":{"name":"2020 Computing in Cardiology","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134605156","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}
{"title":"A Method to Detect Pauses for Ventilation During Cardiopulmonary Resuscitation Using the Thoracic Impedance","authors":"Enrique Rueda, E. Aramendi, U. Irusta, A. Idris","doi":"10.22489/CinC.2020.313","DOIUrl":"https://doi.org/10.22489/CinC.2020.313","url":null,"abstract":"Cardiac arrest is the main cause of death in developed countries. A good quality cardiopulmonary resuscitation (CPR) is key for the survival of the patient in out-of-hospital cardiac arrest (OHCA), including chest compressions (CCs) and ventilations. Ventilations have been proven to have an important impact in the outcome of the patient, and detecting the CC pauses where ventilations were provided is the aim of this study. An algorithm that automatically detects pauses between sequences of CCs using machine learning techniques is proposed. For this study a set of 102 defibrillator files from OHCA patients that include the thoracic impedance recorded through the defibrillation pads was used. The work has been split into 2 main blocks: a random forest (RF) classifier that classifies 1-s windows as CC/no-CC and an algorithm that sets the beginning and the end of each detected pause. The RF classifier was validated using 10 fold cross-validation method, obtaining a median sensitivity (Se), specificity (Sp) and positive predictive value (PPV) of 95.4/97. 9/94.4 % respectively, for window classification. The pause detector returned median Se/PPV values of 90.0/91.3 % with a median pause delimitation error of 0.04 s and a duration error of 0.04 s.","PeriodicalId":407282,"journal":{"name":"2020 Computing in Cardiology","volume":"478 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132181259","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}
Maximiliano Mollura, E. M. Polo, Li-wei H. Lehman, R. Barbieri
{"title":"Assessment of Heart Rate Variability Derived From Blood Pressure Pulse Recordings in Intensive Care Unit Patients","authors":"Maximiliano Mollura, E. M. Polo, Li-wei H. Lehman, R. Barbieri","doi":"10.22489/CinC.2020.423","DOIUrl":"https://doi.org/10.22489/CinC.2020.423","url":null,"abstract":"The role of Pulse Rate estimated from blood pressure pulse when used as a surrogate for Heart Rate Variability (HRV) studies has been addressed under different conditions in healthy subjects. However, there is a lack of validation in studies involving patients admitted in the Intensive Care Unit (ICU). Therefore, our study aims at validating six different possible surrogates for the ECG-derived tachogram, estimated from the time interval series between successive onset (O), systolic (S) and diastolic (D) fiducial points extracted from arterial blood pressure (ABP) and photoplethysmogram (PPG) waveforms. The validation is performed by looking at the ability of such surrogates in providing comparable estimates of the most common HRV measures. Results show a high agreement between the ECG-derived and the ABP/PPG-derived series, with small biases. Results from sub-populations of patients that showed increases (and decreases) in such measures show a good ability of these surrogates in tracking autonomic changes. In addition, differently from PPGO and PPGS, ventilated and sedated subjects did not show differences in estimating HF power from PPGD, indicating diastolic time intervals as less affected by such procedures. In conclusion, HRV measures estimated from ABP or PPG can be reasonably used also in studies on ICU patients whenever ECG recordings are not available.","PeriodicalId":407282,"journal":{"name":"2020 Computing in Cardiology","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122653275","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}