{"title":"Early Prediction of Sepsis From Clinical Data Using Single Light-GBM Model","authors":"S. Chami, K. Tavakolian","doi":"10.23919/CinC49843.2019.9005718","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005718","url":null,"abstract":"Sepsis is a severe medical condition caused by body’s extreme response to an infection leading to tissue damage, organ failure, and even death. The emergence of advanced technologies such as Artificial Intelligence and machine learning, allowed faster exploration of advanced way to recognize sepsis cases. In this paper, we present two main approaches that have been tested using the clinical data. The first method is the combination of survival analysis and neural networks, and the second one is based on booting trees. Our team participated under the name of BERCLAB UND. The proposed model obtained 0.172 on holdout set and 0.005 on the full test set with ranking of 69.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"1 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79529425","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}
K. Rjoob, R. Bond, D. Finlay, V. Mcgilligan, Stephen Leslie, Aleeha Iftikhar, D. Guldenring, A. Rababah, C. Knoery, A. Peace
{"title":"Machine Learning Improves the Detection of Misplaced V1 and V2 Electrodes During 12-Lead Electrocardiogram Acquisition","authors":"K. Rjoob, R. Bond, D. Finlay, V. Mcgilligan, Stephen Leslie, Aleeha Iftikhar, D. Guldenring, A. Rababah, C. Knoery, A. Peace","doi":"10.23919/CinC49843.2019.9005828","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005828","url":null,"abstract":"Electrode misplacement during 12-lead Electrocardiogram (ECG) acquisition can cause false ECG diagnosis and subsequent incorrect clinical treatment. A common misplacement error is the superior placement of V1 and V2 electrodes. The aim of the current research was to detect lead V1 and V2 misplacement using machine learning to enhance ECG data quality to improve clinical decision making. In this particular study, we reasonably assume that V1 and V2 are concurrently superiorly misplaced together. ECGs for 450 patients were extracted from body surface potential maps. Sixteen features were extracted including: morphological, statistical and time-frequency features. Two feature selection approaches (filter method and wrapper method) were applied to find an optimal set of features that provide a high accuracy. To ensure accuracy, six classifiers were applied including: fine tree, coarse tree, bagged tree, Linear Support Vector Machine (LSVM), Quadratic Support Vector Machine (QSVM) and logistic regression. The accuracy of V1 and V2 misplacement detection was 94.3% in the first ICS, 92.7% in the second ICS and 70% in third ICS respectively. Bagged tree was the best classifier in the first, second and third ICS to detect V1 and V2 misplacement.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"39 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86159864","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}
Andy C. Y. Lo, Jieyun Bai, P. Gladding, Jichao Zhao
{"title":"The Ionic Mechanisms of Triggered Atrial Activity Under a TBX5-driven Regulatory Network","authors":"Andy C. Y. Lo, Jieyun Bai, P. Gladding, Jichao Zhao","doi":"10.23919/CinC49843.2019.9005817","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005817","url":null,"abstract":"Atrial fibrillation (AF) is the most prevalent arrhythmia in clinical practice, yet the pathophysiology by which genetic factors can increase the risk of AF is not well understood. Recently, a multitiered transcriptional network, driven by a T-box transcription factor gene TBX5 and a paired-like homeodomain transcription factor 2 gene PITX2 was discovered. This transcriptional network regulates gene expressions associated with ion channels in a complex fashion, and through mice knockout studies, it was found that reducing the expression of TBX5 altered the gene expressions of certain types of ion channels and generated abnormal depolarizations in the form of early afterdepolarizations, delayed afterdepolarizations, or spontaneous triggered action potentials. To systematically investigate the ionic mechanisms by which impaired TBX5 can lead to AF, we integrated the calcium dynamics of the Grandi et al. model into the Courtemanche-Ramirez-Nattel model. Our model reproduced all forms of abnormal depolarizations observed in TBX5 knockout atrial myocytes. Furthermore, we discovered that the remodeling of the inward-rectifier potassium channel (IK1) and the L- type calcium channel (ICaL), due to impaired TBX5, causes an elevation in the concentration of calcium ([Ca2+]), which reactivates the sodium-calcium exchanger (INaCa) and ICaL to generate abnormal depolarizations.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"1 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88247721","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. Tate, E. V. Dam, W. Good, J. Bergquist, P. V. Dam, R. Macleod
{"title":"A Unified Pipeline for ECG Imaging Testing","authors":"J. Tate, E. V. Dam, W. Good, J. Bergquist, P. V. Dam, R. Macleod","doi":"10.23919/CinC49843.2019.9005780","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005780","url":null,"abstract":"The Consortium for ECG Imaging (CEI) has formed several collaborative projects to evaluate and improve technical aspects of Electrocardiographic Imaging (ECGI), but these efforts are not yet implemented into an integrated software framework. We developed a framework to unify the multiple techniques and stages of ECGI into one pipeline. This framework merges existing open source packages: SCIRun, a problem solving environment; the Forward/Inverse toolkit, a series of SCIRun modules for ECGI; and PFEIFER, a cardiac signal pre-processing tool. The Unified ECGI Toolkit (UETK), combined with the EDGAR dataset, allows users to test and validate a vast array of parameters within each stage of the ECGI pipeline. We expect that this unified tool will help introduce new researchers to ECGI, facilitate interaction between the various groups working on ECGI, and establish a common approach for researchers to test and validate their ECGI techniques.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"14 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88261646","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}
Hassaan A. Bukhari, Flavio Palmieri, D. Ferreira, M. Potse, J. Ramírez, P. Laguna, C. Sánchez, E. Pueyo
{"title":"Transmural Ventricular Heterogeneities Play a Major Role in Determining T-Wave Morphology at Different Extracellular Potassium Levels","authors":"Hassaan A. Bukhari, Flavio Palmieri, D. Ferreira, M. Potse, J. Ramírez, P. Laguna, C. Sánchez, E. Pueyo","doi":"10.23919/CinC49843.2019.9005944","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005944","url":null,"abstract":"End-stage renal disease (ESRD) affects more than 10% of the world population. ESRD patients present impaired potassium homeostasis, which increases the risk for ventricular arrhythmias and sudden cardiac death. Noninvasive estimation of serum potassium, [K+], before the patient experiences serious consequences is of major importance. In this study, we investigated the relationship of [K+] with three T-wave morphological descriptors: the T-wave width (Tw), slope-to-amplitude ratio (TSA) and temporal morphological variability (dw) from ECGs of 12 ESRD patients undergoing hemodialysis and from simulated ECGs. Spearman’s correlation coefficients between the descriptors Tw, TSA and dw and [K+] were –0.5, 0. 8 and 0.65, respectively. These associations were, however, highly patient-dependent. The high inter-individual variability in T-wave morphology, particularly observed at high [K+], was reproduced in the simulations and could be explained by differences in transmural heterogeneities, with 10% variations in the proportion of midmyocardial cells leading to changes larger than 15% in T-wave morphology. In conclusion, T-wave morphological descriptors have the potential to be used as predictors of [K+] in ESRD patients, but their associated inter-individual variability should be taken into account, especially under hyperkalemic conditions.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"29 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88276127","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":"Evaluating the Effects of Traditional Persian Music on Nonlinear Parameters of HRV","authors":"Bahareh Khodabakhshian, S. Moharreri, S. Parvaneh","doi":"10.23919/CinC49843.2019.9005806","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005806","url":null,"abstract":"Music has the power to evoke particular emotional states. In this research, the impact of three types of traditional Persian music (happy, peaceful, and sad) on nonlinear parameters for heart rate variability (HRV) analysis is studied. After extracting RR intervals from ECG, the nonlinear parameters were obtained. The parameters include normal descriptors of Poincare plot (SD1 and SD2), Global Occurrence Matrix (GOM), and Co-occurrence Matrix (COM) parameters which demonstrate the dynamic in the Poincare plot. The extracted features in three groups of music stimuli were compared with the controls and then k-nearest neighbor classifier used to distinguish different emotions induced by the different music. The results show that the GOM and COM features were significantly different between different emotions induced by music stimuli. Promising results on emotion classification (accuracy of 90%) in response to music stimuli highlight the power of nonlinear analysis of HRV in emotion assessment application.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"48 9 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77295690","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}
Alejandro Costoya-Sánchez, A. Climent, I. Hernández-Romero, A. Liberos, F. Fernández‐Avilés, S. Narayan, F. Atienza, M. Guillem, M. Rodrigo
{"title":"Temporal Stability of Dominant Frequency as Predictor of Atrial Fibrillation Recurrence","authors":"Alejandro Costoya-Sánchez, A. Climent, I. Hernández-Romero, A. Liberos, F. Fernández‐Avilés, S. Narayan, F. Atienza, M. Guillem, M. Rodrigo","doi":"10.23919/CinC49843.2019.9005772","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005772","url":null,"abstract":"Catheter ablation is one of the main therapies for restoring sinus rhythm in patients with atrial fibrillation (AF), yet AF termination ratios are far from satisfactory. The goal of this work is to study if temporal stability of dominant frequencies (DFs) of electrograms (EGMs) can be used as predictor of AF recurrence.EGMs were recorded from 29 AF patients using 64-pole basket catheters during the ablation procedure. DFs before ablation were obtained for 4-second overlapping fragments of EGM recordings with a 0.4 s shift, and their temporal stability was evaluated for short-term (between 8 and 12 s) and long-term time intervals (>5 min). Patients were classified as AF (N=15) if sinus rhythm was not maintained in a 12-month post-ablation follow-up, and AF free otherwise (N=14).Significant differences were found in the short-term analysis between AF free and AF patients for the difference between the mode value in DFs (p=0.045), as well as for the long-term analysis for the normalized average between DFs (p=0.028) and the average between DFs (p=0.043). More stable values were found for AF free patients for all statistically significant metrics.Short- and long-term temporal stability of DF values of EGM signals were found to be associated with the 12-month success rate of ablative therapies of AF patients.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"88 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91476731","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":"Maximizing the Reliability of a Full-Automatic ECG-Waveforms Delineating Algorithm Using Extensive ECG Databank","authors":"A. Khawaja","doi":"10.23919/CinC49843.2019.9005577","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005577","url":null,"abstract":"Due to the significance of ECG delineation and measurements including QT measurement for drug safety, the objective of this work is to compare the results of manual annotated QT and RR interval measurements of a huge databank with the results of the fully-automated algorithm presented in [3] for validation purposes not only in clinical studies and cardiac safety, but also in all kind of cardiac applications. The differences between the results of the algorithm and the golden manual-annotated reference values are very low. This gives a strong indicator for the reliability of the full-automated delineation program.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"6 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88904064","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 Model of Anatomically Opposed Ischaemia: Revisited","authors":"P. Johnston","doi":"10.23919/CinC49843.2019.9005463","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005463","url":null,"abstract":"This study aims to gain further understanding of anatomically opposed ischaemia, or \"ischaemic ST-segment counterpoise\", by simulating body surface potential distributions resulting from two regions of partial thikcness ischaemia in the left ventricle during the ST-segment.The finite volume method was used to solve the passive bidomain equation in a torso with an idealised model of the heart. Regions of ischaemia of varying size were placed in various positions in the anterior and posterior regions of the ventricular wall.Simulations show that the sources associated with the anterior ischaemic region dominated the body surface potential distribution, irrespective of the relative sizes of the two ischaemic regions. However, further modelling is required to establish a theoretical basis to understand ischaemic ST-segment counterpoise.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"33 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87128838","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}
Y. S. Dogrusoz, L. Bear, J. Bergquist, Rémi Dubois, Wilson Good, Robert S. MacLeod, A. Rababah, J. Stoks
{"title":"Effects of Interpolation on the Inverse Problem of Electrocardiography","authors":"Y. S. Dogrusoz, L. Bear, J. Bergquist, Rémi Dubois, Wilson Good, Robert S. MacLeod, A. Rababah, J. Stoks","doi":"10.23919/CinC49843.2019.9005869","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005869","url":null,"abstract":"Electrocardiographic Imaging (ECGI) aims to reconstruct electrograms from the body surface potential measurements. Bad leads are usually excluded from the inverse problem solution. Alternatively, interpolation can be applied. This study explores how sensitive ECGI is to different bad-lead configurations and interpolation methods. Experimental data from a Langendorff-perfused pig heart suspended in a human-shaped torso-tank was used. Six different bad lead cases were designed based on clinical experience. Inverse problem was solved by applying Tikhonov regularization i) using the complete data, ii) bad-leads-removed data, and iii) interpolated data, with 5 different methods. Our results showed that ECGI accuracy of an interpolation method highly depends on the location of the bad leads. If they are in the high-potential-gradient regions of the torso, a highly accurate interpolation method is needed to achieve an ECGI accuracy close to using complete data. If the BSP reconstruction of the interpolation method is poor in these regions, the reconstructed electro-grams also have lower accuracy, suggesting that bad leads should be removed instead of interpolated. The inverse-forward method was found to be the best among all interpolation methods applied in this study in terms of both missing BSP lead reconstruction and ECGI accuracy, even for the bad leads located over the chest.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"33 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87258503","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}