{"title":"Calcium-Activated Potassium Channel Inhibition in Autonomically Stimulated Human Atrial Myocytes.","authors":"Chiara Celotto, C. Sánchez, P. Laguna, E. Pueyo","doi":"10.22489/cinc.2019.334","DOIUrl":"https://doi.org/10.22489/cinc.2019.334","url":null,"abstract":"","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77910986","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}
As part of the PhysioNet/Computing in Cardiology Challenge 2019, we propose a neural network called AECNet to early detect sepsis based on physiological data. AEC-Net consists of two main components: 1) an Auto Encoder for dimension reduction and feature extraction, and 2) a Fully Connected Neural Network (FCNN) taking the extracted features by the Auto Encoder as the input and generating prediction of sepsis as output. The losses of both the Auto Encoder and FCNN are minimized concurrently. This concurrent optimization helps AEC-Net to have a better generalization and the extracted features by Auto Encoder to be more relevant to the classification problem. Finally, we propose an ensemble method of AECNet, Random Forest and Gradient Boosting Decision Trees to achieve a better prediction. We train our proposed models using data from 40336 patients with 40 physiological features ranging from 8 to 336 hours. Our team Infolab USC evaluated Ensemble with the hidden full test set of the Physionet Challenge 2019, and achieved a Utility score of 0.284 and 24 place in the challenge.
{"title":"Representation Learning for Early Sepsis Prediction","authors":"T. Luan, N. Manh, Shahabi Cyrus","doi":"10.22489/cinc.2019.021","DOIUrl":"https://doi.org/10.22489/cinc.2019.021","url":null,"abstract":"As part of the PhysioNet/Computing in Cardiology Challenge 2019, we propose a neural network called AECNet to early detect sepsis based on physiological data. AEC-Net consists of two main components: 1) an Auto Encoder for dimension reduction and feature extraction, and 2) a Fully Connected Neural Network (FCNN) taking the extracted features by the Auto Encoder as the input and generating prediction of sepsis as output. The losses of both the Auto Encoder and FCNN are minimized concurrently. This concurrent optimization helps AEC-Net to have a better generalization and the extracted features by Auto Encoder to be more relevant to the classification problem. Finally, we propose an ensemble method of AECNet, Random Forest and Gradient Boosting Decision Trees to achieve a better prediction. We train our proposed models using data from 40336 patients with 40 physiological features ranging from 8 to 336 hours. Our team Infolab USC evaluated Ensemble with the hidden full test set of the Physionet Challenge 2019, and achieved a Utility score of 0.284 and 24 place in the challenge.","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85095606","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}
Bouaou Kevin, Bollache Emilie, L. Didier, Mousseaux Élie, Kachenoura Nadjia, D. Thomas, Soulat Gilles, Houriez-Gombaud-Saintonge Sophia, Bargiotas Ioannis, De Cesare Alain, G. Umit, Giron Alain, Redheuil Alban
Ascending thoracic aortic aneurysms (ATAA) are defined by a silent dilation of the ascending aorta (AA). Although maximal aortic diameter is currently used for surgery planning, a high proportion of patients with low diameters ending up with aortic dissection. Our purpose was to propose a fine and comprehensive quantitative evaluation of pressure-flow-wall interplay from 4D flow MRI data in the setting of aortic dilation. We studied 12 patients with ATAA (67±14 years, 7 male) and 12 healthy subjects (63±12 years, 8 male) who underwent 4D flow MRI acquisition. The segmented velocity fields were used to estimate: 1) local AA pressure changes from Navier-Stokes-derived relative pressure maps (AADP), 2) AA wall shear stress (AAWSS) by estimating local velocity derivatives at the aortic borders, 3) aortic flow vorticity using the λ2 method (AAV). AADP was significantly and positively associated with both AAV (r=0.55, p=0.006) and AAWSS (r=0.69 p<0.001). Such associations remained significant after adjustment for maximal diameter, age and BSA. Local variations in pressures within the aorta, rendered possible while using 4D flow MRI, are associated with flow disorganization as quantified by vorticity and with the increase in the stress exerted on the aortic wall, as quantified by wall shear stress.
{"title":"Pressure and Flow Interplay in Aortic Dilation Using 4D Flow Magnetic Resonance Imaging","authors":"Bouaou Kevin, Bollache Emilie, L. Didier, Mousseaux Élie, Kachenoura Nadjia, D. Thomas, Soulat Gilles, Houriez-Gombaud-Saintonge Sophia, Bargiotas Ioannis, De Cesare Alain, G. Umit, Giron Alain, Redheuil Alban","doi":"10.22489/cinc.2019.058","DOIUrl":"https://doi.org/10.22489/cinc.2019.058","url":null,"abstract":"Ascending thoracic aortic aneurysms (ATAA) are defined by a silent dilation of the ascending aorta (AA). Although maximal aortic diameter is currently used for surgery planning, a high proportion of patients with low diameters ending up with aortic dissection. Our purpose was to propose a fine and comprehensive quantitative evaluation of pressure-flow-wall interplay from 4D flow MRI data in the setting of aortic dilation. We studied 12 patients with ATAA (67±14 years, 7 male) and 12 healthy subjects (63±12 years, 8 male) who underwent 4D flow MRI acquisition. The segmented velocity fields were used to estimate: 1) local AA pressure changes from Navier-Stokes-derived relative pressure maps (AADP), 2) AA wall shear stress (AAWSS) by estimating local velocity derivatives at the aortic borders, 3) aortic flow vorticity using the λ2 method (AAV). AADP was significantly and positively associated with both AAV (r=0.55, p=0.006) and AAWSS (r=0.69 p<0.001). Such associations remained significant after adjustment for maximal diameter, age and BSA. Local variations in pressures within the aorta, rendered possible while using 4D flow MRI, are associated with flow disorganization as quantified by vorticity and with the increase in the stress exerted on the aortic wall, as quantified by wall shear stress.","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90680657","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}
Mahmoud Ehnesh, Xin Li, N. Dastagir, Saaima Ahmad, T. Biala, P. J. Stafford, G. André Ng, F. Schlindwein
{"title":"“Investigating the Optimal Recording Duration for Summarising Spatiotemporal Behaviours of Long Lifespan Rotors Using Phase Mapping of Non-Contact Electrograms During Persistent Atrial Fibrillation’’","authors":"Mahmoud Ehnesh, Xin Li, N. Dastagir, Saaima Ahmad, T. Biala, P. J. Stafford, G. André Ng, F. Schlindwein","doi":"10.22489/cinc.2019.149","DOIUrl":"https://doi.org/10.22489/cinc.2019.149","url":null,"abstract":"","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82983538","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}
Maysa M. G. Macedo, Dario AB Oliveira, Marco Antonio Gutierrez
{"title":"Atherosclerotic Plaques Recognition in Intracoronary Optical Images Using Neural Networks","authors":"Maysa M. G. Macedo, Dario AB Oliveira, Marco Antonio Gutierrez","doi":"10.22489/cinc.2019.387","DOIUrl":"https://doi.org/10.22489/cinc.2019.387","url":null,"abstract":"","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78421602","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}
V. Gonçalves Marques, M. Rodrigo, Maria de la Salud Guillem Sánchez", J. Salinet
{"title":"Effects of Reducing the Number of Leads from Body Surface Potential Mapping in Computer Models of Atrial Arrhythmias","authors":"V. Gonçalves Marques, M. Rodrigo, Maria de la Salud Guillem Sánchez\", J. Salinet","doi":"10.22489/cinc.2019.099","DOIUrl":"https://doi.org/10.22489/cinc.2019.099","url":null,"abstract":"","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72895597","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}
In this work, we present a method to separate aortic (A2) and pulmonary (P2) components from second heart sounds (S2). The proposed approach captures the different dynamical behavior of A2 and P2 components via a joint Gaussian mixture model, which is then used to perform separation via a closed-form conditional mean estimator. The proposed approach is tested over synthetic heart sounds and it is shown guarantee a reduction of approximately 25% of the normalized root mean-squared error incurred in signal separation, with respect to a previously presented approach in the literature.
{"title":"Source Separation of the Second Heart Sound Using Gaussian Mixture Models","authors":"Renna Francesco, Coimbra Miguel","doi":"10.22489/cinc.2019.236","DOIUrl":"https://doi.org/10.22489/cinc.2019.236","url":null,"abstract":"In this work, we present a method to separate aortic (A2) and pulmonary (P2) components from second heart sounds (S2). The proposed approach captures the different dynamical behavior of A2 and P2 components via a joint Gaussian mixture model, which is then used to perform separation via a closed-form conditional mean estimator. The proposed approach is tested over synthetic heart sounds and it is shown guarantee a reduction of approximately 25% of the normalized root mean-squared error incurred in signal separation, with respect to a previously presented approach in the literature.","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79633600","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}
Langguth Johannes, Arevalo Hermenegild, H. Gregorius, Cai Xing
{"title":"Towards Detailed Real-Time Simulations of Cardiac Arrhythmia","authors":"Langguth Johannes, Arevalo Hermenegild, H. Gregorius, Cai Xing","doi":"10.22489/cinc.2019.301","DOIUrl":"https://doi.org/10.22489/cinc.2019.301","url":null,"abstract":"","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87988907","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}
Bai Jieyun, Lu Yaosheng, S. Tao, Wang Kuanquan, Zhang Henggui
{"title":"In Silico Investigation of the CACNA1C N2091S Mutation in Timothy Syndrome","authors":"Bai Jieyun, Lu Yaosheng, S. Tao, Wang Kuanquan, Zhang Henggui","doi":"10.22489/cinc.2019.003","DOIUrl":"https://doi.org/10.22489/cinc.2019.003","url":null,"abstract":"","PeriodicalId":6716,"journal":{"name":"2019 Computing in Cardiology Conference (CinC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79247497","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：