Machine learning of ECG waveforms and cardiac magnetic resonance for response and survival after cardiac resynchronization therapy

被引：1
作者：
Bivona D.J. [1 ,2 ]
Ghadimi S. [2 ]
Wang Y. [2 ]
Oomen P.J.A. [4 ]
Malhotra R. [1 ]
Darby A. [1 ]
Mangrum J.M. [1 ]
Mason P.K. [1 ]
Mazimba S. [5 ]
Patel A.R. [1 ,3 ]
Epstein F.H. [2 ,3 ]
Bilchick K.C. [1 ]
机构：
[1] Department of Medicine, University of Virginia Health System, Charlottesville, 22903, VA
[2] Department of Biomedical Engineering, University of Virginia, Charlottesville, 22903, VA
[3] Department of Radiology and Medical Imaging, University of Virginia Health System, Charlottesville, 22903, VA
[4] Department of Biomedical Engineering, University of California Irvine, Irvine, 92697, CA
[5] Advent Health Transplant Institute, AdventHealth, Orlando, 32804, FL
来源：
Computers in Biology and Medicine | 2024年 / 178卷
关键词：
Cardiac resynchronization therapy; Electrocardiogram; Functional principal component decomposition; Heart failure; Machine learning; Magnetic resonance imaging;
D O I：
10.1016/j.compbiomed.2024.108627
中图分类号：
学科分类号：
摘要：
Cardiac resynchronization therapy (CRT) can lead to marked symptom reduction and improved survival in selected patients with heart failure with reduced ejection fraction (HFrEF); however, many candidates for CRT based on clinical guidelines do not have a favorable response. A better way to identify patients expected to benefit from CRT that applies machine learning to accessible and cost-effective diagnostic tools such as the 12-lead electrocardiogram (ECG) could have a major impact on clinical care in HFrEF by helping providers personalize treatment strategies and avoid delays in initiation of other potentially beneficial treatments. This study addresses this need by demonstrating that a novel approach to ECG waveform analysis using functional principal component decomposition (FPCD) performs better than measures that require manual ECG analysis with the human eye and also at least as well as a previously validated but more expensive approach based on cardiac magnetic resonance (CMR). Analyses are based on five-fold cross validation of areas under the curve (AUCs) for CRT response and survival time after the CRT implant using Cox proportional hazards regression with stratification of groups using a Gaussian mixture model approach. Furthermore, FPCD and CMR predictors are shown to be independent, which demonstrates that the FPCD electrical findings and the CMR mechanical findings together provide a synergistic model for response and survival after CRT. In summary, this study provides a highly effective approach to prognostication after CRT in HFrEF using an accessible and inexpensive diagnostic test with a major expected impact on personalization of therapies. © 2024 Elsevier Ltd
引用
收藏
相关论文
共 25 条
[1]  
Chung M.K., Patton K.K., Lau C.P., Dal Forno A.R.J., Al-Khatib S.M., Arora V., Birgersdotter-Green U.M., Cha Y.M., Chung E.H., Cronin E.M., Curtis A.B., Cygankiewicz I., Dandamudi G., Dubin A.M., Ensch D.P., Glotzer T.V., Gold M.R., Goldberger Z.D., Gopinathannair R., Gorodeski E.Z., Gutierrez A., Guzman J.C., Huang W., Imrey P.B., Indik J.H., Karim S., Karpawich P.P., Khaykin Y., Kiehl E.L., Kron J., Kutyifa V., Link M.S., Marine J.E., Mullens W., Park S.J., Parkash R., Patete M.F., Pathak R.K.
[2]  
Bristow M.R., Saxon L.A., Boehmer J., Krueger S., Kass D.A., De Marco T., Carson P., DiCarlo L., DeMets D., White B.G., Cardiac-resynchronization therapy with or without an implantable defibrillator in advanced chronic heart failure, N. Engl. J. Med., 350, 21, pp. 2140-2150, (2004)
[3]  
Abraham W.T., Fisher W.G., Smith A.L., Delurgio D.B., Leon A.R., Loh E., Kocovic D.Z., Packer M., Clavell A.L., Hayes D.L., Cardiac resynchronization in chronic heart failure, N. Engl. J. Med., 346, 24, pp. 1845-1853, (2002)
[4]  
Chung E.S., Leon A.R., Tavazzi L., Sun J.P., Nihoyannopoulos P., Merlino J., Abraham W.T., Ghio S., Leclercq C., Bax J.J., Results of the predictors of response to CRT (PROSPECT) trial, Circulation, 117, 20, pp. 2608-2616, (2008)
[5]  
Linde C., Abraham W.T., Gold M.R., Sutton M.S.J., Ghio S., Daubert C., Randomized trial of cardiac resynchronization in mildly symptomatic heart failure patients and in asymptomatic patients with left ventricular dysfunction and previous heart failure symptoms, J. Am. Coll. Cardiol., 52, 23, pp. 1834-1843, (2008)
[6]  
Arshad A., Moss A.J., Foster E., Padeletti L., Barsheshet A., Goldenberg I., Greenberg H., Hall W.J., McNitt S., Zareba W., Solomon S., Steinberg J.S., Madit-Crt Executive Committee G., Cardiac resynchronization therapy is more effective in women than in men: the MADIT-CRT (multicenter automatic defibrillator implantation trial with cardiac resynchronization therapy) trial, J. Am. Coll. Cardiol., 57, 7, pp. 813-820, (2011)
[7]  
Bilchick K.C., Kuruvilla S., Hamirani Y.S., Ramachandran R., Clarke S.A., Parker K.M., Stukenborg G.J., Mason P., Ferguson J.D., Moorman J.R., Impact of mechanical activation, scar, and electrical timing on cardiac resynchronization therapy response and clinical outcomes, J. Am. Coll. Cardiol., 63, 16, pp. 1657-1666, (2014)
[8]  
Ramachandran R., Chen X., Kramer C.M., Epstein F.H., Bilchick K.C., Singular value decomposition applied to cardiac strain from MR imaging for selection of optimal cardiac resynchronization therapy candidates, Radiology, 275, 2, pp. 413-420, (2015)
[9]  
Bilchick K.C., Auger D.A., Abdishektaei M., Mathew R., Sohn M.W., Cai X., Sun C., Narayan A., Malhotra R., Darby A., Mangrum J.M., Mehta N., Ferguson J., Mazimba S., Mason P.K., Kramer C.M., Levy W.C., Epstein F.H., CMR DENSE and the seattle heart failure model inform survival and arrhythmia risk after CRT, JACC Cardiovasc. Imaging, 13, 4, pp. 924-936, (2020)
[10]  
Bilchick K.C., Wang Y., Curtis J.P., Cheng A., Dharmarajan K., Shadman R., Dardas T.F., Anand I., Lund L.H., Dahlstrom U., Sartipy U., Maggioni A., O'Connor C., Levy W.C., Modeling defibrillation benefit for survival among cardiac resynchronization therapy defibrillator recipients, Am. Heart J., 222, pp. 93-104, (2020)
123