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

Autor: Bivona DJ; Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA; Department of Biomedical Engineering, University of Virginia, Charlottesville, VA 22903, USA., Ghadimi S; Department of Biomedical Engineering, University of Virginia, Charlottesville, VA 22903, USA., Wang Y; Department of Biomedical Engineering, University of Virginia, Charlottesville, VA 22903, USA., Oomen PJA; Department of Biomedical Engineering, University of California Irvine, Irvine, CA 92697, USA., Malhotra R; Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA., Darby A; Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA., Mangrum JM; Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA., Mason PK; Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA., Mazimba S; Advent Health Transplant Institute, AdventHealth, Orlando, FL 32804, USA., Patel AR; Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA; Department of Radiology and Medical Imaging, University of Virginia Health System, Charlottesville, VA 22903, USA., Epstein FH; Department of Biomedical Engineering, University of Virginia, Charlottesville, VA 22903, USA; Department of Radiology and Medical Imaging, University of Virginia Health System, Charlottesville, VA 22903, USA., Bilchick KC; Department of Medicine, University of Virginia Health System, Charlottesville, VA 22903, USA. Electronic address: kcb7f@uvahealth.org.
Jazyk: angličtina
Zdroj: Computers in biology and medicine [Comput Biol Med] 2024 Aug; Vol. 178, pp. 108627. Date of Electronic Publication: 2024 May 22.
DOI: 10.1016/j.compbiomed.2024.108627
Abstrakt: 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.
Competing Interests: Declaration of competing interest Dr. Bilchick has research grant support from Medtronic and Siemens Healthineers. Dr. Mangrum has research grant support from Boston Scientific, CardioFocus, and St. Jude Medical. Dr. Epstein has research grant support from Siemens Healthineers. Dr. Patel has a research grant from GE Healthcare and research support from Circle CVI and Neosoft.
(Copyright © 2024 Elsevier Ltd. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: