Detection of Left Ventricular Systolic Dysfunction From Electrocardiographic Images

Author:

Sangha Veer1,Nargesi Arash A.23,Dhingra Lovedeep S.2ORCID,Khunte Akshay1ORCID,Mortazavi Bobak J.45ORCID,Ribeiro Antônio H.6ORCID,Banina Evgeniya7ORCID,Adeola Oluwaseun8ORCID,Garg Nadish9,Brandt Cynthia A.1011ORCID,Miller Edward J.2ORCID,Ribeiro Antonio Luiz P.1213ORCID,Velazquez Eric J.2ORCID,Giatti Luana14ORCID,Barreto Sandhi M.14ORCID,Foppa Murilo15ORCID,Yuan Neal1617ORCID,Ouyang David1819ORCID,Krumholz Harlan M.2520ORCID,Khera Rohan2521ORCID

Affiliation:

1. Department of Computer Science (V.S., A.K.), Yale University, New Haven, CT.

2. Section of Cardiovascular Medicine, Department of Internal Medicine (A.A.N., L.S.D., E.J.M., E.J.V., H.M.K., R.K.), Yale University, New Haven, CT.

3. Heart and Vascular Center, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA (A.A.N.).

4. Department of Computer Science & Engineering, Texas A&M University, College Station (B.J.M.).

5. Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT (B.J.M., H.M.K., R.K.).

6. Department of Information Technology, Uppsala University, Sweden (A.H.R.).

7. Internal Medicine Department, Lake Regional Hospital Health, Osage Beach, MO (E.B.).

8. Methodist Cardiology Clinic of San Antonio, TX (O.A.).

9. Heart and Vascular Institute, Memorial Hermann Southeast Hospital, Houston, TX (N.G.).

10. Department of Emergency Medicine (C.A.B.), Yale University, New Haven, CT.

11. VA Connecticut Healthcare System, West Haven, CT (C.A.B.).

12. Telehealth Center and Cardiology Service, Hospital das Clínicas (A.L.P.R.), Universidade Federal de Minas Gerais, Belo Horizonte, Brazil.

13. Department of Internal Medicine, Faculdade de Medicina (A.L.P.R.), Universidade Federal de Minas Gerais, Belo Horizonte, Brazil.

14. Department of Preventive Medicine, School of Medicine and Hospital das Clínicas (L.G., S.M.B.), Universidade Federal de Minas Gerais, Belo Horizonte, Brazil.

15. Postgraduate Studies Program in Cardiology and Division of Cardiology, Hospital de Clinicas de Porto Alegre, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil (M.F.).

16. Department of Medicine, University of California, San Francisco, CA (N.Y.).

17. Section of Cardiology, San Francisco Veterans Affairs Medical Center, CA (N.Y.).

18. Department of Cardiology, Smidt Heart Institute (D.O.), Cedars-Sinai Medical Center, Los Angeles, CA.

19. Division of Artificial Intelligence in Medicine (D.O.), Cedars-Sinai Medical Center, Los Angeles, CA.

20. Department of Health Policy and Management (H.M.K.), Yale School of Public Health, New Haven, CT.

21. Section of Health Informatics, Department of Biostatistics (R.K.), Yale School of Public Health, New Haven, CT.

Abstract

BACKGROUND: Left ventricular (LV) systolic dysfunction is associated with a >8-fold increased risk of heart failure and a 2-fold risk of premature death. The use of ECG signals in screening for LV systolic dysfunction is limited by their availability to clinicians. We developed a novel deep learning–based approach that can use ECG images for the screening of LV systolic dysfunction. METHODS: Using 12-lead ECGs plotted in multiple different formats, and corresponding echocardiographic data recorded within 15 days from the Yale New Haven Hospital between 2015 and 2021, we developed a convolutional neural network algorithm to detect an LV ejection fraction <40%. The model was validated within clinical settings at Yale New Haven Hospital and externally on ECG images from Cedars Sinai Medical Center in Los Angeles, CA; Lake Regional Hospital in Osage Beach, MO; Memorial Hermann Southeast Hospital in Houston, TX; and Methodist Cardiology Clinic of San Antonio, TX. In addition, it was validated in the prospective Brazilian Longitudinal Study of Adult Health. Gradient-weighted class activation mapping was used to localize class-discriminating signals on ECG images. RESULTS: Overall, 385 601 ECGs with paired echocardiograms were used for model development. The model demonstrated high discrimination across various ECG image formats and calibrations in internal validation (area under receiving operation characteristics [AUROCs], 0.91; area under precision-recall curve [AUPRC], 0.55); and external sets of ECG images from Cedars Sinai (AUROC, 0.90 and AUPRC, 0.53), outpatient Yale New Haven Hospital clinics (AUROC, 0.94 and AUPRC, 0.77), Lake Regional Hospital (AUROC, 0.90 and AUPRC, 0.88), Memorial Hermann Southeast Hospital (AUROC, 0.91 and AUPRC 0.88), Methodist Cardiology Clinic (AUROC, 0.90 and AUPRC, 0.74), and Brazilian Longitudinal Study of Adult Health cohort (AUROC, 0.95 and AUPRC, 0.45). An ECG suggestive of LV systolic dysfunction portended >27-fold higher odds of LV systolic dysfunction on transthoracic echocardiogram (odds ratio, 27.5 [95% CI, 22.3–33.9] in the held-out set). Class-discriminative patterns localized to the anterior and anteroseptal leads (V 2 and V 3 ), corresponding to the left ventricle regardless of the ECG layout. A positive ECG screen in individuals with an LV ejection fraction ≥40% at the time of initial assessment was associated with a 3.9-fold increased risk of developing incident LV systolic dysfunction in the future (hazard ratio, 3.9 [95% CI, 3.3–4.7]; median follow-up, 3.2 years). CONCLUSIONS: We developed and externally validated a deep learning model that identifies LV systolic dysfunction from ECG images. This approach represents an automated and accessible screening strategy for LV systolic dysfunction, particularly in low-resource settings.

Publisher

Ovid Technologies (Wolters Kluwer Health)

Subject

Physiology (medical),Cardiology and Cardiovascular Medicine

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3