ScholarMate
English简体中文繁體中文
Customer service: 400-1616-289
Sign inSign up
Journal article

A multitask deep learning model utilizing electrocardiograms for major cardiovascular adverse events prediction

Lin, Ching-Heng; Liu, Zhi-Yong; Chu, Pao-Hsien; Chen, Jung-Sheng; Wu, Hsin-Hsu; Wen, Ming-Shien; Kuo, Chang-Fu; Chang, Ting-Yu*chang gung univ
npj Digital Medicine2025-1-2DOI: 10.1038/s41746-024-01410-3
13Reads
CiteSave
Share

Abstract

Deep learning analysis of electrocardiography (ECG) may predict cardiovascular outcomes. We present a novel multi-task deep learning model, the ECG-MACE, which predicts the one-year first-ever major adverse cardiovascular events (MACE) using 2,821,889 standard 12-lead ECGs, including training (n = 984,895), validation (n = 422,061), and test (n = 1,414,933) sets, from Chang Gung Memorial Hospital database in Taiwan. Data from another independent medical center (n = 113,224) was retrieved for external validation. The model's performance achieves AUROCs of 0.90 for heart failure (HF), 0.85 for myocardial infarction (MI), 0.76 for ischemic stroke (IS), and 0.89 for mortality. Furthermore, it outperforms the Framingham risk score at 5-year MACEs and 10-year mortality prediction. Over 10-year follow-ups, the model-predicted-positive group exhibits significantly higher MACE incidences than the model-predicted-negative group (relative incidence ratio: HF: 15.28; MI: 7.87; IS: 4.74; mortality: 13.18). Using solely ECGs, ECG-MACE effectively predicts one-year events and exhibits long-term anticipation. It provides potential applications in preventive medicine.

Disciplines and keywords

Keywords
CONVOLUTIONAL NEURAL-NETWORKST-SEGMENT ELEVATIONMYOCARDIAL-INFARCTIONSTROKERISK
Related
Loading…

Could not load papers. Please retry.

Retry

Publication info

Publication status
Published
Journal
npj Digital Medicine
Publication date
2025-01-02
Volume / issue
Vol. 8, Issue 1
Pages
1
DOI
10.1038/s41746-024-01410-3
Output indexing
SCIE
Funding acknowledgment
Ministry of Science and Technology, Taiwan (Ministry of Science and Technology of Taiwan); Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital [CORPG3L0461, CORPG3N0381, CLRPG3H0015]; Chang Gung Memorial Hospital Research Project [MOST111-2321-B-182A-004]; Ministry of Science and Technology, Taiwan

Authors

  • L

    Lin, Ching-Heng (First author)

    chang gung univ

  • L

    Liu, Zhi-Yong

View all 8 authorsShow fewer authors
  • C

    Chu, Pao-Hsien

    chang gung univ

  • C

    Chen, Jung-Sheng

  • W

    Wu, Hsin-Hsu

    chang gung univ

  • W

    Wen, Ming-Shien

    chang gung univ

  • K

    Kuo, Chang-Fu

    chang gung univ

  • C

    Chang, Ting-Yu (Corresponding)

    chang gung univ

Sign in for more features

  • Save this paper in My collections
  • Claim your outputs and generate promotion materials
  • Follow authors for new outputs
  • Join groups and collaborate
Sign up / Sign in

Products

  • ScholarMate
  • InnoCity
  • IRISaaS

Support

  • Help Center
  • Privacy Policy
  • Terms of Service

Contact

Online support: []
Customer service: 400-1616-289
Email: support@scholarmate.com

Follow or download ScholarMate

WeChat QR code
WeChat official account
App download QR code
Download the app
OutputsResearchersResearch institutionsResearch newsIRISaaS

©2026 深圳市科研之友网络服务有限公司

Public security registration badge粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417