Artificial intelligence-estimated biological heart age using a 12-lead electrocardiogram predicts mortality and cardiovascular outcomes

Yong-Soo Baek; Dong-Ho Lee; Yoonsu Jo; Sang-Chul Lee; Wonik Choi; Dae-Hyeok Kim

doi:10.3389/fcvm.2023.1137892

Artificial intelligence-estimated biological heart age using a 12-lead electrocardiogram predicts mortality and cardiovascular outcomes

Front Cardiovasc Med. 2023 Apr 13:10:1137892. doi: 10.3389/fcvm.2023.1137892. eCollection 2023.

Authors

Yong-Soo Baek^{1

2

3}, Dong-Ho Lee², Yoonsu Jo², Sang-Chul Lee^{2

4}, Wonik Choi^{2

5}, Dae-Hyeok Kim^{1

2}

Affiliations

¹ Division of Cardiology, Department of Internal Medicine, Inha University College of Medicine and Inha University Hospital, Incheon, South Korea.
² DeepCardio Inc., Incheon, South Korea.
³ School of Computer Science, University of Birmingham, Birmingham, United Kingdom.
⁴ Department of Computer Engineering, Inha University, Incheon, South Korea.
⁵ Department of Information and Communication Engineering, Inha University, Incheon, South Korea.

Abstract

Background: There is a paucity of data on artificial intelligence-estimated biological electrocardiography (ECG) heart age (AI ECG-heart age) for predicting cardiovascular outcomes, distinct from the chronological age (CA). We developed a deep learning-based algorithm to estimate the AI ECG-heart age using standard 12-lead ECGs and evaluated whether it predicted mortality and cardiovascular outcomes.

Methods: We trained and validated a deep neural network using the raw ECG digital data from 425,051 12-lead ECGs acquired between January 2006 and December 2021. The network performed a holdout test using a separate set of 97,058 ECGs. The deep neural network was trained to estimate the AI ECG-heart age [mean absolute error, 5.8 ± 3.9 years; R-squared, 0.7 (r = 0.84, p < 0.05)].

Findings: In the Cox proportional hazards models, after adjusting for relevant comorbidity factors, the patients with an AI ECG-heart age of 6 years older than the CA had higher all-cause mortality (hazard ratio (HR) 1.60 [1.42-1.79]) and more major adverse cardiovascular events (MACEs) [HR: 1.91 (1.66-2.21)], whereas those under 6 years had an inverse relationship (HR: 0.82 [0.75-0.91] for all-cause mortality; HR: 0.78 [0.68-0.89] for MACEs). Additionally, the analysis of ECG features showed notable alterations in the PR interval, QRS duration, QT interval and corrected QT Interval (QTc) as the AI ECG-heart age increased.

Conclusion: Biological heart age estimated by AI had a significant impact on mortality and MACEs, suggesting that the AI ECG-heart age facilitates primary prevention and health care for cardiovascular outcomes.

Keywords: ECG age; MACE; artificial intelligence; biological ageing; heart age; hospitalization; mortality.

Grants and funding

This work was supported by an Inha University Research Grant (Y-SB) and an Institute of Information & Communications Technology Planning & Evaluation (IITP) grant (WC) funded by the Korean Government (MSIT) [grant no. RS-2022-00155915, Artificial Intelligence Convergence Innovation Human Resources Development (Inha University)]. The funders of the study had no role in the study design; data collection, analysis, or interpretation; writing of the report; or the decision to submit it for publication.