Artificial Intelligence-Enabled Electrocardiogram Predicted Left Ventricle Diameter as an Independent Risk Factor of Long-Term Cardiovascular Outcome in Patients With Normal Ejection Fraction

Hung-Yi Chen; Chin-Sheng Lin; Wen-Hui Fang; Chia-Cheng Lee; Ching-Liang Ho; Chih-Hung Wang; Chin Lin

doi:10.3389/fmed.2022.870523

Artificial Intelligence-Enabled Electrocardiogram Predicted Left Ventricle Diameter as an Independent Risk Factor of Long-Term Cardiovascular Outcome in Patients With Normal Ejection Fraction

Front Med (Lausanne). 2022 Apr 11:9:870523. doi: 10.3389/fmed.2022.870523. eCollection 2022.

Authors

Hung-Yi Chen¹, Chin-Sheng Lin², Wen-Hui Fang^{3

1

4}, Chia-Cheng Lee^{5

6}, Ching-Liang Ho⁷, Chih-Hung Wang^{8

9}, Chin Lin^{4

10}

Affiliations

¹ Department of Internal Medicine, National Defense Medical Center, Tri-Service General Hospital, Taipei, Taiwan.
² Division of Cardiology, Department of Internal Medicine, National Defense Medical Center, Tri-Service General Hospital, Taipei, Taiwan.
³ Department of Family and Community Medicine, National Defense Medical Center, Tri-Service General Hospital, Taipei, Taiwan.
⁴ Artificial Intelligence of Things Center, National Defense Medical Center, Tri-Service General Hospital, Taipei, Taiwan.
⁵ Medical Informatics Office, National Defense Medical Center, Tri-Service General Hospital, Taipei, Taiwan.
⁶ Division of Colorectal Surgery, Department of Surgery, National Defense Medical Center, Tri-Service General Hospital, Taipei, Taiwan.
⁷ Division of Hematology and Oncology, Department of Internal Medicine, National Defense Medical Center, Tri-Service General Hospital, Taipei, Taiwan.
⁸ Department of Otolaryngology-Head and Neck Surgery, National Defense Medical Center, Tri-Service General Hospital, Taipei, Taiwan.
⁹ National Defense Medical Center, Graduate Institute of Medical Sciences, Taipei, Taiwan.
¹⁰ Medical Technology Education Center, National Defense Medical Center, School of Medicine, Taipei, Taiwan.

Abstract

Background: Heart failure (HF) is a global disease with increasing prevalence in an aging society. However, the survival rate is poor despite the patient receiving standard treatment. Early identification of patients with a high risk of HF is important but challenging. Left ventricular end-diastolic diameter (LV-D) increase was an independent risk factor of HF and adverse cardiovascular (CV) outcomes. In this study, we aimed to develop an artificial intelligence (AI) enabled electrocardiogram (ECG) system to detect LV-D increase early.

Objective: We developed a deep learning model (DLM) to predict left ventricular end-diastolic and end-systolic diameter (LV-D and LV-S) with internal and external validations and investigated the relationship between ECG-LV-D and echocardiographic LV-D and explored the contributions of ECG-LV-D on future CV outcomes.

Methods: Electrocardiograms and corresponding echocardiography data within 7 days were collected and paired for DLM training with 99,692 ECGs in the development set and 20,197 ECGs in the tuning set. The other 7,551 and 11,644 ECGs were collected from two different hospitals to validate the DLM performance in internal and external validation sets. We analyzed the association and prediction ability of ECG-LVD for CV outcomes, including left ventricular (LV) dysfunction, CV mortality, acute myocardial infarction (AMI), and coronary artery disease (CAD).

Results: The mean absolute errors (MAE) of ECG-LV-D were 5.25/5.29, and the area under the receiver operating characteristic (ROC) curves (AUCs) were 0.8297/0.8072 and 0.9295/0.9148 for the detection of mild (56 ≦ LV-D < 65 mm) and severe (LV-D ≧ 65 mm) LV-D dilation in internal/external validation sets, respectively. Patients with normal ejection fraction (EF) who were identified as high ECHO-LV-D had the higher hazard ratios (HRs) of developing new onset LV dysfunction [HR: 2.34, 95% conference interval (CI): 1.78-3.08], CV mortality (HR 2.30, 95% CI 1.05-5.05), new-onset AMI (HR 2.12, 95% CI 1.36-3.29), and CAD (HR 1.59, 95% CI 1.26-2.00) in the internal validation set. In addition, the ECG-LV-D presents a 1.88-fold risk (95% CI 1.47-2.39) on new-onset LV dysfunction in the external validation set.

Conclusion: The ECG-LV-D not only identifies high-risk patients with normal EF but also serves as an independent risk factor of long-term CV outcomes.

Keywords: artificial intelligence; cardiovascular outcome; deep learning; ejection fraction; electrocardiogram; heart failure; left ventricular end-diastolic diameter.