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

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

JOURNAL=Frontiers in Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2022.870523

DOI=10.3389/fmed.2022.870523

ISSN=2296-858X

ABSTRACT=BACKGROUND
Heart failure (HF) is a global disease with increasing prevalence in aging society. However, survival rate is poor despite the patient received standard treatment. Early identification of patients with 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 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.
METHOD
ECGs and corresponding echocardiography data within 7 days were collected and paired for DLM training with 99,692 ECGs in development set and 20,197 ECGs in tuning set. There were 7,551 and 11,644 ECGs in two different hospitals used 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 receiver operation characteristic curves (AUCs) were 0.8297/0.8072 and 0.9295/0.9148 for 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 higher hazard ratios (HRs) of developing new onset LV dysfunction [hazard ratio (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 internal validation set. The ECG-LV-D also presents 1.88-fold risk (95% CI 1.47-2.39) on new-onset LV dysfunction in 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.