Comparing Artificial Intelligence-Enabled Electrocardiogram Models in Identifying Left Atrium Enlargement and Long-term Cardiovascular Risk

Abstract

Background

The role of P wave in identifying left atrial enlargement (LAE) using artificial intelligence (AI)-enabled electrocardiogram (ECG) models is unclear. It is also unknown if AI-enabled single-lead ECGs could be used as a diagnostic tool for LAE surveillance. We aimed to build AI-enabled P-wave and single-lead ECG models to identify LAE using sinus rhythm (SR) and/or non-SR ECGs, and compared the prognostic ability of severe LAE as left atrial diameter (LAD) ≥50 mm assessed by AI-enabled ECG models and echocardiography.

Methods

This retrospective study used data from 382,594 consecutive adults with paired 12-lead ECG and echocardiograms measured within 2 weeks at Chang Gung Memorial Hospital. UNet++ was used for P-wave segmentation. ResNet-18 was used to develop deep convolutional neural network-enabled ECG models for discriminating LAE. External validation was performed using data from 11,753 patients from another hospital.

Results

The AI-enabled 12-lead ECG model outperformed other ECG models for classifying LAE, but the single-lead ECG models also showed excellent performance at an LAD cut-off 50 mm. AI-enabled ECG models had excellent and fair discrimination on LAE using the SR and the non-SR dataset, respectively. Severe LAE identified by AI-enabled ECG models was more predictive of future cardiovascular disease than echocardiography; however, the cumulative incidence of new-onset atrial fibrillation and heart failure was higher in patients with echocardiography-severe LAE than AI-enabled ECG-severe LAE.

Conclusions

P wave plays a crucial role in discriminating LAE in AI-enabled ECG models. AI-enabled ECG models outperform echocardiography in predicting new-onset cardiovascular diseases associated with severe LAE.