JMIR Publications

ABSTRACT

Background:

When using a smartwatch to obtain electrocardiogram (ECG) signals from multiple leads, the device has to be placed on different parts of the body sequentially. The ECG signals measured from different leads are asynchronous. Artificial intelligence (AI) models for asynchronous ECG signals have barely been explored.

Objective:

We aimed to develop an AI model for detecting acute myocardial infarction using asynchronous ECGs and compare its performance with that of automatic ECG interpretations provided by commercial ECG analysis software. We sought to evaluate the feasibility of implementing multiple lead-based AI-enabled ECG algorithms on smartwatches. Moreover, we aimed to determine the optimal number of leads for sufficient diagnostic power.

Methods:

We extracted ECGs recorded within 24 hours from each visit to the emergency room of Ajou University Medical Center between June 1994 and January 2018 from patients aged 20 years or older. The ECGs were labeled according to whether a diagnostic code corresponding to acute myocardial infarction was entered. We derived asynchronous ECG lead sets from standard 12-lead ECG reports and simulated a situation similar to the sequential recording of ECG leads via smartwatches. We constructed an AI model based on residual networks and self-attention mechanisms by randomly masking each lead channel during the training phase and then testing the model using various targeting lead sets with the remainder lead channels masked.

Results:

The performance of lead sets with three or more leads compared favorably with the automatic ECG interpretations provided by a commercial ECG analysis software, with 8.1%–13.9% gain in sensitivity when the specificity was matched. Our results indicated that multiple lead-based AI-enabled ECG algorithms can be implemented on smartwatches. Model performance generally increased as the number of leads increased (12-lead sets: area under the receiver operating characteristic curve [AUROC], 0.880; 4-lead sets: AUROC, 0.858 ± 0.008; 3-lead sets: AUROC, 0.845 ± 0.011; 2-lead sets: AUROC, 0.813 ± 0.018; single-lead sets: AUC, 0.768 ± 0.001). Considering the short amount of time needed to measure additional leads, measuring at least three leads—ideally more than four leads—is necessary for minimizing the risk of failing to detect acute myocardial infarction occurring in a certain spatial location or direction.

Conclusions:

By developing AI models for detecting acute myocardial infarction with asynchronous ECG lead sets, we showed the feasibility of multiple lead-based AI-enabled ECG algorithms on smartwatches for automated diagnosis of cardiac disorders. We also demonstrated the necessity of measuring at least three leads for accurate detection. Our results can be used as reference for the development of other AI models using sequentially measured asynchronous ECG leads via smartwatches for detecting various cardiac disorders.