Background/Objectives: Artificial intelligence (AI)-enabled electrocardiogram (ECG) analysis may assist in objective and reproducible risk stratification. However, the prognostic utility of serial ECGs, particularly the follow-up ECG prior to discharge, has not been extensively studied. This study aimed to evaluate whether dynamic changes in AI-predicted ECG risk scores could enhance prediction of post-discharge outcomes. Methods: This retrospective cohort study included 11,508 ED visits from a single medical center where patients underwent two ECGs and were directly discharged. We stratified the mortality risk of patients as low risk, medium risk, and high risk based on the first and follow-up ECG prior to discharge using AI-enabled ECG models. The Area Under the Curve (AUC) was calculated for the predictive performance of the two ECGs. Kaplan-Meier (KM) curves were used for 90-day mortality analysis, and the Cox proportional hazards model was utilized to compare the risk of death across categories. Results: The AI-enabled ECG risk prediction model, based on the initial and follow-up ECGs prior to discharge, indicated risk transitions among different groups. The AUC for mortality risk was 78.6% for the first ECG and 83.3% for the follow-up ECG. KM curves revealed a significant increase in 90-day mortality for patients transitioning from low to medium/high risk upon discharge (Hazard Ratio: 6.01; Confidence Interval: 1.70-21.27). Conclusions: AI-enabled ECGs obtained prior to discharge provide superior mortality risk stratification for ED patients compared to initial ECGs. Patients classified as medium- or high-risk at discharge require careful consideration, whereas those at low risk can generally be discharged safely. Although AI-ECG alone does not replace comprehensive risk assessment, it offers a practical tool to support clinical judgment, particularly in the dynamic ED environment, by aiding safer discharge decisions.
Su et al. (Fri,) studied this question.