Deep Learning Model Using Transfer Learning for Detecting Left Ventricular Systolic Dysfunction: Retrospective Algorithm Development and Validation Study

Clinical Snapshot

Key Findings

• P Value: P<0.001 for recalibration improvement

• Effect Size: Recalibrated model AUROC 0.956 (internal) vs 0.940 (external validation)

• Primary Outcome: Area under receiver operating curve for LVSD detection

• Nnt Or Sensitivity: Sensitivity and specificity not reported - major limitation for clinical application

• Confidence Interval: Internal: 95% CI 0.946-0.965; External: 95% CI 0.936-0.945

Clinical Application

Requires integration with existing ECG and echocardiography systems; computational resources for deep learning model deployment Would require TGA approval as medical device; potential integration with existing cardiac monitoring programs; cost-effectiveness analysis needed for PBS consideration Patients requiring longitudinal monitoring for LVSD, particularly those with comorbidities where traditional AI-ECG models show degraded performance

Abstract

BACKGROUND: Artificial intelligence-augmented electrocardiogram (AI-ECG) models for detecting left ventricular systolic dysfunction (LVSD) often exhibit degraded performance in patients with comorbidities. OBJECTIVE: This study aimed to introduce and validate a recalibration method using longitudinal patient data to enhance prediction accuracy and simulate its clinical utility for ongoing monitoring. METHODS: We conducted a multicenter, retrospective cohort study using data from 2 hospitals in Korea. A dataset of paired transthoracic echocardiograms (TTEs) and electrocardiograms (ECGs) matched within a 2-week interval was constructed, separating pairs into baseline (first for each patient) and follow-up assessments. In addition to conventional supervised learning, we developed a patient-wise recalibration strategy that incorporated historical left ventricular ejection fraction measurements and prior AI-ECG outputs to adjust for future predictions, thus empirically mitigating confounding effects. Pretraining was also implemented to enhance the model's performance. RESULTS: The recalibrated 12-lead DeepECG LVSD model achieved an area under the receiver operating curve of 0.956 (95% CI 0.946-0.965) for internal validation and 0.940 (95% CI 0.936-0.945) for external validation of follow-up TTE-ECG pairs. The uncalibrated 12-lead DeepECG LVSD model also showed modest performance, with an area under the receiver operating curve of 0.953 (95% CI 0.941-0.965) in the internal validation and 0.947 (95% CI 0.943-0.951) in the external validation when tested on baseline TTE-ECG pairs. Recalibration yielded statistically significant improvements in the 12-lead DeepECG LVSD models (P<.001), with enhanced and more balanced performance across all clinical subgroups. CONCLUSIONS: Patient-wise recalibration improved accuracy and consistency across various comorbidities by mitigating performance degradation and bias. This broadens the application of AI-ECG for LVSD detection from low-risk screening to high-risk longitudinal monitoring.

References

1. 1.Lee, S., Son, J. W., Kim, S. A., Ahn, M. S., Lee, S. J., Han, S. J., Joo, T., Na, Y., Joo, S., Ahn, H. J., Chang, M., Lee, Y., & Park, Y. J. (2026). Deep Learning Model Using Transfer Learning for Detecting Left Ventricular Systolic Dysfunction: Retrospective Algorithm Development and Validation Study. JMIR Medical Informatics, 14(1), e83127. https://doi.org/10.2196/83127