Predicting ventricular arrhythmia in myocardial ischemia using deep learning.

BACKGROUND

Myocardial ischemia can trigger ventricular arrhythmias with life-threatening consequences. Current monitoring is largely reactive, limiting opportunities for preventive intervention.

OBJECTIVE

This study aimed to determine whether high-resolution epicardial electrograms contain predictive signatures that enable forecasting the timing of premature ventricular contractions (PVCs) during acute ischemia, and to quantify subject-specific data requirements for effective personalization.

METHODS

We analyzed epicardial sock electrograms (247 electrodes, 1 kHz) from 21 porcine acute ischemia experiments comprising 2252 spontaneous PVCs. Signals were segmented into overlapping sequences of 3, 5, or 7 consecutive non-PVC beats with a continuous target of time-to-next PVC. A 6-layer long short-term memory network (hidden size 128) with temporal attention was trained using mean absolute error (MAE). Performance was evaluated in (A) pooled 80/10/10 cross-validation and (B) leave-1-experiment-out testing with subject-specific fine-tuning using 10% or 15% of held-out data.

RESULTS

In Paradigm A, MAE decreased with longer context (6.50 seconds for 3 beats, 5.97 seconds for 5 beats, and 4.73 seconds for 7 beats) with excellent calibration (R 2 > 0.996). In Paradigm B, increasing fine-tuning from 10% to 15% reduced mean MAE by 9.6-14.6 seconds and flattened error growth with prediction horizon, improving the fraction of predictions within 30-60 seconds windows.

CONCLUSION

Epicardial electrograms support accurate PVC time-to-event forecasting during acute ischemia, and modest subject-specific adaptation substantially improves generalization, motivating development of real-time predictive monitoring tools.