Class-specific weighted ensemble improved sinus bradycardia recall by 4-5% and sinus tachycardia precision by 7-8% on 12-lead 10-s ECG segments versus bagging baseline.
Does a class-specific weighted ensemble model improve arrhythmia classification accuracy and interpretability compared to a bagging baseline on 12-lead ECGs?
A class-specific weighted ensemble model improves specific arrhythmia classification metrics (SB sensitivity and ST precision) and provides lead-level interpretability using SHAP.
Absolute Event Rate: 0% vs 0%
Accurate arrhythmia classification from short clinical ECGs is hard to achieve and explain. Prior studies are often single-lead, use uniform model fusion, or report point estimates without uncertainty. To address this, we propose a novel class-specific weighted ensemble for 12-lead, 10-s ECG segments that fuses multiple models with per-class weights and provides lead-resolved SHAP explanations over 360 features. Four rhythms (SB, ST, AF, SVT) were evaluated on the Chapman-Shaoxing dataset using an estimation-based framework with Wilson and Newcombe 95% CIs and Cohen's h. Compared with a Bagging baseline, the proposed ensemble yields higher SB recall on both validation and test (Δ +0.040 and +0.050, CIs entirely positive; small h), higher ST precision (Δ +0.070 and +0.080; small h), and comparable overall accuracy (Δ-CIs span 0; h ≈ 0.00-0.02). AF and SVT differences are small or imprecise. SHAP highlights lead-specific contributors (e.g., P-wave area in V2), indicating a path toward minimal-lead configurations while preserving performance. Collectively, integrating per-class weighted fusion, lead-level interpretability, and CI-based estimation on short 12-lead ECGs yields class-specific gains (higher SB sensitivity and ST precision), and SHAP pinpoints lead V2-with P-wave area among the top contributors. The outcome of this study provides potential insights that may be used to classify arrhythmia more accurately for each class and develop minimal lead configurations, given the growing use of wearable and portable devices. However, further studies and data are required for clinical application and device development.
Mina et al. (Thu,) reported a other. Class-specific weighted ensemble improved sinus bradycardia recall by 4-5% and sinus tachycardia precision by 7-8% on 12-lead 10-s ECG segments versus bagging baseline.