Explainable Deep Learning-based Classification of Wolff-Parkinson-White Electrocardiographic Signals

2025-11-08

AI Summary

To address low anatomical resolution, poor model interpretability, and limited generalizability under small-sample conditions in accessory pathway (AP) localization for Wolff–Parkinson–White (WPW) syndrome, this study proposes a novel paradigm integrating cardiac digital twin technology with eXplainable AI (XAI). Physiologically realistic synthetic ECG data are generated from personalized virtual heart models to train a deep learning classifier for noninvasive, high-precision AP localization across 24 cardiac regions. We introduce an ECG lead importance index and augment physiological interpretability via XAI techniques—including Guided Backpropagation and Grad-CAM. The model achieves 95.1% accuracy, 94.32% sensitivity, and 99.78% specificity. Critically, identified key leads (V2, aVF, V1, aVL) align closely with established ventricular depolarization mechanisms—demonstrating substantial improvement over conventional decision-tree approaches and opaque deep learning methods.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Calibration & Uncertainty Quantification
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Wolff-Parkinson-White (WPW) syndrome is a cardiac electrophysiology (EP) disorder caused by the presence of an accessory pathway (AP) that bypasses the atrioventricular node, faster ventricular activation rate, and provides a substrate for atrio-ventricular reentrant tachycardia (AVRT). Accurate localization of the AP is critical for planning and guiding catheter ablation procedures. While traditional diagnostic tree (DT) methods and more recent machine learning (ML) approaches have been proposed to predict AP location from surface electrocardiogram (ECG), they are often constrained by limited anatomical localization resolution, poor interpretability, and the use of small clinical datasets. In this study, we present a Deep Learning (DL) model for the localization of single manifest APs across 24 cardiac regions, trained on a large, physiologically realistic database of synthetic ECGs generated using a personalized virtual heart model. We also integrate eXplainable Artificial Intelligence (XAI) methods, Guided Backpropagation, Grad-CAM, and Guided Grad-CAM, into the pipeline. This enables interpretation of DL decision-making and addresses one of the main barriers to clinical adoption: lack of transparency in ML predictions. Our model achieves localization accuracy above 95%, with a sensitivity of 94.32% and specificity of 99.78%. XAI outputs are physiologically validated against known depolarization patterns, and a novel index is introduced to identify the most informative ECG leads for AP localization. Results highlight lead V2 as the most critical, followed by aVF, V1, and aVL. This work demonstrates the potential of combining cardiac digital twins with explainable DL to enable accurate, transparent, and non-invasive AP localization.

Problem

• Localizing accessory pathways in WPW syndrome using deep learning
• Improving interpretability of ECG classification with explainable AI methods
• Overcoming limited resolution and transparency in traditional diagnostic approaches

Innovation

• Deep Learning model localizes accessory pathways across 24 regions
• Integrates explainable AI methods for transparent decision interpretation
• Uses synthetic ECG database from personalized virtual heart model