xGNN4MI: explainability of graph neural networks in 12-lead electrocardiography for cardiovascular disease classification
Year: 2026
Type: article
Abstract: The clinical deployment of artificial intelligence (AI) solutions for assessing cardiovascular disease (CVD) risk in 12-lead electrocardiography (ECG) is hindered by limitations in interpretability and explainability. To address this, we present xGNN4MI, an open-source framework for graph neural networks (GNNs) in ECG modeling for interpretable CVD prediction. Our framework facilitates modeling clinically relevant spatial relationships between ECG leads and their temporal dynamics. We integrated explainable AI (XAI) and developed a task-specific XAI evaluation and visualization workflow to identify ECG leads crucial to the model's decision-making process, enabling a systematic comparison with established clinical knowledge. We evaluated xGNN4MI on two challenging tasks: diagnostic superclass classification and localization of myocardial infarction. Our findings show that the interpretable ECG-GNN models demonstrate good performance across the tasks. XAI analysis revealed clinically meaningful training effects, such as differentiating between anteroseptal and inferior myocardial infarction. Our work demonstrates the potential of ECG-GNNs for providing trustworthy and interpretable AI-based CVD diagnosis.
Source: npj Digital Medicine
Institutions: Universitätsmedizin Göttingen, Campus-Institut Data Science (CIDAS), University of Göttingen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Universitätsmedizin Greifswald, Universität Greifswald, German Centre for Cardiovascular Research, Technical University of Denmark, Justus-Liebig-Universität Gießen
Language: English
Topic: ECG Monitoring and Analysis
Subfield: Cardiology and Cardiovascular Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $4,090
Awards: Verbundprojekt: Spitzenforschung und Innovation in den Neuen Ländern - GANI_MED - Greifswald Approach to Individualized Medicine, G3030557272, G3865379469, Verbesserung der Leistungsfähigkeit der klinischen Forschung besonders in den Schwerpunkten Community Medicine und Molekulare Medizin, Phase II, G5899436117, G5985637321, G7028758128, Verbund FAIrPaCT - Föderiertes Framework für künstliche Intelligenz zur Optimierung der Behandlung von Bauchspeicheldrüsenkrebs - Standort Universität Göttingen, G7968855343, Verbesserung der Struktur- und Leistungsfähigkeit der klinischen Forschung besonders in den Schwerpunkten Community Medicine und Molekulare Medizin, Verbund FAIrPaCT2 - Föderierte multimodale künstliche Intelligenz für die Vorhersage des Ergebnisses von Bauchspeicheldrüsenkrebs - Universität Göttingen, G915808470
OpenAlex ID: W7127910800