ORIGINAL RESEARCH article
Front. Cardiovasc. Med.
Sec. Cardiac Rhythmology
Volume 12 - 2025 | doi: 10.3389/fcvm.2025.1659971
This article is part of the Research TopicArtificial Intelligence for Arrhythmia Detection and PredictionView all 10 articles
ECG-XPLAIM: eXPlainable Locally-adaptive Artificial Intelligence Model for arrhythmia detection from large-scale electrocardiogram data
Provisionally accepted- 13rd Department of Cardiology, National and Kapodistrian University of Athens, Athens, Greece
- 2Eidgenossische Technische Hochschule Zurich, Zürich, Switzerland
- 31st Department of Cardiology, National and Kapodistrian University of Athens, Athens, Greece
- 4Universitat Politecnica de Valencia Instituto ITACA, Valencia, Spain
- 5Stockholms universitet Institutionen for Data- och Systemvetenskap, Kista, Sweden
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Background: Timely and accurate detection of arrhythmias from electrocardiograms (ECGs) is crucial for improving patient outcomes. While artificial intelligence (AI)-based ECG classification has shown promising results, limited transparency and interpretability often impede clinical adoption. Methods: We present ECG-XPLAIM, a novel deep learning model dedicated to ECG classification that employs a one-dimensional inception-style convolutional architecture to capture local waveform features (e.g. waves and intervals) and global rhythm patterns. To enhance interpretability, we integrate Grad-CAM visualization, highlighting key waveform segments that drive the model's predictions. ECG-XPLAIM was trained on the MIMIC-IV dataset and externally validated on PTB-XL for multiple arrhythmias, including atrial fibrillation (AFib), sinus tachycardia (STach), conduction disturbances (RBBB, LBBB, LAFB), long QT (LQT), Wolff-Parkinson-White (WPW) pattern, and paced rhythm detection. We evaluated performance using sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC), and benchmarked against a simplified convolutional neural network, a two-layer gated recurrent unit (GRU), and an external, pre-trained, ResNet-based model. Results: Internally (MIMIC-IV), ECG-XPLAIM achieved high diagnostic performance (sensitivity, specificity, AUROC > 0.9) across most tasks. External evaluation (PTB-XL) confirmed generalizability, with metric values exceeding 0.95 for AFib and STach. For conduction disturbances, macro-averaged sensitivity reached 0.90, specificity 0.95, and AUROC 0.98. Performance for LQT, WPW, and pacing rhythm detection was 0.691/0.864/0.878, 0.773/0.973/0.895, and 0.96/0.988/0.993 (sensitivity/specificity/AUROC), respectively. Compared to baseline models, ECG-XPLAIM offered superior performance across most tests, and improved sensitivity over the external ResNet-based model, albeit at the cost of specificity. Grad-CAM revealed physiologically relevant ECG segments influencing predictions and highlighted patterns of potential misclassification. Conclusion: ECG-XPLAIM combines high diagnostic performance with interpretability, addressing a key limitation in AI-driven ECG analysis. The open-source release of ECG-XPLAIM's architecture and pre-trained weights encourages broader adoption, external validation, and further refinement for diverse clinical applications.
Keywords: arrhythmia, electrocardiogram, artificial intelligence, deep learning, machine learning, Cardiac Signals, Explainability
Received: 04 Jul 2025; Accepted: 30 Sep 2025.
Copyright: © 2025 Pantelidis, Ruiperez-Campillo, Vogt, Antonopoulos, Gialamas, Zakynthinos, Spartalis, Dilaveris, Millet, Papapetrou, Papaioannou, Oikonomou and Siasos. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Panteleimon Pantelidis, pan.g.pantelidis@gmail.com
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.