Explainable deep learning based techniques for ECG-Based heart disease classification: A systematic literature review and future direction
A considerable amount of XAI-based DL architectures were identified for the classification of ECG-based HD. The techniques frequently selected by these studies have potential limitations such as data standardization, inconsistent explainability, temporal dependency visualization, lack of XAI benchmarking, lack of standardized metrics, and many more, which are presented with proposed future research directions.
Authors
- Mahdi Momeni (ORCID: https://orcid.org/0000-0002-9284-3915)
- Rifa Atul Izza Asyari (ORCID: https://orcid.org/0000-0002-2631-9365)
- Ali Ebrahimi (ORCID: https://orcid.org/0000-0002-3332-6205)
- Jonas Moll (ORCID: https://orcid.org/0000-0002-4772-4730)
- Sadasivan Puthusserypady (ORCID: https://orcid.org/0000-0001-7564-2612)
- Masud Shah Jahan
- Gouthamaan Manimaran (ORCID: https://orcid.org/0000-0002-0890-2450)
- Uffe Kock Wiil (ORCID: https://orcid.org/0000-0001-6898-4083)
- Abdolrahman Peimankar (ORCID: https://orcid.org/0000-0001-9779-9442)
Institutions
- University of Southern Denmark (DK)
- Maersk (Denmark) (DK)
- Vital Research (US)
- Technical University of Denmark (DK)
Publication Details
- Journal
- Computers in Biology and Medicine
- Published
- 2025-11-20
- DOI
- https://doi.org/10.1016/j.compbiomed.2025.111324
- Citations
- 2
- Primary Topic
- ECG Monitoring and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 2.78