The cost of explainability in artificial intelligence-enhanced electrocardiogram models

Artificial intelligence-enhanced electrocardiogram (AI-ECG) models have shown outstanding performance in diagnostic and prognostic tasks, yet their black-box nature hampers clinical adoption. Meanwhile, a growing demand for explainable AI in medicine underscores the need for transparent, trustworthy decision-making. Moving beyond post-hoc explainability techniques that have shown unreliable results, we focus on explicit representation learning using variational autoencoders (VAE) to capture inherently interpretable ECG features. While VAEs have demonstrated potential for ECG interpretability, the presumed performance-explainability trade-off remains underexplored, with many studies relying on complex, non-linear methods that obscure the morphological information of the features. In this work, we present a novel framework (VAE-SCAN) to model bi-directional, interpretable associations between ECG features and clinical factors. We also investigate how different representations affect ECG decoding performance across models with varying levels of explainability. Our findings demonstrate the cost introduced by intrinsic ECG interpretability, based on which we discuss potential implications and directions.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2025-12-05
DOI
https://doi.org/10.1038/s41746-025-02122-y
Citations
1
Primary Topic
ECG Monitoring and Analysis
Type
article
Field-Weighted Citation Impact
1.39

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

The cost of explainability in artificial intelligence-enhanced electrocardiogram models

Antônio H. Ribeiro, James S. Ware, Joseph Barker, Konstantinos Patlatzoglou et al.
1 citations
npj Digital Medicine
ECG Monitoring and Analysis
1.39
article

The cost of explainability in artificial intelligence-enhanced electrocardiogram models

Antônio H. Ribeiro, James S. Ware, Joseph Barker, Konstantinos Patlatzoglou, Libor Pastika, Ewa Sieliwończyk, Daniel B. Kramer, Nicholas S. Peters, Arunashis Sau, Gul Rukh Khattak, Fu Siong Ng, Jonathan W. Waks, Boroumand Zeidaabadi, Antonio Luiz P. Ribeiro
article en
1 citations

Abstract

Artificial intelligence-enhanced electrocardiogram (AI-ECG) models have shown outstanding performance in diagnostic and prognostic tasks, yet their black-box nature hampers clinical adoption. Meanwhile, a growing demand for explainable AI in medicine underscores the need for transparent, trustworthy decision-making. Moving beyond post-hoc explainability techniques that have shown unreliable results, we focus on explicit representation learning using variational autoencoders (VAE) to capture inherently interpretable ECG features. While VAEs have demonstrated potential for ECG interpretability, the presumed performance-explainability trade-off remains underexplored, with many studies relying on complex, non-linear methods that obscure the morphological information of the features. In this work, we present a novel framework (VAE-SCAN) to model bi-directional, interpretable associations between ECG features and clinical factors. We also investigate how different representations affect ECG decoding performance across models with varying levels of explainability. Our findings demonstrate the cost introduced by intrinsic ECG interpretability, based on which we discuss potential implications and directions.

npj Digital MedicineVol. 8(1)
Uppsala University (SE), Beth Israel Deaconess Medical Center (US), Harvard University (US), University of Antwerp (BE), Imperial College Healthcare NHS Trust (GB), Guy's and St Thomas' NHS Foundation Trust (GB), Chelsea and Westminster Hospital NHS Foundation Trust (GB), Royal Brompton & Harefield NHS Foundation Trust (GB), Harefield Hospital (GB), Lung Institute (US), Antwerp University Hospital (BE), Hospital das Clínicas da Universidade Federal de Minas Gerais (BR), MRC London Institute of Medical Sciences (GB), Deaconess Hospital (US), Imperial College London (GB)
British Heart Foundation
Openalex Percentile: Top 13%
ECG Monitoring and Analysis
1.39
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.