ArticleEuropean heart journal. Digital health2022
Improving explainability of deep neural network-based electrocardiogram interpretation using variational auto-encoders
Article in European heart journal. Digital health, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 33 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
33 citing papers in PubMed, 1 synthesis or guideline pooled it, 62 citations in OpenAlex.
- Advances in machine and deep learning for ECG beat classification: a systematic review.Frontiers in digital health · 2025Pooled it
- I-GraphECG: Observability-Based Lead Selection and Interpretable Disease Prediction from the 12-Lead ECG Using a Gray-Box Graph Electrophysiology Surrogate.Sensors (Basel, Switzerland) · 2026Article
- Artificial intelligence-enhanced electrocardiography for the prediction of future type 2 diabetes mellitus: a model-development and multicentre validation study.European heart journal. Digital health · 2026Article
- Premature ventricular contraction-mediated ventricular fibrillation: Clinical characteristics, application of machine-learning algorithm, and outcomes of catheter ablation-A case series.Heart rhythm O2 · 2026Article
- The Evolving Utility of Artificial Intelligence-Based Tools for the Detection of Heart Failure and Cardiomyopathies: From Potential to Implementation.Current heart failure reports · 2026Review
- Artificial Intelligence-Enabled Electrocardiography for Prediction of Sudden Cardiac Death and Malignant Ventricular Arrhythmias: A Scoping Review.Journal of cardiovascular development and disease · 2026Review
- Discovering Interpretable Semantics from Radio Signals for Contactless Cardiac Monitoring.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- AI-enabled privacy-preserving cardiac diagnostics via electrocardiograms.Scientific reports · 2026Article
- Synthetic artificial intelligence in cardiology: from generative models to clinical applications.European heart journal open · 2026Review
- Challenges in the Classification of Cardiac Arrhythmias and Ischemia Using End-to-End Deep Learning and the Electrocardiogram: A Systematic Review.Diagnostics (Basel, Switzerland) · 2026Review
- The cost of explainability in artificial intelligence-enhanced electrocardiogram models.NPJ digital medicine · 2025Article
- Deriving novel atrial fibrillation phenotypes using a tree-based artificial intelligence-enhanced electrocardiography approach.NPJ digital medicine · 2025Article
- Artificial intelligence-enhanced electrocardiography to predict regurgitant valvular heart diseases: an international study.European heart journal · 2025Article
- Preoperative risk prediction of major cardiovascular events in noncardiac surgery using the 12-lead electrocardiogram: an explainable deep learning approach.British journal of anaesthesia · 2025Observational
- Unsupervised feature extraction using deep learning empowers discovery of genetic determinants of the electrocardiogram.Genome medicine · 2025Article
- Enhancing explainability in clinical deep-learning models: Latent-space variable decoding is superior to gradient-weighted class activation mapping.Heart rhythm O2 · 2025Article
- Deep representation learning of electrocardiogram reveals biological insights in cardiac phenotypes and cardiovascular diseases.iScience · 2025Article
- Revisiting Abnormalities of Ventricular Depolarization: Redefining Phenotypes and Associated Outcomes Using Tree-Based Dimensionality Reduction.Journal of the American Heart Association · 2025Article
- Deep learning for electrocardiogram interpretation: Bench to bedside.European journal of clinical investigation · 2025Review
- Unsupervised deep learning of electrocardiograms enables scalable human disease profiling.NPJ digital medicine · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
12 authors at 4 institutions in 3 countries.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Aims: Deep neural networks (DNNs) perform excellently in interpreting electrocardiograms (ECGs), both for conventional ECG interpretation and for novel applications such as detection of reduced ejection fraction (EF). Despite these promising developments, implementation is hampered by the lack of trustworthy techniques to explain the algorithms to clinicians. Especially, currently employed heatmap-based methods have shown to be inaccurate. Methods and results: We present a novel pipeline consisting of a variational auto-encoder (VAE) to learn the underlying factors of variation of the median beat ECG morphology (the FactorECG), which are subsequently used in common and interpretable prediction models. As the ECG factors can be made explainable by generating and visualizing ECGs on both the model and individual level, the pipeline provides improved explainability over heatmap-based methods. By training on a database with 1.1 million ECGs, the VAE can compress the ECG into 21 generative ECG factors, most of which are associated with physiologically valid underlying processes. Performance of the explainable pipeline was similar to 'black box' DNNs in conventional ECG interpretation [area under the receiver operating curve (AUROC) 0.94 vs. 0.96], detection of reduced EF (AUROC 0.90 vs. 0.91), and prediction of 1-year mortality (AUROC 0.76 vs. 0.75). Contrary to the 'black box' DNNs, our pipeline provided explainability on which morphological ECG changes were important for prediction. Results were confirmed in a population-based external validation dataset. Conclusions: Future studies on DNNs for ECGs should employ pipelines that are explainable to facilitate clinical implementation by gaining confidence in artificial intelligence and making it possible to identify biased models.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.