mlsanityData to 14 Oct 2026

Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery

arXiv 2305.17043 ↗First posted 26 May 2023eess.SP cs.LG stat.MLcited by 15

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have become increasingly popular for analyzing ECG data because of their ability to accurately identify cardiac conditions and hidden clinical factors. However, the lack of transparency due to the black box nature of these models is a common concern. To address this issue, explainable AI (XAI) methods can be employed. In this study, we present a comprehensive analysis of post-hoc XAI methods, investigating the local (attributions per sample) and global (based on domain expert concepts) perspectives. We have established a set of sanity checks to identify sensible attribution methods, and we provide quantitative evidence in accordance with expert rules. This dataset-wide analysis goes beyond anecdotal evidence by aggregating data across patient subgroups. Furthermore, we demonstrate how these XAI techniques can be utilized for knowledge discovery, such as identifying subtypes of myocardial infarction. We believe that these proposed methods can serve as building blocks for a complementary assessment of the internal validity during a certification process, as well as for knowledge discovery in the field of ECG analysis.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 26 of its 78 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

26 of 78 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  7. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  8. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 431
  9. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  10. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  11. 2019Automatic diagnosis of the 12-lead ECG using a deep neural networkcited by 164
  12. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 159
14 more
  1. 2020Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XLcited by 158
  2. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  3. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 91
  4. 2021Self-supervised representation learning from 12-lead ECG datacited by 80
  5. 2022Concept Activation Regions: A Generalized Framework For Concept-Based Explanationscited by 57
  6. 2021Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAycited by 55
  7. 2023Multi-dimensional concept discovery (MCD): A unifying framework with completeness guaranteescited by 50
  8. 2019Deep neural networks can predict mortality from 12-lead electrocardiogram voltage datacited by 21
  9. 2018Detecting and interpreting myocardial infarction using fully convolutional neural networkscited by 19
  10. 2018Automated and Interpretable Patient ECG Profiles for Disease Detection, Tracking, and Discoverycited by 14
  11. 2022Analysis of a Deep Learning Model for 12-Lead ECG Classification Reveals Learned Features Similar to Diagnostic Criteriacited by 11
  12. 2022Improving ECG Classification Interpretability using Saliency Mapscited by 9
  13. 2022Advancing the State-of-the-Art for ECG Analysis through Structured State Space Modelscited by 9
  14. 2020Using Deep Networks for Scientific Discovery in Physiological Signalscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 4; 2026: 4.

15 papers.

Sort:

  1. 2024Enhancing clinical decision support with physiological waveforms -- a multimodal benchmark in emergency carecited by 15
  2. 2025Generalizable deep learning for photoplethysmography-based blood pressure estimation -- A Benchmarking Studycited by 9
  3. 2025Machine-learning for photoplethysmography analysis: Benchmarking feature, image, and signal-based approachescited by 8
  4. 2023Using explainable AI to investigate electrocardiogram changes during healthy aging -- from expert features to raw signalscited by 7
  5. 2024Estimation of Cardiac and Non-cardiac Diagnosis from Electrocardiogram Featurescited by 5
  6. 2024Abnormality Prediction and Forecasting of Laboratory Values from Electrocardiogram Signals Using Multimodal Deep Learningcited by 5
  7. 2023Glocal Explanations of Expected Goal Models in Soccercited by 4
  8. 2024Explaining Time Series Classification Predictions via Causal Attributionscited by 4
  9. 2025Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Datacited by 2
  10. 2023Prospects for AI-Enhanced ECG as a Unified Screening Tool for Cardiac and Non-Cardiac Conditions -- An Explorative Study in Emergency Carecited by 1
  11. 2026Deriving Health Metrics from the Photoplethysmogram: Benchmarks and Insights from MIMIC-III-Ext-PPGcited by 1
  12. 2025AICRN: Attention-Integrated Convolutional Residual Network for Interpretable Electrocardiogram Analysiscited by 0
3 more
  1. 2026Associations between echocardiographic traits and AI-ECG predictions of heart failurecited by 0
  2. 2026MSAIC-Net: A Multi-Scale Attention and Imbalance-Aware Contrastive Network for ECG-Based Myocardial Substrate Abnormality Detectioncited by 0
  3. 2026Beyond Local Inspection: Global, Guideline-Grounded Evaluation of Post-hoc XAI Methods for ECG Classificationcited by 0