# Beyond Local Inspection: Global, Guideline-Grounded Evaluation of Post-hoc XAI Methods for ECG Classification

arXiv: https://arxiv.org/abs/2607.24035 · HTML: https://mlsanity.com/paper/2607.24035/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 60 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL](https://mlsanity.com/paper/2004.13701/) (2020)
- [From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation](https://mlsanity.com/paper/2206.03208/) (2022)
- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)
- [The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies](https://mlsanity.com/paper/2007.15911/) (2020)
- [General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models](https://mlsanity.com/paper/2007.04131/) (2020)
- [Towards a Rigorous Evaluation of XAI Methods on Time Series](https://mlsanity.com/paper/1909.07082/) (2019)
- [Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values](https://mlsanity.com/paper/1810.03307/) (2018)
- [A Network Perspective on Stratification of Multi-Label Data](https://mlsanity.com/paper/1704.08756/) (2017)
- [Diffusion-based Conditional ECG Generation with Structured State Space Models](https://mlsanity.com/paper/2301.08227/) (2023)
- [Detecting and interpreting myocardial infarction using fully convolutional neural networks](https://mlsanity.com/paper/1806.07385/) (2018)
- [Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery](https://mlsanity.com/paper/2305.17043/) (2023)
- [Analysis of a Deep Learning Model for 12-Lead ECG Classification Reveals Learned Features Similar to Diagnostic Criteria](https://mlsanity.com/paper/2211.01738/) (2022)
- [A Conceptual Framework for Establishing Trust in Real World Intelligent Systems](https://mlsanity.com/paper/2104.05432/) (2021)

## Abstract (arXiv)

Explainable AI (XAI) is used to assess whether artificial intelligence models rely on meaningful patterns, yet explanations that appear plausible for individual predictions may systematically misrepresent model behavior. This is particularly problematic in medicine, where models may rely on irrelevant signal characteristics rather than disease-specific patterns without being recognizable. We address this challenge using electrocardiogram (ECG) data, for which clinical guidelines provide explicit knowledge about diagnostically relevant signal regions. We introduce a global, guideline-grounded framework that aggregates explanations across heartbeats to evaluate them against clinically defined regions of interest. Using four binary classifiers trained on PTB-XL, we assess 13 gradient-based methods across two categories of patterns: low-amplitude segments and high-amplitude QRS morphology. Our results reveal a systematic failure of methods transferred from computer vision. Their explanations often follow signal amplitude rather than clinical relevance, with mean Spearman correlations up to 0.69, leading them to overlook diagnostically decisive low-amplitude regions. For ischemia, LRP-ε assigns only 4.6% of relevance to the ST segment, compared with 63.8% for LRP-SIGN. Nine of 13 methods fall below chance for at least one condition, indicating inconsistent reliability across patterns. These findings show that global, domain-grounded evaluation can uncover systematic explanation failures not obvious from sample-level heatmaps.