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

• URL: http://arxiv.org/abs/2607.24035v1
• Date: Mon, 27 Jul 2026 06:16:28 GMT
• Title: Beyond Local Inspection: Global, Guideline-Grounded Evaluation of Post-hoc XAI Methods for ECG Classification
• Abstract summary: We introduce a framework that aggregates explanations across heartbeats to evaluate them against clinically defined regions of interest.<n>Our results reveal a systematic failure of methods transferred from computer vision.<n>Nine of 13 methods fall below chance for at least one condition, indicating inconsistent reliability across patterns.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• Seeing Beyond the Lesion: Disease Recognition from Reactive CNS Tissue [1.2182821723492487]
  We benchmark four pathology foundation models as frozen patch encoders within a shared attention-based learning framework.<n>We first show that coarse disease-category prediction can be reproduced largely from slide size alone.<n>Surprisingly, performance is statistically indistinguishable across all foundation-model encoders.
  arXiv  Detail & Related papers  (2026-09-02T10:02:43Z)
• SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation [1.5782980044380892]
  Current evaluation protocols for Vision-Language Models in Radiology Report Generation rely on report-level metrics that measure lexical overlap or aggregate clinical correctness.<n>We introduce SHOVIR, a benchmark for evaluating vision shortcut behavior in RRG.
  arXiv  Detail & Related papers  (2026-06-29T12:17:35Z)
• Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports [49.5225801722164]
  Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar.<n>We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance.
  arXiv  Detail & Related papers  (2026-06-17T08:10:30Z)
• Validating the Clinical Utility of CineECG 3D Reconstructions through Cross-Modal Feature Attribution [6.049628621178308]
  We propose a cross-modal method that projects feature attributions from high-performance 12-lead ECG models onto the CineECG 3D anatomical space.<n>Our study reveals that while models trained directly on CineECG signals suffer from reduced accuracy and incoherent attributions, the proposed mapping mechanism effectively recovers clinically relevant feature rankings.
  arXiv  Detail & Related papers  (2026-04-29T12:21:43Z)
• H-LDM: Hierarchical Latent Diffusion Models for Controllable and Interpretable PCG Synthesis from Clinical Metadata [7.158541967057649]
  H-LDM is a Hierarchical Latent Diffusion Model for generating clinically accurate and controllable PCG signals from structured metadata.<n>Our approach features a multi-scale VAE that learns a physiologically-disentangled latent space, separating rhythm, heart sounds, and murmurs.<n> Experiments on the PhysioNet CirCor dataset demonstrate state-the-art performance, achieving a Fréchet Audio Distance of 9.7, a 92% attribute disentanglement score, and 87.1% clinical validity confirmed by cardiologists.
  arXiv  Detail & Related papers  (2025-11-18T10:16:22Z)
• Transformer Classification of Breast Lesions: The BreastDCEDL_AMBL Benchmark Dataset and 0.92 AUC Baseline [1.9336815376402718]
  This study introduces a transformer-based framework for automated classification of breast lesions in dynamic contrast-enhanced MRI.<n>We implemented a SegFormer architecture that achieved an AUC of 0.92 for lesion-level classification, with 100% sensitivity and 67% specificity at the patient level.<n>Public release of the dataset, models, and evaluation protocols provides the first standardized benchmark for DCE-MRI lesion classification.
  arXiv  Detail & Related papers  (2025-09-30T15:58:02Z)
• Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping [80.92960114162746]
  We propose PathPT, a novel framework that exploits the potential of vision-language pathology foundation models.<n>PathPT converts WSI-level supervision into fine-grained tile-level guidance by leveraging the zero-shot capabilities of VL models.<n>Results show that PathPT consistently delivers superior performance, achieving substantial gains in subtyping accuracy and cancerous region grounding ability.
  arXiv  Detail & Related papers  (2025-08-21T18:04:41Z)
• Reflecting Topology Consistency and Abnormality via Learnable Attentions for Airway Labeling [19.269806092729468]
  airway anatomical labeling is crucial for clinicians to identify and navigate complex bronchial structures during bronchoscopy.<n>Previous methods are prone to generate inconsistent predictions.<n>This paper proposes a novel method that enhances topological consistency and improves the detection of abnormal airway branches.
  arXiv  Detail & Related papers  (2024-10-31T12:04:30Z)
• SemioLLM: Evaluating Large Language Models for Diagnostic Reasoning from Unstructured Clinical Narratives in Epilepsy [45.2233252981348]
  Large Language Models (LLMs) have been shown to encode clinical knowledge.<n>We present SemioLLM, an evaluation framework that benchmarks 6 state-of-the-art models.<n>We show that most LLMs are able to accurately and confidently generate probabilistic predictions of seizure onset zones in the brain.
  arXiv  Detail & Related papers  (2024-07-03T11:02:12Z)
• Fairness Evolution in Continual Learning for Medical Imaging [47.52603262576663]
  This study examines how bias evolves across tasks using domain-specific fairness metrics and how different CL strategies impact this evolution.<n>Our results show that Learning without Forgetting and Pseudo-Label achieve optimal classification performance, but Pseudo-Label is less biased.
  arXiv  Detail & Related papers  (2024-04-10T09:48:52Z)
• Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies [62.840338941861134]
  We propose to leverage transfer learning from large datasets annotated by radiologists, to predict the histological score available on a small annex dataset. We compare different pretraining methods, namely weakly-supervised and self-supervised ones, to improve the prediction of the cirrhosis. This method outperforms the baseline classification of the METAVIR score, reaching an AUC of 0.84 and a balanced accuracy of 0.75.
  arXiv  Detail & Related papers  (2023-02-16T17:06:23Z)
• Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features [47.45835732009979]
  Neural networks have demonstrated remarkable performance in classification and regression tasks on chest X-rays. Features attribution methods identify the importance of input features for the output prediction. We evaluate our methods using both human-centric (ground-truth-based) interpretability metrics, and human-independent feature importance metrics on NIH Chest X-ray8 and BrixIA datasets.
  arXiv  Detail & Related papers  (2021-04-01T11:42:39Z)
• Variational Knowledge Distillation for Disease Classification in Chest X-Rays [102.04931207504173]
  We propose itvariational knowledge distillation (VKD), which is a new probabilistic inference framework for disease classification based on X-rays. We demonstrate the effectiveness of our method on three public benchmark datasets with paired X-ray images and EHRs.
  arXiv  Detail & Related papers  (2021-03-19T14:13:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.