# From Prototypes to Sparse ECG Explanations: SHAP-Driven Counterfactuals for Multivariate Time-Series Multi-class Classification

arXiv: https://arxiv.org/abs/2510.19514 · HTML: https://mlsanity.com/paper/2510.19514/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [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)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019)
- [Instance-based Counterfactual Explanations for Time Series Classification](https://mlsanity.com/paper/2009.13211/) (2020)
- [Unremarkable AI: Fitting Intelligent Decision Support into Critical, Clinical Decision-Making Processes](https://mlsanity.com/paper/1904.09612/) (2019)
- [A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME](https://mlsanity.com/paper/2305.02012/) (2023)
- [WindowSHAP: An Efficient Framework for Explaining Time-series Classifiers based on Shapley Values](https://mlsanity.com/paper/2211.06507/) (2022)
- [Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI](https://mlsanity.com/paper/2301.11970/) (2023)
- [Deep Generative Models for Physiological Signals: A Systematic Literature Review](https://mlsanity.com/paper/2307.06162/) (2023)
- [Interactive Machine Learning: A State of the Art Review](https://mlsanity.com/paper/2207.06196/) (2022)
- [Securing the Digital World: Protecting smart infrastructures and digital industries with Artificial Intelligence (AI)-enabled malware and intrusion detection](https://mlsanity.com/paper/2401.01342/) (2023)
- [Rule Generation for Classification: Scalability, Interpretability, and Fairness](https://mlsanity.com/paper/2104.10751/) (2021)
- [Clinicians' Voice: Fundamental Considerations for XAI in Healthcare](https://mlsanity.com/paper/2411.04855/) (2024)
- [Operationalizing Counterfactual Metrics: Incentives, Ranking, and Information Asymmetry](https://mlsanity.com/paper/2305.14595/) (2023)
- [Interpretable ECG Analysis for Myocardial Infarction Detection through Counterfactuals](https://mlsanity.com/paper/2312.08304/) (2023)
- [ArrhythmiaVision: Resource-Conscious Deep Learning Models with Visual Explanations for ECG Arrhythmia Classification](https://mlsanity.com/paper/2505.03787/) (2025)
- [Explaining Time Series Classifiers with PHAR: Rule Extraction and Fusion from Post-hoc Attributions](https://mlsanity.com/paper/2508.01687/) (2025)

## Built on by (most cited first, 3 of 3)

- [Actionable and diverse counterfactual explanations incorporating domain knowledge and plausibility constraints](https://mlsanity.com/paper/2511.20236/) (2025)
- [Counterfactual Transition Graphs: Evaluating Cross-Class Transition Quality](https://mlsanity.com/paper/2608.23164/) (2026)
- [FCA-Guided Counterfactual Explanations for Multi-Modal Breast Cancer Diagnosis: A Framework Achieving Perfect Validity with Emergent Sparsity](https://mlsanity.com/paper/2609.20067/) (2026)

## Abstract (arXiv)

In eXplainable Artificial Intelligence (XAI), instance-based explanations for time series have gained increasing attention due to their potential for actionable and interpretable insights in domains such as healthcare. Addressing the challenges of explainability of state-of-the-art models, we propose a prototype-driven framework for generating sparse counterfactual explanations tailored to 12-lead ECG classification models. Our method employs SHAP-based thresholds to identify critical signal segments and convert them into interval rules, uses Dynamic Time Warping (DTW) and medoid clustering to extract representative prototypes, and aligns these prototypes to query R-peaks for coherence with the sample being explained. The framework generates counterfactuals that modify only 78% of the original signal while maintaining 81.3% validity across all classes and achieving 43% improvement in temporal stability. We evaluate three variants of our approach, Original, Sparse, and Aligned Sparse, with class-specific performance ranging from 98.9% validity for myocardial infarction (MI) to challenges with hypertrophy (HYP) detection (13.2%). This approach supports near realtime generation (< 1 second) of clinically valid counterfactuals and provides a foundation for interactive explanation platforms. Our findings establish design principles for physiologically-aware counterfactual explanations in AI-based diagnosis systems and outline pathways toward user-controlled explanation interfaces for clinical deployment.