UniCoMTE: A Universal Counterfactual Framework for Explaining Time-Series Classifiers on ECG Data

TL;DR

UniCoMTE is a versatile, model-agnostic framework that generates clear, stable, and clinically relevant counterfactual explanations for ECG time series classifiers, improving interpretability and trust in healthcare AI applications.

Contribution

We propose UniCoMTE, a novel universal counterfactual explanation framework for multivariate time series classifiers that works directly on raw data and outperforms existing interpretability methods.

Findings

Produces concise, stable explanations that align with human understanding.

Outperforms LIME and SHAP in clarity and generalizability.

Clinically useful explanations validated by medical experts.

Abstract

Machine learning models, particularly deep neural networks, have demonstrated strong performance in classifying complex time series data. However, their black-box nature limits trust and adoption, especially in high-stakes domains such as healthcare. To address this challenge, we introduce UniCoMTE, a model-agnostic framework for generating counterfactual explanations for multivariate time series classifiers. The framework identifies temporal features that most heavily influence a model's prediction by modifying the input sample and assessing its impact on the model's prediction. UniCoMTE is compatible with a wide range of model architectures and operates directly on raw time series inputs. In this study, we evaluate UniCoMTE's explanations on a time series ECG classifier. We quantify explanation quality by comparing our explanations' comprehensibility to comprehensibility of established techniques (LIME and SHAP) and assessing their generalizability to similar samples. Furthermore, clinical utility is assessed through a questionnaire completed by medical experts who review counterfactual explanations presented alongside original ECG samples. Results show that our approach produces concise, stable, and human-aligned explanations that outperform existing methods in both clarity and applicability. By linking model predictions to meaningful signal patterns, the framework advances the interpretability of deep learning models for real-world time series applications.