Quantifying Explainable AI-introduced signal noise on ECG data with Spectral Entropy

2026-06-23

AI Summary

This work addresses the challenge that explanation methods in explainable artificial intelligence (XAI) often introduce signal noise in medical applications, thereby obscuring the true decision-making basis of models. To tackle this issue, the study proposes spectral entropy as a novel, objective metric to quantify the noise induced by XAI techniques on electrocardiogram (ECG) signals. Leveraging post-hoc explanation methods such as Grad-CAM and Integrated Gradients, the approach is evaluated within the context of arrhythmia classification. Experimental results demonstrate that spectral entropy effectively identifies and measures the interference introduced by XAI, offering a new paradigm for enhancing the fidelity and trustworthiness of explanations generated by deep learning models in clinical decision-making.

Abstract

Explainability techniques are used to assess the output of various deep learning models. This is especially true in healthcare, where models need to be trusted and decisions justified. Explainability (XAI) tools use heuristics which often add signal noise to the explanation "core". It is not always obvious what is signal from the model and what is noise from the XAI. We propose the use of spectral entropy as a measure of noise in XAI output. We demonstrate its usefulness in the context of classifying arrhythmias in an ECG dataset with different post hoc explainability techniques.

Problem

• Explainable AI
• signal noise
• ECG
• spectral entropy
• arrhythmia classification

Innovation

• Spectral Entropy
• Explainable AI
• Signal Noise
• ECG
• Arrhythmia Classification