Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech

TL;DR

This paper evaluates the effectiveness of various explainability methods in speech-based Parkinson's disease detection, highlighting their alignment with classifiers but limited usefulness for domain experts.

Contribution

It systematically assesses multiple interpretability techniques for PD speech models, providing insights into their faithfulness and practical utility.

Findings

Explainability maps align with classifiers but lack domain relevance

Quantitative evaluation of saliency maps reveals limited interpretability

Saliency maps often do not convey valuable clinical information

Abstract

Speech impairments in Parkinson's disease (PD) provide significant early indicators for diagnosis. While models for speech-based PD detection have shown strong performance, their interpretability remains underexplored. This study systematically evaluates several explainability methods to identify PD-specific speech features, aiming to support the development of accurate, interpretable models for clinical decision-making in PD diagnosis and monitoring. Our methodology involves (i) obtaining attributions and saliency maps using mainstream interpretability techniques, (ii) quantitatively evaluating the faithfulness of these maps and their combinations obtained via union and intersection through a range of established metrics, and (iii) assessing the information conveyed by the saliency maps for PD detection from an auxiliary classifier. Our results reveal that, while explanations are aligned with the classifier, they often fail to provide valuable information for domain experts.