Speech as a Biomarker for Disease Detection

TL;DR

This paper introduces an interpretable framework using reference speech and neural additive models to detect diseases like Alzheimer's and Parkinson's from speech signals, aiming to improve clinical understanding and trust.

Contribution

It proposes a novel reference interval-based approach combined with glass-box neural networks for disease detection from speech, enhancing interpretability and clinical relevance.

Findings

Effective detection of Alzheimer's and Parkinson's diseases using speech deviations.

Provides clinically meaningful explanations for model predictions.

Supports medical decision-making with interpretable results.

Abstract

Speech is a rich biomarker that encodes substantial information about the health of a speaker, and thus it has been proposed for the detection of numerous diseases, achieving promising results. However, questions remain about what the models trained for the automatic detection of these diseases are actually learning and the basis for their predictions, which can significantly impact patients' lives. This work advocates for an interpretable health model, suitable for detecting several diseases, motivated by the observation that speech-affecting disorders often have overlapping effects on speech signals. A framework is presented that first defines "reference speech" and then leverages this definition for disease detection. Reference speech is characterized through reference intervals, i.e., the typical values of clinically meaningful acoustic and linguistic features derived from a reference population. This novel approach in the field of speech as a biomarker is inspired by the use of reference intervals in clinical laboratory science. Deviations of new speakers from this reference model are quantified and used as input to detect Alzheimer's and Parkinson's disease. The classification strategy explored is based on Neural Additive Models, a type of glass-box neural network, which enables interpretability. The proposed framework for reference speech characterization and disease detection is designed to support the medical community by providing clinically meaningful explanations that can serve as a valuable second opinion.