Evaluating the Usefulness of Non-Diagnostic Speech Data for Developing Parkinson's Disease Classifiers

TL;DR

This study assesses whether speech data not originally designed for diagnosis can effectively be used to develop Parkinson's disease classifiers, highlighting the potential of non-diagnostic speech datasets for PD detection.

Contribution

It demonstrates that non-diagnostic speech datasets like Turn-Taking can be as useful as diagnostic datasets for PD classification and analyzes factors influencing model performance.

Findings

Turn-Taking dataset is comparable to PC-GITA for PD classification.

Balancing gender and participant status improves model accuracy.

Models trained on TT generalize better to PC-GITA than vice versa.

Abstract

Speech-based Parkinson's disease (PD) detection has gained attention for its automated, cost-effective, and non-intrusive nature. As research studies usually rely on data from diagnostic-oriented speech tasks, this work explores the feasibility of diagnosing PD on the basis of speech data not originally intended for diagnostic purposes, using the Turn-Taking (TT) dataset. Our findings indicate that TT can be as useful as diagnostic-oriented PD datasets like PC-GITA. We also investigate which specific dataset characteristics impact PD classification performance. The results show that concatenating audio recordings and balancing participants' gender and status distributions can be beneficial. Cross-dataset evaluation reveals that models trained on PC-GITA generalize poorly to TT, whereas models trained on TT perform better on PC-GITA. Furthermore, we provide insights into the high variability across folds, which is mainly due to large differences in individual speaker performance.