Beyond Fairness: Age-Harmless Parkinson's Detection via Voice

TL;DR

This paper introduces a novel debiasing approach using GradCAM-based feature masking and ensemble models to improve Parkinson's detection from voice data across different age groups without sacrificing accuracy.

Contribution

The study presents a new debiasing method that selectively masks age-related features and employs ensemble models to enhance detection fairness and accuracy for early-onset Parkinson's patients.

Findings

Improved detection accuracy for young PD patients.

Maintained high accuracy for elderly group.

Effective mitigation of age-related bias in voice-based PD detection.

Abstract

Parkinson's disease (PD), a neurodegenerative disorder, often manifests as speech and voice dysfunction. While utilizing voice data for PD detection has great potential in clinical applications, the widely used deep learning models currently have fairness issues regarding different ages of onset. These deep models perform well for the elderly group (age $>$ 55) but are less accurate for the young group (age $\leq$ 55). Through our investigation, the discrepancy between the elderly and the young arises due to 1) an imbalanced dataset and 2) the milder symptoms often seen in early-onset patients. However, traditional debiasing methods are impractical as they typically impair the prediction accuracy for the majority group while minimizing the discrepancy. To address this issue, we present a new debiasing method using GradCAM-based feature masking combined with ensemble models, ensuring that neither fairness nor accuracy is compromised. Specifically, the GradCAM-based feature masking selectively obscures age-related features in the input voice data while preserving essential information for PD detection. The ensemble models further improve the prediction accuracy for the minority (young group). Our approach effectively improves detection accuracy for early-onset patients without sacrificing performance for the elderly group. Additionally, we propose a two-step detection strategy for the young group, offering a practical risk assessment for potential early-onset PD patients.