Disentangling Acoustic Cues in Alzheimer's Pathology and Perception: The Roles of Language and Gender

2026-07-27

AI Summary

This study investigates whether acoustic cues used in AI-based speech diagnosis of Alzheimer’s disease align with human auditory perception, and examines how language (Mandarin vs. Greek) and gender modulate this alignment. By training models to predict both clinical status and human perceptual ratings, and integrating SHAP-based interpretability with statistical validation, the work reveals—for the first time—that globally interpretable AI models may obscure critical demographic disparities: strong alignment between pathological markers and human perception is observed in Mandarin speakers and females, whereas model performance for Greek speakers and males does not exceed random chance. These findings underscore the necessity of population-specific interpretability audits in clinical speech AI to ensure equitable deployment.

Abstract

Acoustic biomarkers show promise for detecting Alzheimer's Disease (AD), yet whether the cues driving diagnostic AI align with those salient to human listeners is underexplored across languages and genders, where pathological markers and perceptual strategies differ. We train models to predict clinical AD status (pathology) and human perceptual scores across Mandarin and Greek, male and female speakers. Using SHAP for interpretability and statistical models for validation, we compare feature importance by subgroup. Results reveal a context-dependent divergence: pathological-perceptual alignment is significant for Mandarin and female speakers but disappears for Greek and male speakers, where pathology models did not exceed chance; this is a failure mode that population-specific auditing surfaces. Global Explainable AI (XAI) explanations can mask critical demographic divergences, highlighting the need for population-specific explainability auditing for equitable deployment of clinical speech AI.

Problem

• Alzheimer's Disease
• acoustic biomarkers
• perceptual alignment
• language
• gender

Innovation

• acoustic biomarkers
• Alzheimer's Disease
• explainable AI
• cross-linguistic
• demographic fairness