Disentangling Acoustic Cues in Alzheimer's Pathology and Perception: The Roles of Language and Gender
2026-07-27 • Sound
SoundMachine Learning
AI summaryⓘ
The authors studied how AI detects Alzheimer's Disease using voice clues and whether these clues match what humans notice when listening. They looked at speakers of Mandarin and Greek, both men and women. They found that AI and human judgments align well for Mandarin speakers and women, but not for Greek speakers and men, where AI struggled. This means AI explanations that work overall might miss important differences for specific groups, suggesting the need for tailored checks to make AI fairer in clinical use.
Alzheimer's Diseaseacoustic biomarkersclinical AISHAPpathological markershuman perceptual scoresMandarinGreekgender differencesexplainable AI (XAI)
Authors
Liu He, Yuanchao Li, Yin-Long Liu, Rui Feng, Yiming Wang, Jiaxin Chen, Yizhe Wang, Jiahong Yuan
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.