On the Within-class Variation Issue in Alzheimer's Disease Detection

Abstract:Alzheimer's Disease (AD) detection commonly employs machine learning classification models to distinguish between individuals with AD and those without. Different from conventional classification tasks, AD detection involves substantial within-class variation, as individuals sharing the same diagnosis may exhibit different degrees of cognitive impairment. We formulate two aspects of this issue: within-class heterogeneity and instance-level imbalance. To model such variation under binary supervision, we estimate sample-specific AD class probabilities as sample scores and develop two corresponding methods: Soft Target Distillation (SoTD) and Instance-level Re-balancing (InRe). Experiments on the ADReSS and CU-MARVEL corpora show that the estimated scores align with independent cognitive assessments and that the proposed approaches improve AD detection performance. These findings provide insights for modeling within-class variation in speech-based AD detection.

Accepted by Interspeech 2025. This is an extended version of the conference paper

Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD); Neurons and Cognition (q-bio.NC)

arXiv:2409.16322 [eess.AS]

(or arXiv:2409.16322v4 [eess.AS] for this version)

https://doi.org/10.21437/Interspeech.2025-2751 DOI(s) linking to related resources