analiza aiqbench
This research addresses a critical nuance in speech-based Alzheimer's detection by modeling within-class variation, where patients with the same diagnosis exhibit varying degrees of cognitive impairment. The authors propose Soft Target Distillation and Instance-level Re-balancing to generate sample-specific probability scores that better align with independent clinical assessments. These methods offer a robust framework for improving binary classification performance in medical AI applications involving heterogeneous data distributions.
On the Within-class Variation Issue in Alzheimer's Disease Detection
arXiv:2409.16322v4 Announce Type: replace-cross 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.
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
Text integral sub licența deschisă a publicației · 170 cuvinte
Subiecte conexe
News Archive 2026
Quantum Computing Report · 25 iul. 2026
I Did This Without Your Knowledge
LessWrong · 17 oct. 2026
Forbes Asia 100 To Watch 2026
forbes.com · 24 aug. 2026
GraM-Diff: A Unified Graph-Mamba Diffusion Framework for EEG-Based Alzheimer's Disease Data Generation and Diagnosis
arXiv · 1 sept. 2026