Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908395915706368 |
|---|---|
| author | Sheng, Zhecheng Ding, Xiruo Hur, Brian Li, Changye Cohen, Trevor Pakhomov, Serguei |
| author_facet | Sheng, Zhecheng Ding, Xiruo Hur, Brian Li, Changye Cohen, Trevor Pakhomov, Serguei |
| contents | Deep transformer models have been used to detect linguistic anomalies in patient transcripts for early Alzheimer's disease (AD) screening. While pre-trained neural language models (LMs) fine-tuned on AD transcripts perform well, little research has explored the effects of the gender of the speakers represented by these transcripts. This work addresses gender confounding in dementia detection and proposes two methods: the $\textit{Extended Confounding Filter}$ and the $\textit{Dual Filter}$, which isolate and ablate weights associated with gender. We evaluate these methods on dementia datasets with first-person narratives from patients with cognitive impairment and healthy controls. Our results show transformer models tend to overfit to training data distributions. Disrupting gender-related weights results in a deconfounded dementia classifier, with the trade-off of slightly reduced dementia detection performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05610 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking Sheng, Zhecheng Ding, Xiruo Hur, Brian Li, Changye Cohen, Trevor Pakhomov, Serguei Computation and Language Deep transformer models have been used to detect linguistic anomalies in patient transcripts for early Alzheimer's disease (AD) screening. While pre-trained neural language models (LMs) fine-tuned on AD transcripts perform well, little research has explored the effects of the gender of the speakers represented by these transcripts. This work addresses gender confounding in dementia detection and proposes two methods: the $\textit{Extended Confounding Filter}$ and the $\textit{Dual Filter}$, which isolate and ablate weights associated with gender. We evaluate these methods on dementia datasets with first-person narratives from patients with cognitive impairment and healthy controls. Our results show transformer models tend to overfit to training data distributions. Disrupting gender-related weights results in a deconfounded dementia classifier, with the trade-off of slightly reduced dementia detection performance. |
| title | Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.05610 |