Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking
This addresses a specific confounding issue in medical AI for early Alzheimer's screening, but it is incremental as it builds on existing transformer-based methods.
The paper tackled gender confounding in speech-based dementia detection by proposing weight masking methods to isolate and ablate gender-related weights in transformer models, resulting in a deconfounded classifier with slightly reduced detection performance.
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.