Reasoning-Based Approach with Chain-of-Thought for Alzheimer's Detection Using Speech and Large Language Models
This work addresses dementia diagnosis for aging populations, offering an incremental improvement in detection accuracy.
The paper tackles Alzheimer's disease detection by combining speech and language models with a Chain-of-Thought reasoning approach, achieving a 16.7% relative performance improvement over methods without CoT and claiming state-of-the-art results in CoT-based methods.
Societies worldwide are rapidly entering a super-aged era, making elderly health a pressing concern. The aging population is increasing the burden on national economies and households. Dementia cases are rising significantly with this demographic shift. Recent research using voice-based models and large language models (LLM) offers new possibilities for dementia diagnosis and treatment. Our Chain-of-Thought (CoT) reasoning method combines speech and language models. The process starts with automatic speech recognition to convert speech to text. We add a linear layer to an LLM for Alzheimer's disease (AD) and non-AD classification, using supervised fine-tuning (SFT) with CoT reasoning and cues. This approach showed an 16.7% relative performance improvement compared to methods without CoT prompt reasoning. To the best of our knowledge, our proposed method achieved state-of-the-art performance in CoT approaches.