Researchers have developed a method using Large Language Models (LLMs) to assess dementia and depression severity from clinical interview transcripts. The study compared three LLMs—Mistral 3.1, DeepHermes, and Qwen3—using both zero-shot prediction and LLM-based feature extraction for Support Vector Regression. Results indicated that LLMs are effective for predicting depression severity directly, while dementia assessment improved significantly with structured feature extraction, achieving up to a 35% reduction in errors compared to zero-shot methods. The use of pause-enriched transcripts proved competitive with human transcriptions, paving the way for automated screening pipelines. AI
IMPACT LLMs show promise in automating neuropsychiatric assessments, potentially improving early detection and differential diagnosis of dementia and depression.
RANK_REASON The cluster contains an academic paper detailing research findings on the application of LLMs for medical assessment.
- arXiv
- DeepHermes
- Global Depression Scale (GDS-D)
- Global Deterioration Scale (GDS)
- Hugging Face
- Mistral 3.1
- Qwen3
- Support Vector Regression
- Large Language Models
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
