Researchers have developed OAK-Mind, a novel pipeline that uses multi-agent large language models (LLMs) to infer mental health changes from passive sensing data without requiring task-specific training. This system analyzes behavioral data from wearable and smartphone sensors, organizing it into dimensions like sleep, activity, and mobility. Specialized agents, grounded in mental health literature, interpret longitudinal behavioral shifts and synthesize their findings with questionnaire-based symptom ratings to provide human-readable rationales. OAK-Mind demonstrates performance comparable to or better than supervised baselines, highlighting the potential of knowledge-grounded, multi-agent LLMs for training-free mental health inference. AI
IMPACT This research demonstrates a novel approach for leveraging LLMs in healthcare, potentially enabling more accessible and continuous mental health monitoring.
RANK_REASON This is a research paper detailing a new methodology for mental health inference using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]
- arXiv
- large-language models
- multi-agent system
- OAK-Mind
- Smartphone Sensors for Health Monitoring and Diagnosis.
- Wearable Sensors
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →