Transforming Wearable Data into Personal Health Insights using Large Language Model Agents
This work addresses the problem of making wearable data analysis accessible for individuals to improve behavioral health, representing a novel application of LLM agents in this domain.
The paper tackles the challenge of deriving personalized insights from wearable tracker data by introducing the Personal Health Insights Agent (PHIA), which uses LLM agents with multistep reasoning and code generation, achieving 84% accuracy on objective questions and 83% favorable ratings on open-ended ones in human evaluations.
Deriving personalized insights from popular wearable trackers requires complex numerical reasoning that challenges standard LLMs, necessitating tool-based approaches like code generation. Large language model (LLM) agents present a promising yet largely untapped solution for this analysis at scale. We introduce the Personal Health Insights Agent (PHIA), a system leveraging multistep reasoning with code generation and information retrieval to analyze and interpret behavioral health data. To test its capabilities, we create and share two benchmark datasets with over 4000 health insights questions. A 650-hour human expert evaluation shows that PHIA significantly outperforms a strong code generation baseline, achieving 84% accuracy on objective, numerical questions and, for open-ended ones, earning 83% favorable ratings while being twice as likely to achieve the highest quality rating. This work can advance behavioral health by empowering individuals to understand their data, enabling a new era of accessible, personalized, and data-driven wellness for the wider population.