Transforming wearable data into personal health insights using large language model agents

Преобразование данных носимых устройств в персонализированные сведения о здоровье с помощью агентов на основе больших языковых моделей
Yi Liu, Cory Y. McLean, Tim Althoff, Daniel McDuff, Shwetak Patel, Kumar Ayush, Hao-Wei Su, Naghmeh Rezaei, Mike A. Merrill, Akshay Paruchuri, Geza Kovacs, Javier Perez, Yun Liu, Erik Schenck, Nova Hammerquist, Jake Sunshine, Shyam Tailor, Kumar Ayush, Qian He, Mark Malhotra, Shwetak Patel, Jiening Zhan, Tim Althoff, Daniel McDuff, Geza Kovacs, Shyam A. Tailor, Hao-Wei Su, Xin Liu
2026-01-12

code generationinformation retrievallarge language model agentspersonalized health insightswearable health data
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. Wearable devices generate vast streams of health data, but making sense of these measurements requires complex numerical reasoning beyond the reach of conventional language models. This study introduces a large language model agent that interprets wearable data to deliver accurate, personalized health insights.
1
Across a 650-hour human expert evaluation, PHIA achieved 84% accuracy on objective numerical questions, significantly outperforming a strong code-generation baseline.
2
For open-ended questions, PHIA received 83% favorable ratings and was twice as likely as the baseline to receive the highest quality rating.
3
PHIA demonstrates the potential of LLM agents to provide accessible, personalized, data-driven insights from wearable health data.
4
The Personal Health Insights Agent (PHIA) uses multistep reasoning, code generation, and information retrieval to interpret wearable behavioral health data.
5
The study introduces and shares two benchmark datasets containing more than 4,000 health-insight questions for evaluating wearable-data analysis systems.

wearable-device behavioral health data

accurate, personalized interpretation and insight generation from wearable data through complex numerical reasoning

Publication Details
Publication Date
2026-01-12
Journal
Publisher
ISSN
Cited by
84
Access Type
Author Information
Authors
Yi Liu
Cory Y. McLean
Tim Althoff
Daniel McDuff
Shwetak Patel
Kumar Ayush
Hao-Wei Su
Naghmeh Rezaei
Mike A. Merrill
Akshay Paruchuri
Geza Kovacs
Javier Perez
Yun Liu
Erik Schenck
Nova Hammerquist
Jake Sunshine
Shyam Tailor
Kumar Ayush
Qian He
Mark Malhotra
Shwetak Patel
Jiening Zhan
Tim Althoff
Daniel McDuff
Geza Kovacs
Shyam A. Tailor
Hao-Wei Su
Xin Liu
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%