A personal health large language model for sleep and fitness coaching

Although large language models (LLMs) show promise for clinical healthcare applications, their utility for personalized health monitoring using wearable device data remains underexplored. Here we introduce the Personal Health Large Language Model (PH-LLM), designed for applications in sleep and fitness. PH-LLM is a version of the Gemini LLM that was finetuned for text understanding and reasoning when applied to aggregated daily-resolution numerical sensor data. We created three benchmark datasets to assess multiple complementary aspects of sleep and fitness: expert domain knowledge, generation of personalized insights and recommendations and prediction of self-reported sleep quality from longitudinal data. PH-LLM achieved scores that exceeded a sample of human experts on multiple-choice examinations in sleep medicine (79% versus 76%) and fitness (88% versus 71%). In a comprehensive evaluation involving 857 real-world case studies, PH-LLM performed similarly to human experts for fitness-related tasks and improved over the base Gemini model in providing personalized sleep insights. Finally, PH-LLM effectively predicted self-reported sleep quality using a multimodal encoding of wearable sensor data, further demonstrating its ability to effectively contextualize wearable modalities. This work highlights the potential of LLMs to revolutionize personal health monitoring via tailored insights and predictions from wearable data and provides datasets, rubrics and benchmark performance to further accelerate personal health-related LLM research.

Authors

Institutions

Publication Details

Journal
Nature Medicine
Published
2025-08-14
DOI
https://doi.org/10.1038/s41591-025-03888-0
Citations
22
Primary Topic
Sleep and related disorders
Type
article
Field-Weighted Citation Impact
46.60
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A personal health large language model for sleep and fitness coaching

Shravya Shetty, Logan Douglas Schneider, Jameson K. Rogers, Cory Y. McLean et al.
22 citations
Nature Medicine
Sleep and related disorders
46.60
article

A personal health large language model for sleep and fitness coaching

Shravya Shetty, Logan Douglas Schneider, Jameson K. Rogers, Cory Y. McLean, Tim Althoff, Nicholas A. Furlotte, Shwetak Patel, Anastasiya Belyaeva, John Hernandez, Conor Heneghan, Yojan Patel, Yossi Matias, Greg S. Corrado, Roy Lee, Yun Liu, Allen Jiang, Chace Lee, Justin Cosentino, Zhun Yang, Xin Liu, Ryan G. Gomes, Cathy Speed, Erik Schenck, Daniel McDuff, Jian Cui, Shruthi Prabhakara, Jeffrey Xu Yu, Javier Perez, Jiening Zhan, Mark Malhotra, Shyam Tailor, Leor Stern, Megan Walker, Robby Bryant
article en
22 citations

Abstract

Although large language models (LLMs) show promise for clinical healthcare applications, their utility for personalized health monitoring using wearable device data remains underexplored. Here we introduce the Personal Health Large Language Model (PH-LLM), designed for applications in sleep and fitness. PH-LLM is a version of the Gemini LLM that was finetuned for text understanding and reasoning when applied to aggregated daily-resolution numerical sensor data. We created three benchmark datasets to assess multiple complementary aspects of sleep and fitness: expert domain knowledge, generation of personalized insights and recommendations and prediction of self-reported sleep quality from longitudinal data. PH-LLM achieved scores that exceeded a sample of human experts on multiple-choice examinations in sleep medicine (79% versus 76%) and fitness (88% versus 71%). In a comprehensive evaluation involving 857 real-world case studies, PH-LLM performed similarly to human experts for fitness-related tasks and improved over the base Gemini model in providing personalized sleep insights. Finally, PH-LLM effectively predicted self-reported sleep quality using a multimodal encoding of wearable sensor data, further demonstrating its ability to effectively contextualize wearable modalities. This work highlights the potential of LLMs to revolutionize personal health monitoring via tailored insights and predictions from wearable data and provides datasets, rubrics and benchmark performance to further accelerate personal health-related LLM research.

Nature MedicineVol. 31(10)
Google (United States) (US)
Openalex Percentile: Top 0%
Sleep and related disorders
46.60
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.