Brief

Researchers have developed a foundation model for wearable health data, trained on over a trillion minutes of unlabeled signals from five million participants. This model demonstrates significant improvements in predicting various health outcomes, including cardiovascular, metabolic, sleep, and mental health conditions. By leveraging large-scale pretraining and LLM agents for downstream task discovery, the system enables efficient few-shot learning and supports a Personal Health Agent capable of providing relevant, context-aware, and safe responses, as validated by clinicians. AI

Researchers have developed a foundation model for wearable health data, trained on over a trillion minutes of unlabeled signals from five million participants. This model demonstrates significant improvements in performance across 35 health prediction tasks, enabling efficient few-shot learning and generative capabilities for daily metric estimation. By integrating LLM agents and a Personal Health Agent, the system provides more relevant, context-aware, and safe health insights, validated by clinician ratings. AI