Foundation model for wearable health data trained on 5M participants

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

IMPACT Enables label-efficient few-shot learning for personalized health insights from wearable data.

RANK_REASON The cluster contains an academic paper detailing a new foundation model for wearable health data. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Girish Narayanswamy

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →