AI Agents for Patient-Centered Care, Prevention, and Biomedical Research.
We develop computational methods for multimodal AI agents that retrieve and interpret evidence from wearable signals, electronic health records, and patient-reported experiences.
Visit our website, explore our research and publications, and meet the team.
- AI agents: Heartwood supports researcher-supervised biomedical analyses. Plainly supports patient-facing AI.
- Multimodal methods: OpenTSLM, TimeCAP, PocketTSLM, and OpenTSLMMLX connect time-series data with language models.
- Digital-health infrastructure: Grove provides modular application components. Trove supports study configuration and management.
- Studies and interventions: My Heart Counts, ENGAGE-HF, and the one sec Stanford study examine cardiovascular health, patient support, and digital wellbeing.
Browse all repositories, join our discussions, or read the contributing guidelines.
