Hoifung Poon, General Manager, Microsoft Health Futures, introduces an agenda in precision health, utilizing generative AI to pretrain high-fidelity patient embeddings from multimodal, longitudinal patient journeys. This approach unlocks population-scale real-world evidence, optimizing clinical care and accelerating biomedical discovery.

Multimodal Generative AI: www.microsoft.com/en-us/research/articles/multimod…
GigaPath (Nature article): www.nature.com/articles/s41586-024-07441-w
BiomedParse (Nature article): www.nature.com/articles/s41592-024-02499-w
LLaVA-Med Paper: proceedings.neurips.cc/paper_files/paper/2023/file…
Microsoft Health Futures: www.microsoft.com/en-us/research/lab/microsoft-hea…
Unimodal pretraining on arXiv: arxiv.org/abs/2311.16452
Comprehensive genomic profiling Providence blog: blog.providence.org/national-news/comprehensive-ge…
Azure Health AI model catalog announcement: techcommunity.microsoft.com/blog/aiplatformblog/an…

This session aired on February 25, 2025, at Microsoft Research Forum, Episode 5.

Register for the series: aka.ms/registerresearchforumYTe5

Continue watching episode 5: aka.ms/researchforumYTe5
Explore all previous episodes: aka.ms/researchforumYTplaylist