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: https://www.microsoft.com/en-us/research/articles/multimodal-generative-ai-the-next-frontier-in-precision-health/
GigaPath (Nature article): https://www.nature.com/articles/s41586-024-07441-w
BiomedParse (Nature article): https://www.nature.com/articles/s41592-024-02499-w
LLaVA-Med Paper: https://proceedings.neurips.cc/paper_files/paper/2023/file/5abcdf8ecdcacba028c6662789194572-Paper-Datasets_and_Benchmarks.pdf
Microsoft Health Futures: https://www.microsoft.com/en-us/research/lab/microsoft-health-futures/?msockid=02b405ef82956e0f3d9f10f683226f80
Unimodal pretraining on arXiv: https://arxiv.org/abs/2311.16452
Comprehensive genomic profiling Providence blog: https://blog.providence.org/national-news/comprehensive-genomic-profiling-leads-to-better-patient-outcomes-new-joint-study-says
Azure Health AI model catalog announcement: https://techcommunity.microsoft.com/blog/aiplatformblog/announcing-healthcare-ai-models-in-azure-ai-model-catalog/4282460
This session aired on February 25, 2025, at Microsoft Research Forum, Episode 5.
Register for the series: https://aka.ms/registerresearchforumYTe5
Continue watching episode 5: https://aka.ms/researchforumYTe5
Explore all previous episodes: https://aka.ms/researchforumYTplaylist