Speaker Profile
Ph.D., General Manager, Microsoft Health Futures
Biography
Hoifung Poon leads biomedical AI research and incubation, with the overarching goal of structuring all medical data to optimize delivery and accelerate discovery for precision health. His team and collaborators are among the first to explore generative AI in health applications. His research produces popular opensource large foundation models such as PubMedBERT, BioGPT, BiomedCLIP, LLaVAMed. He has led successful partnerships with large health providers and life science companies, creating AI systems in daily use for applications such as molecular tumor board and clinical trial matching. He has given tutorials on these topics at top AI conferences such as the ACL, the AAAI, and KDD, and his prior work has been recognized with Best Paper Awards from premier AI venues such as NAACL, EMNLP, and UAI. He received his PhD in Computer Science and Engineering from the University of Washington, specializing in machine learning and NLP.
Talk
Advancing Health at the Speed of AI
The dream of precision health is to develop a continuous learning system where new health information is instantly incorporated to optimize care delivery and accelerate biomedical discovery. I'll present our research progress on advancing generative AI for precision health, spanning biomedical large language models, multimodal learning, and causal discovery.
Session Abstract – PMWC 2024 Silicon Valley
Track Chair:
- William Oh, Mount Sinai
Patient-centric data – Real-World Evidence (RWE) and Real-World Data (RWD) - is becoming instrumental in the drug development process and for health care decisions in general. This data is not only informative for the process from discovery to new indications, clinical trial design, and drug development, it also can be of value to monitor post-marketing drug safety and for decision support in clinical practice. As the data becomes a decision driver, science companies and medical organizations are increasingly focused on leveraging RWD and RWE to not only better understand the patient populations using their drugs and the respective outcomes, but also to accelerate clinical decision support. This session will focus on the various aspects of integrating RWE and RWD to support drug development and clinical decision support.
Sessions:
- PMWC 2024 Award Ceremony
Pioneer Honoree: Atul Butte, UCSF
- Opening Talk: Pioneering the Next Decade: The Transformative Potential of Real-World Evidence/Data
- William Oh, Mount Sinai
- Strategies to Enhance Data Sharing in Medical Research (PANEL)
Chair: Craig Eagle, Guardant Health
- Paul Boutros, UCLA
- Ziad Obermeyer, UC Berkeley
- Atul Butte, UCSF
- George Sledge, Caris Life Sciences
- Erica Galvez, Manifest MedEx - Data Privacy and Security in RWE/D (PANEL)
Chair: Deven McGraw, Invitae
- Christopher Boone
- Susan Stayn, Stanford
- Using RWD to Accelerate Precision Medicine Product Development
- Mark Watson, Guardian Research Network
- Multi-Modal Datasets & RWE/D: Pioneering Tools for Accelerated Biomedical Research
Chair: Ilyana Rosenberg, Microsoft
- Charlene Son Rigby, STXBP1 Foundation
- Danielle Ciofani, Broad Institute
- Hoifung Poon, Microsoft - Leveraging RWE/D in Lupus: Using RNA Data and Predictive AI to Enhance Patient Care Decisions
Chair: Amrie Grammer, Ampel Biosolutions
- Ajay Nirula, Eli Lilly
- Pete Schafer, Bristol Myers Squibb - Accelerating Drug Development Approvals Using RWE/D (PANEL)
Chair: Maria Karasarides, BMS
- Leo Russo, Pfizer
- Eric Schadt, Ethos AI
- Ashley Brenton, Optum - CVS Health Real World Evidence – Updates and New Directions in RWE
Chair: Alexandra Berk, CVS Health
- Kate Rosenbluth, Cala Health - Regulatory Challenges in RWE (PANEL)
Chair: Susan Winkler, Reagan-Udall Center
- Mei Sheng Duh, Analysis Group
- Rachael Fones, IQVIA
