News
Congratulations to Atul Butte and Madhumita Sushil on their recent grant award from the Chan Zuckerberg Initiative (Science in Society initiative).
The research will be on "Applying AI/LLMs to Characterize Rare Diseases and Address Diagnostic Challenges." The goal is to build LLM-based methodology to automatically identify and characterize rare disease patient cohorts from the UC-wide deidentified patient database of 8+ million patients, and reduce the diagnostic odyssey for rare diseases. The team plans to build generalizable strategies, but initiating a proof of concept with two diseases that UCSF is a center of excellence for: Hereditary Hemorrhagic Telangiectasia and cerebral cavernous malformations. They will also engage with patient foundations for both diseases to incorporate their views and disseminate findings back to them. Learn more here
Julian Hong, Travis Zack, Atul Butte et al publish on the effectiveness of proprietary and open large language models (LLMs) in detecting disease presence, location, and treatment response in…
Habibeh Ashouri Choshali, Gundolf Schenk, Sharat Israni collaborated with Harvard investigators on this longitudinal study.
Marina Sirota and Alice Tang join the podcast to share their research on how AI could be used to predict one’s risk of developing Alzheimer’s disease based on their electronic health records.
