UC Berkeley researchers led by Emma Pierson (EECS) and Ziad Obermeyer (Public Health) have been awarded $1.7 million through Google.org Impact Challenge: AI for Science. The research grant will support advancements in medical discovery using AI interpretability and agentic AI techniques.
UC Berkeley is one of 17 organizations selected globally from more than 3,000 applicants across 30 countries to share a total of $36 million in funding.
Pierson and Obermeyer’s work aims to establish a general framework for medical discovery by using interpretability and agentic AI techniques to translate complex foundation model representations into human-readable, physiologically grounded concepts across cardiology and oncology. This focus breaks the barrier between the opaque predictions and safety risks of today’s medical AI models and the potentially transformative biomedical knowledge that remains inaccessible and unusable by clinicians to improve patient care.
“We’re at an extraordinary moment for science, as advances in AI open up new possibilities for discovery that were difficult to imagine just a few years ago,” said Leslie Yeh, director of scientific progress at Google.org. “UC Berkeley is bringing together AI and deep scientific expertise in ambitious, creative ways to address some of humanity’s most important questions. We’re honored to support their work as they apply AI to interpret medical foundation models to push the boundaries of scientific discovery and turn breakthrough ideas into real-world impact.”