Jean Feng

Jean Feng is an Associate Professor in the Department of Epidemiology and Biostatistics at the University of California, San Francisco (UCSF) School of Medicine. She is also affiliated with the UCSF-UC Berkeley Joint Program in Computational Precision Health and serves as a principal investigator at the UCSF-Stanford Center of Excellence in Regulatory Science and Innovation (CERSI). Additionally, she is the data science lead on the PROSPECT team, the digital innovation taskforce for the Zuckerberg San Francisco General Hospital.

Education:

• BS and MS in Computer Science from Stanford University (2013)
• MS and PhD in Biostatistics from University of Washington (2020)

Jean Feng's research focuses on the interpretability, reliability, and regulation of machine learning algorithms in healthcare. Her recent projects include fairness auditing, performance monitoring, and safe updating of ML algorithms. Her methodological expertise spans high-dimensional statistics, multiple hypothesis testing, causal inference, semiparametric theory, deep learning, and generative AI. Prior to her academic career, she worked as a software engineer at Coursera.

Her publication trends reveal a strong emphasis on applying machine learning to clinical prediction problems across various medical specialties. Her work frequently involves developing and validating risk prediction models for surgical outcomes, cancer treatment responses, and patient monitoring. A significant portion of her research addresses the methodological challenges of implementing and monitoring AI systems in clinical settings, reflecting her interest in regulatory science for healthcare AI.

Grants and Collaborations:

• Principal Investigator on PCORI-funded project studying robustness of LLMs in healthcare
• Co-Principal Investigator on UCSF-Stanford CERSI grant for "Safe algorithmic change protocols for modifications to AI/ML-based Software as a Medical Device"
• Collaborates with regulatory bodies including the US FDA and Korea MFDS

Dr. Feng actively contributes to the development of standards for clinical AI monitoring systems. Her lab has grown to include postdoctoral researchers like Harvineet Singh and data scientists like Avni Kothari. She regularly teaches machine learning courses, including the Columbia ML bootcamp with Noah Simon and Cody Chiuzan.

Her leadership in the PROSPECT Lab focuses on creating diagnostic tools for ML-based clinical decision support systems, with particular attention to the challenges of implementing AI in safety-net hospital settings where she serves as data science lead.