Fei Jiang, PhD, MS, is an Associate Professor in biostatistics at the University of California, San Francisco. Her expertise lies in the field of machine/statistical learning methodologies and their applications to the health domain. As a theoretical statistician, she has developed fundamental tools for analyzing various types of data in the medical field. Some of the highlights include: a) change point detection – she developed a Bayesian method to detect change points in medical device signals, b) functional data analysis – she created an unsupervised and supervised learning framework to uncover the relationship between continuous blood pressure measurement and recurrent stroke risk, c) high-dimensional data analysis – she designed a novel pipeline to extract important genetic variations from massive genomics data, and d) clinical trial design – she applied reinforcement learning to design a clinical trial that preserves error rates and reduces required sample sizes.

These tools have been utilized in health studies, such as COHORT, BOSS, and VALANT, generating new insights into disease pathologies and treatment effects. The related computational programs are publicly available for health professionals to use. Her efforts have resulted in high-quality statistical (JASA, Biometrika, AOS, etc.) and computational publications (NIPS, TKDD), which focus on addressing practical problems in the medical domain. Her work has been presented at major national and international statistical and machine learning conferences, as well as to the Hong Kong government and AI conferences. Her current main research area is in image data analysis, and she has developed a novel algorithm to extract dynamic functional connectivity from both fMRI and Magnetoencephalography data, which has been published in Neuroimage.

Dr. Jiang will serve as the chief scientist of the company, focusing on algorithm development and testing, experimental design, and implementation.