Veridical Data Science for Precision Medicine: Subgroup Discovery through staDISC

St. Jude Children’s Research Hospital Danny Thomas Lecture Series


March 26, 2021
10:00am to 11:00am
Virtual Participation


BIDS Faculty Affiliate Bin Yu was invited to deliver a lecture for the prestigious "Danny Thomas Lecture Series" at St Jude Children’s Research Hospital, during which she presented her vision and framework on veridical data science. After a gap of 15 years, a major statistician delivered this lecture, which had an audience of over 250 viewers, including over 60 doctors. She presented her vision for Veridical Data Science via her PCS framework that stands for the three core principles of statistics and machine learning: Predictability, Computability, and Stability. The PCS framework aims at responsible, reliable, reproducible, and transparent data analysis and decision-making.  It consists of a workflow and documentation (in R Markdown or Jupyter Notebook) for the entire data science life cycle from problem formulation, data collection, data cleaning to modeling, results interpretation, and conclusions. She illustrated the PCS framework in action for precision medicine by presenting the recently developed methodology StaDISC that stands for the stable discovery of interpretable subgroups via calibration in causal inference. This work demonstrates the promises of the PCS framework: desirable subgroups of subjects discovered by StaDISC in one clinical trial (the VIGOR study regarding Merck’s pain-killer Vioxx against Naproxen) were validated to a good extent in the other trial (the APPROVe study regarding Vioxx against placebo). Read more about this work in these two publications: Veridical Data Science (PNAS 2020) and Stable Discovery of Interpretable Subgroups via Calibration in Causal Studies (International Statistical Review, 2020).


Bin Yu

Chancellor’s Professor of Statistics and of Electrical Engineering & Computer Sciences, UC Berkeley

Bin Yu is Chancellor’s Professor in the Departments of Statistics and of Electrical Engineering & Computer Science at the University of California at Berkeley. She is founding co-director of the Microsoft Joint Lab at Peking University on Statistics and Information Technology. Her group at Berkeley is engaged in interdisciplinary research with scientists from genomics, neuroscience, and medicine. In order to solve data problems in these domain areas, her group employs quantitative critical thinking and develops statistical and machine learning algorithms and theory. She has published more than 100 scientific papers in premier journals in statistics, machine learning, information theory, signal processing, remote sensing, neuroscience, genomics, and networks. She is a member of the U.S. National Academy of Sciences and fellow of the American Academy of Arts and Sciences.