Dr. Yilun Sun is a biostatistician who develops statistical methodologies as well as applications in missing data, causal inference, and individualized treatment regimens. His ongoing work in precision medicine aims to tailor cancer treatment decisions at multiple time points through embedding causal relationships in machine learning and integrating diverse data sources.
Dr. Sun’s research also focuses on improving the clinical utility of prediction models through developing and applying interpretable machine learning approaches.
He has extensively collaborated with clinicians and biologists on numerous early-phase oncology clinical trials design and cancer data science projects, including developing and validating risk prediction models and prognostic/predictive biomarkers.
Before coming to ÐÇ¿Õ´«Ã½, Dr. Sun spent two years as faculty in the Department of Radiation Oncology and Biostatistics at the University of Michigan, Ann Arbor.
Research Information
Research Interests
Dr. Sun’s research interests include developing robust estimation methods, including but not limited to missing data problems, causal inference, and synthesizing randomized trials with real-world data (e.g., omics, imaging data).
He has broad interest in methodologies for estimating optimal treatment rules for complex treatment (binary, continuous, multi-dimensional categorical, matrix) and various outcome types (longitudinal, binary, continuous, time-to-event, etc.).
In addition, he investigates how to quantify and harness the uncertainty in estimating individualized treatment rules and how to identify critical variables for personalized treatment rules. In addition to methodological work, he also is interested in pursuing collaborations in a wide range of applications.
Professional Memberships
Publications
Find Dr. Sun's publications here:
MyNCBI:
Google Scholar:
‪Editorial Roles:
International Journal of Radiation Oncology, Biology, Physics. Statistical Editor