My research focuses on identifying the optimal strategies for cancer prevention, detection, and treatment. Many important decisions about cancer control must be made in the absence of evidence from randomized trials, which may be impractical or too lengthy to provide a timely answer. In these cases, I apply advanced causal inference methods to large observational databases (e.g., electronic health records) to provide the best available evidence to inform clinical decision-making and future trial design. I am particularly interested in the intersection between causal inference and machine learning. I teach clinical data science at the Harvard Medical School and causal inference methodology at the Harvard T.H. Chan School of Public Health.
- Body fat distribution on computed tomography imaging and prostate cancer risk and mortality in the AGES-Reykjavik study
- Guideline-Based Physical Activity and Survival Among US Men With Nonmetastatic Prostate Cancer
- Alcohol Intake and Risk of Lethal Prostate Cancer in the Health Professionals Follow-Up Study
- Metabolic Factors and Prostate Cancer Risk
- Midlife metabolic factors and prostate cancer risk in later life
- Skin cancer interventions across the cancer control continuum: Review of technology, environment, and theory