My research is focused on using methods in causal inference and machine learning and the vast amount of data available in health care to personalize and improve cancer control. 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 rigorous 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 teach clinical data science at the Harvard Medical School and causal inference methodology at the Harvard T.H. Chan School of Public Health.
- Obesity, height, and advanced prostate cancer: extending current evidence toward precision prevention
- Risk of dementia following androgen deprivation therapy for treatment of prostate cancer
- Avoidable flaws in observational analyses: an application to statins and cancer
- 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