Research

I co-direct the Inference Lab, a research group in the MGH Vincent Department of Obstetrics and Gynecology that works to improve health care delivery in obstetrics and gynecology. We focus on actionable research that can improve outcomes, increase value, and address inequity in pregnancy care, family planning, fertility, benign disorders of the female reproductive tract, and gynecologic cancers.

In my observational research, I use analytical approaches that can, sometimes, overcome unmeasured confounding by identifying natural experiments in health care delivery. Specifically, I am interested in how focusing on the variability of treatments across time, space, and provider can help to estimate treatment effects and overcome treatment selection bias. I use methods like difference-in-differences, instrumental variables analysis, interrupted time series, and regression discontinuity designs to generate evidence about the causal effects of cancer treatments on survival, treatment-related toxicity, and medical costs. As a surgeon, oncologist, and gynecologist, I am especially interested in surgical care, cancer care delivery, and women's health.

I also have an interest in predictive modeling that can help improve women's health. Our group utilizes machine learning and AI methods to develop models that can help generate personalized predictions of patient outcomes.

By generating credible clinical evidence from observational data, I seek to help patients and clinicians make better and more informed treatment decisions.