Hi! I am a postdoc at Cornell, working with Emma Pierson and Jenna Wiens. I completed my Ph.D. in the Clinical and Applied Machine Learning group at MIT, where I was lucky to be advised by John Guttag. Before, I was at MIT for undergrad, where I majored in computer science with a concentration in South Asian studies.

I work on machine learning for healthcare. My current research (often) falls into one or more of these categories:

Measuring human behavior in health datasets
Human behavior shapes the health data we use to train machine learning systems; how can we use machine learning to measure these effects? What can these models tell us about how care is currently delivered?
    > How can we measure the extent to which diseases are underdiagnosed in different patient subgroups? (NWH 2024)
    > How can we measure different patterns of health access? (under review)
    > How can do financial incentives shape treatment decisions? (in progress)
Learning in the absence of large, labeled datasets
Current approaches to updating, evaluating, and selecting models rely on a scarce resource: labeled data. How can we use alternate sources of supervision as a supplement to labeled data in post-training decision making?
    > How can we use label-preserving transformations to update models to be more accurate and robust? (ICCV 2021)
    > How can we use user-specified criteria to facilitate semantically-grounded, context-specific evaluation? (CHI 23)
    > How can we use unlabeled data to evaluate classifiers? (under review)
Health equity
Can we use AI to characterize and mitigate persistent health inequities? I (and many of my co-authors) would say yes! I am especially committed to translating advances in machine learning to women's health.
    > What disparities might we miss without access to granular race data? (MLHC 2023)
    > What features are important when modeling fertility? (SR 2023)
    > How can we better measure the prevalence of intimate partner violence? (NWH 2024)
    > What new opportunities in health equity do large language models enable? (NEJM AI 2025)

Sometimes I describe my interests as “everything but model training”. This is because 1. I am impatient and 2. I believe there’s a lot to gain by studying data curation and deployment.