My research addresses the challenges of applying machine learning and natural language processing to healthcare. I work to develop tools that can augment clinicians and patients by helping them quickly find and interpret abundant medical data. My work is motivated by two core questions: (1) How do we develop generalizable models that can learn with limited annotated data? and (2) How can we design trustworthy human-in-the-loop tools that augment clinician decision making?

I am currently a postdoctoral fellow at Brigham and Women’s Hospital and Harvard Medical School (HMS) where I am working to deploy ML models within the Mass General Brigham healthcare system. I completed my PhD in the Health Science & Technology (HST) program at MIT & HMS, co-advised by Zak Kohane and Pete Szolovits. During my PhD, I created ClinicalBERT, a language model trained on electronic health records that has millions of downloads on HuggingFace, and developed SHEPHERD, a graph neural network approach for the diagnosis of patients with rare genetic diseases in the Undiagnosed Disease Network.