Developing Novel Methods for Robust De-identification of Electronic Health Record Data
In the USA the HIPAA Privacy Rule restricts exchange of medical data containing protected health information (PHI) defined as any information that might be used to identify the individual(s) from whom the data were collected. However much of the data collected from hospitals for research purposes does contain PHI. The process of removing this PHI from free-text medical records is very tedious and error-prone. Existing automated de-identification software is inefficient and limited in applicability across different datasets. Hence we aim to build a modularized de-identification package that robustly de-identifies medical records in accordance with HIPAA standards and is widely applicable easy-to-use and efficient.

I’m fascinated by the intersection of computer science and medicine and am excited to work on a project that can augment the data-driven approach to healthcare research. I’ve gained experience with big data & machine learning as an intern at Google Uber and Apple and data security & privacy at NASA and Univ. of Washington so I hope to apply and enhance my skillset as I work in the Lab for Computational Physiology.