Areas of Interest
My current research focuses on the integration of genetic information and electronic health records (EHR) to predict human health-related risk in large EHR-linked biobank datasets, such as UK biobank and Michigan Genomics Initiative (MGI) cohort. With distinct genetic variants composition among each race groups, we are calculating race-specific polygenic risk score (PRS) for different populations to identify the genetic risk. To account for the small sample size in underrepresented population, we are implementing phenotyping algorithm, using structured EHR data and unstructured clinical note, for disease outcome curation to enhance statistical power.
- M.S., Michigan State University (Bio-Statistics)