Challenges and Opportunities for Large-scale Healthcare Analytic Research

Heterogeneous and large volume of Electronic Health Records (EHR) data are becoming available in many healthcare institutes, which include diagnosis, procedures, medications, lab results, clinical notes, medical images, genetic information and etc. Such EHR data from millions of patients serve as huge collective memory of doctors and patients over time. How to leverage that EHR data to help caregivers and patients to make better decisions in future? How to use these data to help clinical and pharmaceutical research?


My research focuses on developing large-scale algorithms and systems to build and deploy healthcare analytics. First, I will describe our healthcare analytic architecture, which provides an efficient framework for collaborating with various teams. Second, under this framework, I will overview various techniques and their clinical applications that we developed, which covers clinical text mining, patient representation, knowledge+data feature selection, patient similarity analytics, and patient visualization techniques. Finally, I will highlight some current/future work that I am pursuing in this area.