I am a Ph.D. Candidate in the Computer Science department of Vanderbilt University. I am interested in inventing new methods for analyzing complex data and identifying deep links between complex concepts and raw data.

My current research work focuses on building novel machine learning models to support information retrieval from a large number of medical notes. Specifically, I developed methods to (i) extract clinical similar terms from electronic medical records (EMRs) to refine and recommend query for complex tasks, and (ii) learn from users’ behaviors and rapidly adapt to their needs for search terms. documents or medical events. I have already published the first work in Journal of Biomedical Informatics (JBI) and AMIA Summits on Translational Science Proceedings, and I am now preparing to submit the second work to JBI.

My previous research focused on doing feature engineering to identify fine-grained temporal features that associate with students’ early stage performance (e.g., drop-out) in massive open online courses (MOOCs). The work has been published in the Journal of Learning Analytics and Educational Data Mining conference.

Besides the research work, I have rich experience in developing software systems for extracting, analyzing, and visualizing complex data. I independently developed the Summit (https://www.vumc.org/hail-lab/hail-lab/), a medical note retrieval and analysis system containing multiple sub-systems to support identifying important evidence for difficult questions and revealing deep links better different types of medical data (e.g., the connections between images and text).

The system has been used to support more than ten medical researches, including Graft-versus-host disease (GVHD), diabetes, Acute Myocardial Infarction (AMI), Crohn’s disease, Cancer, student-patient-interaction analysis. The system significantly reduces the time of reviewing and labeling notes in those researches (e.g., from hours per patient to seconds per patient).