I am a Ph.D. student at Columbia'sDepartment of Biomedical Informatics studying techniques for summarization of patient information from clinical narrative using natural language processing techniques.
Trudeau is an immunological research laboratory in upstate New York that began as a sanitorium for treating tuberculosis patients in 1884. Today they are a leading research institution focusing on immune system response to various conditions including influenza, tuberlocosis and cancer.
Instead of imposing patient summaries on a physician, how can we learn from physician note-taking how to best create a patient summary in a format most comfortable and efficient for physicians?
Given a critical quality of text mining from clinical notes, can we create a better top-down patient summary from information gathered from NLP-processed clinical notes than from structured data?
Academic Publications
Van Vleck TT, Wilcox A, Stetson PD, Johnson SB, Elhadad N. Content and Structure of Clinical Problem Lists: A Corpus Analysis. Proc AMIA Annual Fall Symposium 2008. [PubMed]
Van Vleck TT, Stein DM, Stetson PD, Johnson SB. Assessing Data Relevance For Automated Generation Of A Clinical Summary. Proc AMIA Annual Fall Symposium 2007. (Nominated a finalist in AMIA Student Paper Competition) [PubMed]
Patel C, Xu H, Fan JW, Bales ME, Gilman S, Van Vleck TT. Mining Potentially Interesting Hypotheses from the Nationwide Inpatient Sample. Proc AMIA Annual Fall Symposium 2007.
Johnson SB, Bakken S, Dine D, Hyun S, Mendonça E, Morrison F, Bright T, Van Vleck T, Wrenn J, Stetson P. (2007). An Electronic Health Record based on Structured Narrative. J Am Med Inform Assoc. [PubMed]
Stetson PD, Keselman A, Rappaport D, Van Vleck T, Cooper M, Boyer A, Hripcsak G. [Abstract] Electronic Discharge Summaries. Proceedings of AIMA 2005 pg. 1121 [PubMed]
