Development of phenotype algorithms using electronic medical records and incorporating natural language processing

Liao, KatherineCai, TianxiSavova, Guergana KMurphy, ShawnKarlson, ElizabethAnanthakrishnan, AshwinGainer, Vivian SShaw, StanleyXia, ZongqiSzolovits, PeterChurchill, SusanneKohane, Isaac2016-02-012015Liao, K. P., T. Cai, G. K. Savova, S. N. Murphy, E. W. Karlson, A. N. Ananthakrishnan, V. S. Gainer, et al. 2015. “Development of phenotype algorithms using electronic medical records and incorporating natural language processing.” BMJ : British Medical Journal 350 (1): h1885. doi:10.1136/bmj.h1885. http://dx.doi.org/10.1136/bmj.h1885.0959-8138http://nrs.harvard.edu/urn-3:HUL.InstRepos:24984054Electronic medical records are emerging as a major source of data for clinical and translational research studies, although phenotypes of interest need to be accurately defined first. This article provides an overview of how to develop a phenotype algorithm from electronic medical records, incorporating modern informatics and biostatistics methods.en-USDevelopment of phenotype algorithms using electronic medical records and incorporating natural language processingJournal Article2016-02-0110.1136/bmj.h1885