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

• Published in: BMJ (Online) Vol. 350; no. apr24 11; p. h1885
• Main Authors: Liao, Katherine P, Cai, Tianxi, Savova, Guergana K, Murphy, Shawn N, Karlson, Elizabeth W, Ananthakrishnan, Ashwin N, Gainer, Vivian S, Shaw, Stanley Y, Xia, Zongqi, Szolovits, Peter, Churchill, Susanne, Kohane, Isaac
• Format: Journal Article
• Language: English
• Published: England British Medical Journal Publishing Group 24.04.2015; BMJ Publishing Group LTD; BMJ Publishing Group Ltd
• Subjects: Accuracy; Algorithms; Codes; Computerized physician order entry; Disease; Electronic health records; Electronic Health Records - statistics & numerical data; Genotype & phenotype; Health risk assessment; Humans; Informatics; Information Storage and Retrieval; Interdisciplinary Communication; Language; Linguistics; Medical records; Multidisciplinary teams; Natural Language Processing; Patients; Phenotype; RESEARCH METHODS & REPORTING; Rheumatoid arthritis; Smoking; Translational Medical Research
• ISSN: 0959-8138; 1756-1833; 1756-1833
• DOI: 10.1136/bmj.h1885

Electronic 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.