Improving Case Definition of Crohnʼs Disease and Ulcerative Colitis in Electronic Medical Records Using Natural Language Processing A Novel Informatics Approach

• Published in: Inflammatory bowel diseases Vol. 19; no. 7; pp. 1411 - 1420
• Main Authors: Ananthakrishnan, Ashwin N., Cai, Tianxi, Savova, Guergana, Cheng, Su-Chun, Chen, Pei, Perez, Raul Guzman, Gainer, Vivian S., Murphy, Shawn N., Szolovits, Peter, Xia, Zongqi, Shaw, Stanley, Churchill, Susanne, Karlson, Elizabeth W., Kohane, Isaac, Plenge, Robert M., Liao, Katherine P.
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 01.06.2013
• Subjects: Accuracy; Adult; Algorithms; Classification; Codes; Colitis, Ulcerative - diagnosis; Crohn Disease - diagnosis; Crohn's disease; Electronic Health Records; Female; Follow-Up Studies; Humans; Inflammatory bowel disease; Male; Medical Informatics; Medical records; Natural Language Processing; Prognosis; Tertiary Care Centers
• ISSN: 1078-0998; 1536-4844; 1536-4844
• DOI: 10.1097/MIB.0b013e31828133fd

Previous studies identifying patients with inflammatory bowel disease using administrative codes have yielded inconsistent results. Our objective was to develop a robust electronic medical record-based model for classification of inflammatory bowel disease leveraging the combination of codified data and information from clinical text notes using natural language processing. Using the electronic medical records of 2 large academic centers, we created data marts for Crohn's disease (CD) and ulcerative colitis (UC) comprising patients with ≥1 International Classification of Diseases, 9th edition, code for each disease. We used codified (i.e., International Classification of Diseases, 9th edition codes, electronic prescriptions) and narrative data from clinical notes to develop our classification model. Model development and validation was performed in a training set of 600 randomly selected patients for each disease with medical record review as the gold standard. Logistic regression with the adaptive LASSO penalty was used to select informative variables. We confirmed 399 CD cases (67%) in the CD training set and 378 UC cases (63%) in the UC training set. For both, a combined model including narrative and codified data had better accuracy (area under the curve for CD 0.95; UC 0.94) than models using only disease International Classification of Diseases, 9th edition codes (area under the curve 0.89 for CD; 0.86 for UC). Addition of natural language processing narrative terms to our final model resulted in classification of 6% to 12% more subjects with the same accuracy. Inclusion of narrative concepts identified using natural language processing improves the accuracy of electronic medical records case definition for CD and UC while simultaneously identifying more subjects compared with models using codified data alone.