Natural language processing as an alternative to manual reporting of colonoscopy quality metrics

• Published in: Gastrointestinal endoscopy Vol. 82; no. 3; pp. 512 - 519
• Main Authors: Raju, Gottumukkala S., MD, FASGE, Lum, Phillip J., BS, Slack, Rebecca S., MS, Thirumurthi, Selvi, MD, Lynch, Patrick M., MD, Miller, Ethan, MD, Weston, Brian R., MD, Davila, Marta L., MD, FASGE, Bhutani, Manoop S., MD, FASGE, Shafi, Mehnaz A., MD, Bresalier, Robert S., MD, Dekovich, Alexander A., MD, Lee, Jeffrey H., MD, MPH, FASGE, Guha, Sushovan, MD, PhD, Pande, Mala, PhD, MPH, Blechacz, Boris, MD, PhD, Rashid, Asif, MD, PhD, Routbort, Mark, MD, PhD, Shuttlesworth, Gladis, PhD, MBA, Mishra, Lopa, MD, Stroehlein, John R., MD, FASGE, Ross, William A., MD, MBA, FASGE
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.09.2015
• Subjects: Adenoma - diagnosis; Automatic Data Processing - methods; Colonic Neoplasms - diagnosis; Colonoscopy - standards; Documentation; Early Detection of Cancer; Female; Gastroenterology and Hepatology; Humans; Male; Natural Language Processing; Quality Indicators, Health Care; SSA; adenoma detection rate; NLP; natural language processing; CAADRR; sessile serrated adenoma; MRN; medical record number; computer application for ADR reporting; ADR
• ISSN: 0016-5107; 1097-6779
• DOI: 10.1016/j.gie.2015.01.049

Background and Aims The adenoma detection rate (ADR) is a quality metric tied to interval colon cancer occurrence. However, manual extraction of data to calculate and track the ADR in clinical practice is labor-intensive. To overcome this difficulty, we developed a natural language processing (NLP) method to identify adenomas and sessile serrated adenomas (SSAs) in patients undergoing their first screening colonoscopy. We compared the NLP-generated results with that of manual data extraction to test the accuracy of NLP and report on colonoscopy quality metrics using NLP. Methods Identification of screening colonoscopies using NLP was compared with that using the manual method for 12,748 patients who underwent colonoscopies from July 2010 to February 2013. Also, identification of adenomas and SSAs using NLP was compared with that using the manual method with 2259 matched patient records. Colonoscopy ADRs using these methods were generated for each physician. Results NLP correctly identified 91.3% of the screening examinations, whereas the manual method identified 87.8% of them. Both the manual method and NLP correctly identified examinations of patients with adenomas and SSAs in the matched records almost perfectly. Both NLP and the manual method produced comparable values for ADRs for each endoscopist and for the group as a whole. Conclusions NLP can correctly identify screening colonoscopies, accurately identify adenomas and SSAs in a pathology database, and provide real-time quality metrics for colonoscopy.