Original articleClinical endoscopyApplying a natural language processing tool to electronic health records to assess performance on colonoscopy quality measures
Section snippets
Background
NLP is a field of computer science in which the computer is trained to “read” text to identify relevant data.20 C-QUAL automatically analyzes both colonoscopy and pathology reports in the electronic health record (EHR) and abstracts the necessary information (eg, indication, polyp detection, cecal intubation). It can thereby assess all the important aspects of colonoscopy quality. We tested C-QUAL by comparing it with the criterion standard of manual abstraction by a physician and found that
Methods
We conducted a cross-sectional analysis of reports from relevant colonoscopy procedures over a 2-year period in a single hospital system.
Results
A total of 24,157 reports were analyzed by using the NLP tool. Of all colonoscopies, 54.1% were performed on women and the majority of patients (59.0%) were between 50 and 69 years of age (Table 2). All 9 hospitals were in urban areas, and 4 were members of the Council of Teaching Hospitals. The number of admissions per year at the hospitals varied from 5000 to less than 10,000 (n = 2, 22.2%), 10,000 to less than 20,000 (n = 5, 55.6%), and 20,000 or more (n = 2, 22.2%) (Online Appendix Table 5
Discussion
Our results highlight the potential of NLP to measure performance on colonoscopy quality measures. Our NLP tool efficiently analyzed a large sample of colonoscopy reports. Our findings demonstrate that there is clear variation in performance, even within a highly regarded academic health care system. Across the 9 hospitals, there was almost a threefold variation in the adenoma detection rate. The variation in performance on the quality measures across physicians was even greater.
Previous work
References (32)
- et al.
How many endoscopies are performed for colorectal cancer screening?Results from CDC's survey of endoscopic capacity
Gastroenterology
(2004) Who is the best colonoscopist?
Gastrointest Endosc
(2007)- et al.
Colonoscopic miss rates of adenomas determined by back-to-back colonoscopies
Gastroenterology
(1997) - et al.
Analysis of administrative data finds endoscopist quality measures associated with postcolonoscopy colorectal cancer
Gastroenterology
(2011) - et al.
Assessment of the quality of colonoscopy reports: results from a multicenter consortium
Gastrointest Endosc
(2009) - et al.
Utilization of surveillance colonoscopy in community practice
Gastroenterology
(2010) - et al.
Standardized colonoscopy reporting and data system: report of the Quality Assurance Task Group of the National Colorectal Cancer Roundtable
Gastrointest Endosc
(2007) - et al.
The medical archival system: an information retrieval system based on distributed parallel processing
Inform Process Manag
(1991) - et al.
Natural language processing in the electronic medical record: assessing clinician adherence to tobacco treatment guidelines
Am J Prev Med
(2005) - et al.
Cancer statistics, 2010
CA Cancer J Clin
(2010)
Cost-effectiveness of colonoscopy in screening for colorectal cancer
Ann Intern Med
Polyp miss rate determined by tandem colonoscopy: a systematic review
Am J Gastroenterol
Risk of developing colorectal cancer following a negative colonoscopy examination: evidence for a 10-year interval between colonoscopies
JAMA
Colonoscopic withdrawal times and adenoma detection during screening colonoscopy
N Engl J Med
Quality indicators for colonoscopy and the risk of interval cancer
N Engl J Med
Overuse of screening colonoscopy in the Medicare population
Arch Intern Med
Cited by (0)
DISCLOSURE: All authors disclosed no financial relationships relevant to this publication.
If you would like to chat with an author of this article, you may contact Dr Mehrotra at [email protected].