Multi-Center Colonoscopy Quality Measurement Utilizing Natural Language Processing
Autor: | Gyorgy Baffy, Jason A. Dominitz, Sameer D. Saini, Huiping Xu, Douglas J. Robertson, Justin Morea, Thomas F. Imperiale, Jon Cardwell, Dennis J. Ahnen, Walter E. Smalley, Charles J. Kahi, Christopher Ashley, Anil B. Nagar, Ilseung Cho, Amandeep K. Shergill, Jason K. Hou, Mark A. Korsten, Fadi Antaki, Cynthia S. Johnson, Timothy D. Imler, Kittichai Promrat |
---|---|
Rok vydání: | 2015 |
Předmět: |
Adenoma
Colorectal cancer Colonic Polyps Colonoscopy computer.software_genre Medical Records Primary outcome medicine Humans Reference standards Early Detection of Cancer Natural Language Processing Hyperplasia Hepatology medicine.diagnostic_test business.industry Gastroenterology Quality measurement Reference Standards medicine.disease Artificial intelligence Detection rate Colorectal Neoplasms business computer Natural language processing |
Zdroj: | American Journal of Gastroenterology. 110:543-552 |
ISSN: | 0002-9270 |
DOI: | 10.1038/ajg.2015.51 |
Popis: | Background An accurate system for tracking of colonoscopy quality and surveillance intervals could improve the effectiveness and cost-effectiveness of colorectal cancer (CRC) screening and surveillance. The purpose of this study was to create and test such a system across multiple institutions utilizing natural language processing (NLP). Methods From 42,569 colonoscopies with pathology records from 13 centers, we randomly sampled 750 paired reports. We trained (n=250) and tested (n=500) an NLP-based program with 19 measurements that encompass colonoscopy quality measures and surveillance interval determination, using blinded, paired, annotated expert manual review as the reference standard. The remaining 41,819 nonannotated documents were processed through the NLP system without manual review to assess performance consistency. The primary outcome was system accuracy across the 19 measures. Results A total of 176 (23.5%) documents with 252 (1.8%) discrepant content points resulted from paired annotation. Error rate within the 500 test documents was 31.2% for NLP and 25.4% for the paired annotators (P=0.001). At the content point level within the test set, the error rate was 3.5% for NLP and 1.9% for the paired annotators (P=0.04). When eight vaguely worded documents were removed, 125 of 492 (25.4%) were incorrect by NLP and 104 of 492 (21.1%) by the initial annotator (P=0.07). Rates of pathologic findings calculated from NLP were similar to those calculated by annotation for the majority of measurements. Test set accuracy was 99.6% for CRC, 95% for advanced adenoma, 94.6% for nonadvanced adenoma, 99.8% for advanced sessile serrated polyps, 99.2% for nonadvanced sessile serrated polyps, 96.8% for large hyperplastic polyps, and 96.0% for small hyperplastic polyps. Lesion location showed high accuracy (87.0-99.8%). Accuracy for number of adenomas was 92%. Conclusions NLP can accurately report adenoma detection rate and the components for determining guideline-adherent colonoscopy surveillance intervals across multiple sites that utilize different methods for reporting colonoscopy findings. |
Databáze: | OpenAIRE |
Externí odkaz: |