Clinical decision support with natural language processing facilitates determination of colonoscopy surveillance intervals

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Background & Aims: With an increased emphasis on improving quality and decreasing costs, new tools are needed to improve adherence to evidence-based practices and guidelines in endoscopy. We investigated the ability of an automated system that uses natural language processing (NLP) and clinical decision support (CDS) to facilitate determination of colonoscopy surveillance intervals. Methods: We performed a retrospective study at a single Veterans Administration medical center of patients age 40 years and older who had an index outpatient colonoscopy from 2002 through 2009 for any indication except surveillance of a previous colorectal neoplasia. We analyzed data from 10,798 reports, with 6379 linked to pathology results and 300 randomly selected reports. NLP-based CDS surveillance intervals were compared with those determined by paired, blinded, manual review. The primary outcome was adjusted agreement between manual review and the fully automated system. Results: κ statistical analysis produced a value of 0.74 (P < .001) for agreement between the full text annotation and the NLP-based CDS system. Fifty-five reports (18.3%; 95% confidence interval, 14.1%-23.2%) differed between manual review and CDS recommendations. Of these, NLP error accounted for 30 (54.5%), incomplete resection of adenomatous tissue accounted for 14 (25.5%), and masses observed without biopsy findings of cancer accounted for 4 (7.2%). NLP-based CDS surveillance intervals had higher levels of agreement with the standard (81.7%) than the level agreement between experts (72% agreement between paired reviewers). Conclusions: A fully automated system that uses NLP and a guideline-based CSD system can accurately facilitate guideline-recommended adherence surveillance for colonoscopy.

Original languageEnglish
Pages (from-to)1130-1136
Number of pages7
JournalClinical Gastroenterology and Hepatology
Volume12
Issue number7
DOIs
StatePublished - 2014

Fingerprint

Clinical Decision Support Systems
Natural Language Processing
Colonoscopy
Guideline Adherence
United States Department of Veterans Affairs
Evidence-Based Practice
Practice Guidelines
Endoscopy
Neoplasms
Outpatients
Retrospective Studies
Guidelines
Confidence Intervals
Pathology
Biopsy
Costs and Cost Analysis

Keywords

  • Clinical decision support
  • Colonoscopy
  • Natural language processing
  • Surveillance

ASJC Scopus subject areas

  • Gastroenterology
  • Hepatology

Cite this

@article{c04867122c1c49b88a3ef8837409dbe5,
title = "Clinical decision support with natural language processing facilitates determination of colonoscopy surveillance intervals",
abstract = "Background & Aims: With an increased emphasis on improving quality and decreasing costs, new tools are needed to improve adherence to evidence-based practices and guidelines in endoscopy. We investigated the ability of an automated system that uses natural language processing (NLP) and clinical decision support (CDS) to facilitate determination of colonoscopy surveillance intervals. Methods: We performed a retrospective study at a single Veterans Administration medical center of patients age 40 years and older who had an index outpatient colonoscopy from 2002 through 2009 for any indication except surveillance of a previous colorectal neoplasia. We analyzed data from 10,798 reports, with 6379 linked to pathology results and 300 randomly selected reports. NLP-based CDS surveillance intervals were compared with those determined by paired, blinded, manual review. The primary outcome was adjusted agreement between manual review and the fully automated system. Results: κ statistical analysis produced a value of 0.74 (P < .001) for agreement between the full text annotation and the NLP-based CDS system. Fifty-five reports (18.3{\%}; 95{\%} confidence interval, 14.1{\%}-23.2{\%}) differed between manual review and CDS recommendations. Of these, NLP error accounted for 30 (54.5{\%}), incomplete resection of adenomatous tissue accounted for 14 (25.5{\%}), and masses observed without biopsy findings of cancer accounted for 4 (7.2{\%}). NLP-based CDS surveillance intervals had higher levels of agreement with the standard (81.7{\%}) than the level agreement between experts (72{\%} agreement between paired reviewers). Conclusions: A fully automated system that uses NLP and a guideline-based CSD system can accurately facilitate guideline-recommended adherence surveillance for colonoscopy.",
keywords = "Clinical decision support, Colonoscopy, Natural language processing, Surveillance",
author = "Timothy Imler and Justin Morea and Thomas Imperiale",
year = "2014",
doi = "10.1016/j.cgh.2013.11.025",
language = "English",
volume = "12",
pages = "1130--1136",
journal = "Clinical Gastroenterology and Hepatology",
issn = "1542-3565",
publisher = "W.B. Saunders Ltd",
number = "7",

}

TY - JOUR

T1 - Clinical decision support with natural language processing facilitates determination of colonoscopy surveillance intervals

AU - Imler, Timothy

AU - Morea, Justin

AU - Imperiale, Thomas

PY - 2014

Y1 - 2014

N2 - Background & Aims: With an increased emphasis on improving quality and decreasing costs, new tools are needed to improve adherence to evidence-based practices and guidelines in endoscopy. We investigated the ability of an automated system that uses natural language processing (NLP) and clinical decision support (CDS) to facilitate determination of colonoscopy surveillance intervals. Methods: We performed a retrospective study at a single Veterans Administration medical center of patients age 40 years and older who had an index outpatient colonoscopy from 2002 through 2009 for any indication except surveillance of a previous colorectal neoplasia. We analyzed data from 10,798 reports, with 6379 linked to pathology results and 300 randomly selected reports. NLP-based CDS surveillance intervals were compared with those determined by paired, blinded, manual review. The primary outcome was adjusted agreement between manual review and the fully automated system. Results: κ statistical analysis produced a value of 0.74 (P < .001) for agreement between the full text annotation and the NLP-based CDS system. Fifty-five reports (18.3%; 95% confidence interval, 14.1%-23.2%) differed between manual review and CDS recommendations. Of these, NLP error accounted for 30 (54.5%), incomplete resection of adenomatous tissue accounted for 14 (25.5%), and masses observed without biopsy findings of cancer accounted for 4 (7.2%). NLP-based CDS surveillance intervals had higher levels of agreement with the standard (81.7%) than the level agreement between experts (72% agreement between paired reviewers). Conclusions: A fully automated system that uses NLP and a guideline-based CSD system can accurately facilitate guideline-recommended adherence surveillance for colonoscopy.

AB - Background & Aims: With an increased emphasis on improving quality and decreasing costs, new tools are needed to improve adherence to evidence-based practices and guidelines in endoscopy. We investigated the ability of an automated system that uses natural language processing (NLP) and clinical decision support (CDS) to facilitate determination of colonoscopy surveillance intervals. Methods: We performed a retrospective study at a single Veterans Administration medical center of patients age 40 years and older who had an index outpatient colonoscopy from 2002 through 2009 for any indication except surveillance of a previous colorectal neoplasia. We analyzed data from 10,798 reports, with 6379 linked to pathology results and 300 randomly selected reports. NLP-based CDS surveillance intervals were compared with those determined by paired, blinded, manual review. The primary outcome was adjusted agreement between manual review and the fully automated system. Results: κ statistical analysis produced a value of 0.74 (P < .001) for agreement between the full text annotation and the NLP-based CDS system. Fifty-five reports (18.3%; 95% confidence interval, 14.1%-23.2%) differed between manual review and CDS recommendations. Of these, NLP error accounted for 30 (54.5%), incomplete resection of adenomatous tissue accounted for 14 (25.5%), and masses observed without biopsy findings of cancer accounted for 4 (7.2%). NLP-based CDS surveillance intervals had higher levels of agreement with the standard (81.7%) than the level agreement between experts (72% agreement between paired reviewers). Conclusions: A fully automated system that uses NLP and a guideline-based CSD system can accurately facilitate guideline-recommended adherence surveillance for colonoscopy.

KW - Clinical decision support

KW - Colonoscopy

KW - Natural language processing

KW - Surveillance

UR - http://www.scopus.com/inward/record.url?scp=84902545323&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902545323&partnerID=8YFLogxK

U2 - 10.1016/j.cgh.2013.11.025

DO - 10.1016/j.cgh.2013.11.025

M3 - Article

AN - SCOPUS:84902545323

VL - 12

SP - 1130

EP - 1136

JO - Clinical Gastroenterology and Hepatology

JF - Clinical Gastroenterology and Hepatology

SN - 1542-3565

IS - 7

ER -