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

Clin Gastroenterol Hepatol

Division of Gastroenterology and Hepatology, Department of Medicine, Indiana University School of Medicine, Indianapolis, Indiana; Department of Medicine, Indiana University School of Medicine, Indianapolis, Indiana; Center of Excellence for Implementation of Evidence-Based Practice, Richard L. Roudebush VA Medical Center, Indiana University, Indianapolis, Indiana.

Published: July 2014

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.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cgh.2013.11.025DOI Listing

Publication Analysis

Top Keywords

surveillance intervals
12
nlp-based cds
12
manual review
12
clinical decision
8
decision support
8
natural language
8
language processing
8
determination colonoscopy
8
colonoscopy surveillance
8
automated system
8

Similar Publications

Background: The global dissemination of carbapenem-resistant hypervirulent Klebsiella pneumoniae (CR-hvKp) poses a critical threat to public health. However, comprehensive data on the prevalence and resistance rates of CR-hvKp are limited. This systematic review and meta-analysis aim to estimate the pooled prevalence of carbapenem resistance among hvKp strains and assess the distribution of carbapenemase genes.

View Article and Find Full Text PDF

Healthcare performance of leprosy management in peripheral health facilities of Dhanusa and Mahottari, Nepal.

BMC Health Serv Res

January 2025

Department of Health Services, Epidemiology and Disease Control Division, Ministry of Health and Population, Kathmandu, Nepal.

Background: The global elimination of leprosy transmission by 2030 is a World Health Organization (WHO) target. Nepal's leprosy elimination program depends on early case diagnosis and the performance of health workers and facilities. The knowledge and skills of paramedical staff (Leprosy Focal Person, LFP) and case documentation and management by health facilities are therefore key to the performance of health care services.

View Article and Find Full Text PDF

Background: The evidence on the relationship of dietary antioxidant nutrients with the survival of ovarian cancer (OC) remains scarce.

Objective: This study aimed to investigate these associations in a prospective cohort of Chinese patients with OC.

Methods: In this prospective cohort study, patients with epithelial OC completed a food frequency questionnaire at diagnosis and 12 months post-diagnosis, and were followed from 2015 to 2023.

View Article and Find Full Text PDF

Background: Sexual and reproductive health issues in adolescents living with HIV (ALHIV) have been left behind in HIV care programs. ALHIV are at risk of unintended pregnancy which jeopardizes their socio-economic future, health outcomes and exposes their newborn to HIV transmission. A better understanding of these events is needed.

View Article and Find Full Text PDF

Background: Infections may play a role in the etiology of sudden infant death syndrome (SIDS), with Bordetella pertussis being a potential agent. The objective was to analyze the association of SIDS and infant pertussis hospitalization rates over time, comparing a previously unvaccinated population (West Germany) versus a predominantly vaccinated population (East Germany).

Methods: We calculated SIDS rates per 1000 live births per state.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!