Background & Aims: Little is known about the ability of natural language processing (NLP) to extract meaningful information from free-text gastroenterology reports for secondary use.
Methods: We randomly selected 500 linked colonoscopy and pathology reports from 10,798 nonsurveillance colonoscopies to train and test the NLP system. By using annotation by gastroenterologists as the reference standard, we assessed the accuracy of an open-source NLP engine that processed and extracted clinically relevant concepts. The primary outcome was the highest level of pathology. Secondary outcomes were location of the most advanced lesion, largest size of an adenoma removed, and number of adenomas removed.
Results: The NLP system identified the highest level of pathology with 98% accuracy, compared with triplicate annotation by gastroenterologists (the standard). Accuracy values for location, size, and number were 97%, 96%, and 84%, respectively.
Conclusions: The NLP can extract specific meaningful concepts with 98% accuracy. It might be developed as a method to further quantify specific quality metrics.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4026927 | PMC |
| http://dx.doi.org/10.1016/j.cgh.2012.11.035 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Season of conception and risk of hypertensive disorder during pregnancy.
BMC Pregnancy Childbirth
January 2025
National Office for Maternal and Child Health Surveillance of China, West China Second University Hospital, Sichuan University, No. 17, Section 3, Renmin South Road, Chengdu, Sichuan, 610041, China.
Background: Hypertensive Disorder during Pregnancy (HDP) is the most prevalent obstetric conditions in maternal health, but the etiology of most cases remains unexplained. Seasonal variations in the conception of HDP may offer insights into the potential seasonal-specific risk factors.
Methods: Data were sourced from the China's National Maternal Near Miss Surveillance System (NMNMSS) between January 1, 2012, and December 31, 2021.
The Mendelian Phenotype Search Engine (MPSE), a clinical decision support tool using Natural Language Processing and Machine Learning, helped neonatologists expedite decisions to whole genome sequencing (WGS) to diagnose patients in the neonatal intensive care unit. After the MPSE was introduced, utilization of WGS increased, time to ordering WGS decreased, and WGS diagnostic yield increased.
View Article and Find Full Text PDFBiomedical named entity recognition using improved green anaconda-assisted Bi-GRU-based hierarchical ResNet model.
BMC Bioinformatics
January 2025
Department of Information Technology, Vardhaman College of Engineering, Shamshabad, Hyderabad, India.
Background: Biomedical text mining is a technique that extracts essential information from scientific articles using named entity recognition (NER). Traditional NER methods rely on dictionaries, rules, or curated corpora, which may not always be accessible. To overcome these challenges, deep learning (DL) methods have emerged.
View Article and Find Full Text PDFAbdominal and Pelvic MRI Protocol Prediction Using Natural Language Processing.
J Imaging Inform Med
January 2025
Department of Radiology, Mayo Clinic, Rochester, MN, USA.
Exam protocoling is a significant non-interpretive task burden for radiologists. The purpose of this work was to develop a natural language processing (NLP) artificial intelligence (AI) solution for automated protocoling of standard abdomen and pelvic magnetic resonance imaging (MRI) exams from basic associated order information and patient metadata. This Institutional Review Board exempt retrospective study used de-identified metadata from consecutive adult abdominal and pelvic MRI scans performed at our institution spanning 2.
View Article and Find Full Text PDFPutting the prime in priming: Using prime processing behavior to predict target structural processing.
Psychon Bull Rev
January 2025
University of California, Santa Barbara, CA, USA.
Structural priming effects are widespread and heavily relied upon to assess structural representation and processing. Whether these effects are caused by error-driven implicit learning, residual activation, a combination of these, or some other learning mechanism remains to be established. The current study used preexisting data and a novel data analysis approach that links processing at the prime to later processing at the target to better understand the nature of structural priming.
View Article and Find Full Text PDFWant 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!