A foundation systematic review of natural language processing applied to gastroenterology & hepatology

This review assesses the progress of NLP in gastroenterology to date, grades the robustness of the methodology, exposes the field to a new generation of authors, and highlights opportunities for future research.

Seven scholarly databases (ACM Digital Library, Arxiv, Embase, IEEE Explore, Pubmed, Scopus and Google Scholar) were searched for studies published between 2015 and 2023 that met the inclusion criteria. Studies lacking a description of appropriate validation or NLP methods were excluded, as were studies ufinavailable in English, those focused on non-gastrointestinal diseases and those that were duplicates. Two independent reviewers extracted study information, clinical/algorithm details, and relevant outcome data. Methodological quality and bias risks were appraised using a checklist of quality indicators for NLP studies.

Fifty-three studies were identified utilising NLP in endoscopy, inflammatory bowel disease, gastrointestinal bleeding, liver and pancreatic disease. Colonoscopy was the focus of 21 (38.9%) studies; 13 (24.1%) focused on liver disease, 7 (13.0%) on inflammatory bowel disease, 4 (7.4%) on gastroscopy, 4 (7.4%) on pancreatic disease and 2 (3.7%) on endoscopic sedation/ERCP and gastrointestinal bleeding. Only 30 (56.6%) of the studies reported patient demographics, and only 13 (24.5%) had a low risk of validation bias. Thirty-five (66%) studies mentioned generalisability, but only 5 (9.4%) mentioned explainability or shared code/models.

NLP can unlock substantial clinical information from free-text notes stored in EPRs and is already being used, particularly to interpret colonoscopy and radiology reports. However, the models we have thus far lack transparency, leading to duplication, bias, and doubts about generalisability. Therefore, greater clinical engagement, collaboration, and open sharing of appropriate datasets and code are needed.