Advancements in Barrett's esophagus detection: The role of artificial intelligence and its implications.

World J Gastroenterol

Division of Gastroenterology and Center for Autoimmune Liver Diseases, Department of Medicine and Surgery, Fondazione IRCCS San Gerardo dei Tintori, University of Milano-Bicocca, Monza 20900, Italy.

Published: March 2024

Artificial intelligence (AI) is making significant strides in revolutionizing the detection of Barrett's esophagus (BE), a precursor to esophageal adenocarcinoma. In the research article by Tsai , researchers utilized endoscopic images to train an AI model, challenging the traditional distinction between endoscopic and histological BE. This approach yielded remarkable results, with the AI system achieving an accuracy of 94.37%, sensitivity of 94.29%, and specificity of 94.44%. The study's extensive dataset enhances the AI model's practicality, offering valuable support to endoscopists by minimizing unnecessary biopsies. However, questions about the applicability to different endoscopic systems remain. The study underscores the potential of AI in BE detection while highlighting the need for further research to assess its adaptability to diverse clinical settings.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11008413PMC
http://dx.doi.org/10.3748/wjg.v30.i11.1494DOI Listing

Publication Analysis

Top Keywords

barrett's esophagus
8
artificial intelligence
8
advancements barrett's
4
esophagus detection
4
detection role
4
role artificial
4
intelligence implications
4
implications artificial
4
intelligence making
4
making strides
4

Similar Publications

Background And Aims: Oral microbiota may contribute to the development of upper gastrointestinal (UGI) disorders. We aimed to study the association between the microbiome of saliva, subgingival and buccal mucosa, and UGI disorders, particularly precancerous lesions. We also aimed to determine which oral site might serve as the most effective biomarker for UGI disorders.

View Article and Find Full Text PDF

Background/aims: Distal mean nocturnal baseline impedance (MNBI) measuring via pH-impedance may be valuable in diagnosing patients with suspected laryngopharyngeal reflux (LPR). However, its wide adoption is hindered by cost and invasiveness. This study investigates whether baseline impedance measured during high-resolution impedance manometry (HRIM-BI) can predict pathological MNBI.

View Article and Find Full Text PDF

Data on Barrett's esophagus (BE) and esophageal cancer (EC) outcomes in patients with eosinophilic esophagitis (EoE) are limited. We aimed to determine the risk of prevalent BE (<1 year after endoscopy), incident BE (≥1 year after endoscopy), and incident EC in patients with versus without EoE, and to identify predictors of BE/EC in EoE patients. We identified adult patients in the Merative MarketScan Database who underwent first-time upper endoscopy between 2008 and 2020.

View Article and Find Full Text PDF

Barrett's Esophagus (BE) is the only known precursor for esophageal adenocarcinoma (EAC). Patients with multiple risk factors for BE/EAC are recommended for screening; however, few eligible patients undergo evaluation by endoscopy. EsoGuard (EG) is a commercially available biomarker assay used to analyze esophageal cells collected non-endoscopically with EsoCheck (EC) for the qualitative detection of BE/EAC.

View Article and Find Full Text PDF

: Barrett's esophagus (BE), with metaplastic columnar epithelium in the lower esophagus, predisposes patients to esophageal adenocarcinoma (EAC). Despite extensive research, mechanisms underlying BE progression to EAC remain unclear, and no validated biomarkers are available for clinical use. Progastricsin/Pepsinogen-C (PGC), an aspartic proteinase linked to maintaining normal epithelial morphology, is often absent in advanced gastrointestinal malignancies.

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!