Parsa, Nasim

INTRODUCTION: The American College of Gastroenterology assembled a multidisciplinary task force to evaluate the current state and future direction of artificial intelligence (AI) in gastroenterology, hepatology, and endoscopy leading to the development of consensus-based recommendations for responsible AI integration in clinical practice. METHODS: A total of 32 subject-matter experts and 12 industry partners, representing diverse practice settings and expertise, conducted subgroup literature reviews across 5 key areas (endoscopy, practice management clinical applications, training and education, inflammatory bowel disease and liver disease, ethics and equity). Draft statements were developed and rated on a 5-point Likert scale using a modified Delphi process. A consensus was set at ≥70% combined agreement. Nonconsensus items were revised and revoted electronically. RESULTS: A total of 43 statements, 40 (93%) reached consensus in round 1 and the remaining 3 achieved consensus after round 2. Evidence supports computer-aided detection improving adenoma detection rate and miss rate in controlled studies, with mixed real-world impact and insufficient long-term outcomes (e.g., interval colon cancer rate). Recommendations emphasize thorough validation and reduction of bias by heterogeneous Data sets. Outside endoscopy, ambient AI scribes, natural language processing (NLP)-enabled coding, workflow optimization, and previous authorization support show potential. Training recommendations endorse a structured AI curriculum while preserving independent procedural competence to avoid deskilling. In inflammatory bowel disease and hepatology, AI could help improve diagnostic accuracy, help predict risk of disease progression, and help guide therapy. Equity, governance, and reimbursement statements call for chain-of-custody data protections, specialty-society oversight, and payment models that reward quality and cost reduction. DISCUSSION: This consensus outlines how AI can augment rather than replace clinical expertise while promoting safety, transparency, interoperability, and equity. Priorities include pragmatic and prospective trials, multi-institutional data-sharing consortia, bias mitigation, and workforce training to enable trustworthy and clinically impactful AI adoption in gastroenterology, liver, and endoscopy care.

ABSTRACT Objective Despite high stand‐alone performance, studies demonstrate that artificial intelligence (AI)‐supported endoscopic diagnostics often fall short in clinical applications due to human‐AI interaction factors. This video‐based trial on Barrett's esophagus aimed to investigate how examiner behavior, their levels of confidence, and system usability influence the diagnostic outcomes of AI‐assisted endoscopy. Methods The present analysis employed data from a multicenter randomized controlled tandem video trial involving 22 endoscopists with varying degrees of expertise. Participants were tasked with evaluating a set of 96 endoscopic videos of Barrett's esophagus in two distinct rounds, with and without AI assistance. Diagnostic confidence levels were recorded, and decision changes were categorized according to the AI prediction. Additional surveys assessed user experience and system usability ratings. Results AI assistance significantly increased examiner confidence levels ( p < 0.001) and accuracy. Withdrawing AI assistance decreased confidence ( p < 0.001), but not accuracy. Experts consistently reported higher confidence than non‐experts ( p < 0.001), regardless of performance. Despite improved confidence, correct AI guidance was disregarded in 16% of all cases, and 9% of initially correct diagnoses were changed to incorrect ones. Overreliance on AI, algorithm aversion, and uncertainty in AI predictions were identified as key factors influencing outcomes. The System Usability Scale questionnaire scores indicated good to excellent usability, with non‐experts scoring 73.5 and experts 85.6. Conclusions Our findings highlight the pivotal function of examiner behavior in AI‐assisted endoscopy. To fully realize the benefits of AI, implementing explainable AI, improving user interfaces, and providing targeted training are essential. Addressing these factors could enhance diagnostic accuracy and confidence in clinical practice.

Abstract Background This study evaluated the effect of an artificial intelligence (AI)-based clinical decision support system on the performance and diagnostic confidence of endoscopists in their assessment of Barrett’s esophagus (BE). Methods 96 standardized endoscopy videos were assessed by 22 endoscopists with varying degrees of BE experience from 12 centers. Assessment was randomized into two video sets: group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett’s esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level. Results AI had a stand-alone sensitivity, specificity, and accuracy of 92.2%, 68.9%, and 81.3%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3%, 58.1%, and 71.5%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.8% [95%CI 65.2%–74.2%] to 78.0% [95%CI 74.0%–82.0%]; specificity 67.3% [95%CI 62.5%–72.2%] to 72.7% [95%CI 68.2%–77.3%]). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI. Conclusion BE nonexperts benefitted significantly from additional AI. BE experts and nonexperts remained significantly below the stand-alone performance of AI, suggesting that there may be other factors influencing endoscopists’ decisions to follow or discard AI advice.

Achalasia is a rare esophageal motility disorder characterized by incomplete relaxation of the lower esophageal sphincter and absence of normal peristalsis. A precise diagnosis is crucial to successful treatment, and over the past few years significant advances have been made in how achalasia is diagnosed. Although high resolution manometry (HRM) is generally considered the gold standard diagnostic modality, manometric findings can be inconclusive and in some cases patients may not tolerate the procedure. Therefore, the addition of provocative maneuvers during HRM, and the use of timed barium esophagram and the functional lumen imaging probe (FLIP) are all important tools that have improved our ability to accurately diagnose achalasia. In this review, we go over the current approach to the diagnosis of achalasia.

Abstract Background and Aims Lack of clinical validation and inter-observer variability are two limitations of endoscopic assessment and scoring of disease severity in patients with ulcerative colitis [UC]. We developed a deep learning [DL] model to improve, accelerate and automate UC detection, and predict the Mayo Endoscopic Subscore [MES] and the Ulcerative Colitis Endoscopic Index of Severity [UCEIS]. Methods A total of 134 prospective videos [1550 030 frames] were collected and those with poor quality were excluded. The frames were labelled by experts based on MES and UCEIS scores. The scored frames were used to create a preprocessing pipeline and train multiple convolutional neural networks [CNNs] with proprietary algorithms in order to filter, detect and assess all frames. These frames served as the input for the DL model, with the output being continuous scores for MES and UCEIS [and its components]. A graphical user interface was developed to support both labelling video sections and displaying the predicted disease severity assessment by the artificial intelligence from endoscopic recordings. Results Mean absolute error [MAE] and mean bias were used to evaluate the distance of the continuous model’s predictions from ground truth, and its possible tendency to over/under-predict were excellent for MES and UCEIS. The quadratic weighted kappa used to compare the inter-rater agreement between experts’ labels and the model’s predictions showed strong agreement [0.87, 0.88 at frame-level, 0.88, 0.90 at section-level and 0.90, 0.78 at video-level, for MES and UCEIS, respectively]. Conclusions We present the first fully automated tool that improves the accuracy of the MES and UCEIS, reduces the time between video collection and review, and improves subsequent quality assurance and scoring.