Parasa, Sravanthi

ABSTRACT Background and Aims Artificial intelligence (AI) is increasingly integrated into gastrointestinal (GI) endoscopy, yet limited data exist on how patients and endoscopists perceive its use. This study aimed to evaluate users' values and preferences regarding AI in endoscopy to support effective implementation and inform guideline development. Methods As part of the World Endoscopy Organization (WEO) AI committee initiatives, two structured international surveys were conducted—one for patients and one for practicing endoscopists. Thirteen AI‐related statements were presented to patients via an established online platform, while 23 statements were shared with endoscopists through professional networks. Responses were captured using 5‐point Likert scales and analyzed with non‐parametric tests, including subgroup comparisons by age, gender, and endoscopic experience. Results A total of 1237 patients and 476 endoscopists participated. Most patients supported AI in image analysis (75.5%) but emphasized the need for endoscopist oversight (92.3%). Among endoscopists, 90.3% believed AI improves endoscopy quality, and 85.3% believed it benefits outcomes. Concerns were raised about liability (47%), operator dependency (34.8%), and procedure time (49%). Most respondents felt primary responsibility for AI‐related errors should rest with the endoscopist. Younger and male patients reported greater trust in AI. Conclusions Patients and endoscopists are generally supportive of AI in GI endoscopy, especially as an adjunct to human expertise. However, key concerns—including accountability, trust, and clinical integration—must be addressed to ensure responsible and effective adoption.

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.

The number of artificial intelligence (AI) tools for colonoscopy on the market is increasing with supporting clinical evidence. Nevertheless, their implementation is not going smoothly for a variety of reasons, including lack of data on clinical benefits and cost‐effectiveness, lack of trustworthy guidelines, uncertain indications, and cost for implementation. To address this issue and better guide practitioners, the World Endoscopy Organization (WEO) has provided its perspective about the status of AI in colonoscopy as the position statement. WEO Position Statement: Statement 1.1: Computer‐aided detection (CADe) for colorectal polyps is likely to improve colonoscopy effectiveness by reducing adenoma miss rates and thus increase adenoma detection; Statement 1.2: In the short term, use of CADe is likely to increase health‐care costs by detecting more adenomas; Statement 1.3: In the long term, the increased cost by CADe could be balanced by savings in costs related to cancer treatment (surgery, chemotherapy, palliative care) due to CADe‐related cancer prevention; Statement 1.4: Health‐care delivery systems and authorities should evaluate the cost‐effectiveness of CADe to support its use in clinical practice; Statement 2.1: Computer‐aided diagnosis (CADx) for diminutive polyps (≤5 mm), when it has sufficient accuracy, is expected to reduce health‐care costs by reducing polypectomies, pathological examinations, or both; Statement 2.2: Health‐care delivery systems and authorities should evaluate the cost‐effectiveness of CADx to support its use in clinical practice; Statement 3: We recommend that a broad range of high‐quality cost‐effectiveness research should be undertaken to understand whether AI implementation benefits populations and societies in different health‐care systems.

INTRODUCTION: Endoscopic surveillance guidelines in Barrett’s esophagus (BE) to detect progression to high grade dysplasia (HGD) or esophageal adenocarcinoma (EAC) are based solely on dysplasia grade. Given low rates of progression, identification of predictors (and scores) of progression may help to focus surveillance or intervention in those at higher risk. We aimed to assess predictors of progression and externally validate the Progression in Barrett’s (PIB) score in an independent multicenter prospective BE and EAC cohort. METHODS: The EA and Barrett’s esophagus (EABE) registry is a prospective cohort of patients recruited from three medical centers. Progressors were defined as those with the development of HGD or EAC more than 12 months after initial diagnosis. Demographic and clinical variables were abstracted. The annual incidence rate and predictors of progression were assessed using univariate and multivariable Cox proportional hazards analysis. The ability of the PIB score (incorporating weighted scores for male gender, smoking (ever versus never), BE length and confirmed LGD) to risk stratify the cohort into low (0-10 points), intermediate (11-20 points) and high risk (> 20 points) groups was assessed. RESULTS: 429 patients were included. 84% were men, with a mean (SD) age of 61.5 (9.9) years. 65% were ever smokers and most (76.7%), had NDBE at diagnosis. Mean (SD) maximal BE segment length was 5.9 (3.2) cm. Eighty-two patients (19.1%) progressed to HGD (n = 65) or EAC (n = 17) over a median (IQR) follow up of 7.5 (3.7, 12.5) years. Annual incidence rates of progression to EAC and EAC/HGD were 0.5% and 2.0% respectively. Univariate and multivariable predictors of progression are displayed in Table 1. The PIB score divided patients into three groups (Table 2) with progressively increasing rates of progression. The risk in the high risk group was three fold higher than the low risk group ( P = 0.024). The risk in the intermediate group was twofold higher but not statistically significantly higher ( P = 0.13). The PIB score had a c-statistic score of 0.76 in the original cohort. In this cohort the c-statistic value was lower at 0.64, suggesting moderate performance. CONCLUSION: Male sex and BE length predicted progression in this independent multicenter cohort. The PIB score was also able to risk-stratify patients in this validation cohort with the high risk cohort being 3x more likely to progress compared to the low risk cohort.