Chawla, Saurabh

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 Background and study aims Hemospray (TC-325) is a mineral powder with adsorptive properties designed for use in various gastrointestinal bleeding (GIB) scenarios. We conducted a systematic review & meta-analysis of randomized controlled trials (RCTs) comparing TC-325 to standard endoscopic therapy (SET) for non-variceal GIB (NVGIB). Methods Multiple databases were searched through October 2022. Meta-analysis was performed using a random-effects model to determine pooled relative risk (RR) and proportions with 95 % confidence intervals (CI) for primary hemostasis, hemostasis failure, 30-day rebleeding, length of stay (LOS), and need for rescue interventions. Heterogeneity was assessed using I2%. Results Five RCTs with 362 patients (TC-325 178, SET 184) – 123 females and 239 males with a mean age 65 ± 16 years). The most common etiologies were peptic ulcer disease (48 %), malignancies (35 %), and others (17 %). Bleeding was characterized as Forrest IA (7 %), IB (73 %), IIA (3 %), and IIB (1 %). SET included epinephrine injection, electrocautery, hemoclips, or a combination. No statistical difference in primary hemostasis between TC-325 compared to SET, RR 1.09 (CI 0.95–1.25; I2 43), P = 0.2, including patients with oozing/spurting hemorrhage, RR 1.13 (CI 0.98–1.3; I2 35), P = 0.08. Failure to achieve hemostasis was higher in SET compared to TC-325, RR 0.30 (CI 0.12–0.77, I2 0), P = 0.01, including patients with oozing/spurting hemorrhage, RR 0.24 (CI 0.09 – 0.63, I2 0), P = 0.004. We found no difference between the two interventions in terms of rebleeding, RR 1.13 (CI 0.62–2.07, I2 26), P = 0.8 and LOS, standardized mean difference (SMD) 0.27 (CI, –0.20–0.74; I2 62), P = 0.3. Finally, pooled rate of rescue interventions (angiography) was statistically higher in SET compared to TC-325, RR 0.68 (CI 0.5–0.94; I2 0), P = 0.02. Conclusions Our analysis shows that for acute NV GIB, including oozing/spurting hemorrhage, TC-325 does not result in higher rates of primary hemostasis compared to SET. However, lower rates of failures were seen with TC-325 than SET. In addition, there was no difference in the two modalities when comparing rates of rebleeding and LOS.