Coelho-Prabhu, Nayantara

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.

Lay Summary Oral vancomycin shows promise in treating pouchitis in patients with primary sclerosing cholangitis and ulcerative colitis. In this study, vancomycin helped reduce stool frequency, urgency, and incontinence. More research is needed to confirm its long-term benefits and best treatment practices.

Inflammatory bowel disease (IBD) is a group of chronic inflammatory conditions of the gastrointestinal tract resulting from an inappropriate immune response to an altered gut microbiome in genetically predisposed individuals. Endoscopy plays a central role in IBD management, aiding in diagnosis, disease staging, monitoring, and therapeutic guidance. Patients with IBD face an increased risk of colorectal neoplasia due to chronic inflammation. Artificial intelligence (AI)-based systems show promise in detecting and classifying dysplasia and neoplasia during endoscopic evaluation. While there have been several studies on the application of AI to detect and diagnose various types of neoplasia in the non-IBD population, the literature in patients with IBD is limited. We aim to summarize the current evidence on the application of AI technologies to detect IBD-associated neoplasia, highlighting potential benefits, limitations, and future directions. A comprehensive literature search was performed using the PubMed database to identify relevant studies from January 2010 to February 2025. Additional references were identified from the relevant articles’ bibliographies. AI-assisted endoscopy, particularly using machine learning and deep learning techniques, has shown promise in improving lesion detection rates and supporting real-time decision-making. Computer-aided detection systems may increase the sensitivity of dysplasia identification, while computer-aided diagnosis tools can aid in lesion characterization. Early studies suggest that AI can reduce interobserver variability, improve targeting of biopsies, and potentially lead to more personalized surveillance strategies. Although clinical data specific to IBD-related neoplasia remain limited compared to sporadic colorectal neoplasia, the integration of AI into endoscopic practice holds significant potential to enhance dysplasia detection and improve patient outcomes. Continued research, validation in IBD-specific cohorts, and integration with clinical workflows are essential to realize the full impact of AI in this setting.

Abstract Background Patients with Crohn’s disease (CD) who have ileal or any small bowel (SB) involvement are at increased risk of developing SB cancer. Due to the rarity of this complication of CD, we aimed to describe the clinical features, presentation, and of small bowel neoplasms (SBN) in patients with CD. Methods A case-control study was performed to include patients ≥18 years old with a diagnosis of CD with or without SBN at a single large referral center from January 1992 to May 2023. Patients were identified using bioinformatics and natural language processing tools, as well as anatomic pathology records. Two age- and sex-matched controls were identified for each case. Results In total, 54 patients with CD and SBN and 108 patients with CD without SBN were identified. Of the cases, most had ileal CD (55.6%) with stricturing (59.3%) phenotype. Median duration of CD prior to SBN diagnosis was 19.5 years. Nonpenetrating/nonstricturing behavior (odds ratio [OR], 9.23; 95% CI, 2.91-29.32; P = .0008) was significantly associated with an increased odds of SBN. History of tobacco use (OR, 0.27; 95% CI, 0.13-0.60; P = .0011) and IBD-associated colonic neoplasia (OR, 0.18; 95%, CI 0.4-0.85; P = .0303) were protective in development of SBN. Conclusions Nonpenetrating/nonstricturing CD appeared to raise SBN risk. History of tobacco use and colonic IBD-associated neoplasia are associated with reduced risk of SBN. Further studies with large sample sizes are needed to determine true incidence and risk factors associated with SBN in CD and assess potentially protective effects of early surgery.

Abstract Background and Aims Patients with inflammatory bowel disease (IBD) have a higher risk of developing colorectal dysplasia and colorectal cancer compared to the general population. Although the use of surveillance protocols has improved the ability to detect dysplasia, some lesions are still missed at colonoscopy. This study aims to determine the rate of dysplastic lesions that are undetected at colonoscopies in IBD patients undergoing colectomy and to identify factors associated with missed dysplasia. Methods Patients who had received a total or subtotal colectomy at Mayo Clinic (Rochester, Minnesota), between January 2003 and December 2022, and had a complete colonoscopy within 5 years before surgery were retrospectively enrolled. Data abstracted included demographic information, disease-related data, colonoscopy and pathology reports, and surgery pathology reports. Colonoscopy and surgery findings were compared, and patients were divided into 3 groups: no dysplasia at both, detected dysplasia, and undetected dysplasia. Results Among 1320 IBD patients undergoing colectomy, 5.4% had undetected dysplastic lesions identified only at surgery. Factors independently associated with dysplasia detection were endoscopic remission or mild endoscopic disease activity (odds ratio [OR], 2.326; P = .0081; 95% CI, 1.246-4.342), prior dysplasia detection (OR, 1.876; P = .0491; 95% CI, 1.002-3.511), colonoscopy performed for surveillance (OR, 2.380; P = .0048; 95% CI, 1.302-4.350), and longer disease duration at surgery (OR, 1.039; P = .0085; 95% CI, 1.010-1.070). Conclusions Clinicians should be aware of the risk of missing dysplastic lesions, especially when endoscopic disease activity is moderate/severe, and not only for longstanding disease. Efforts should be made to obtain endoscopic remission to make the “invisible” visible.

Abstract Background Fecal calprotectin (FC) is a promising biomarker for assessing ulcerative colitis (UC) endoscopic activity. However, the optimal FC cutoff to identify each Mayo endoscopic subscore (MES) remains inconclusive. Methods The electronic medical records of 177 adult UC patients evaluated at Mayo Clinic Rochester from January 2017 to March 2023 were retrospectively reviewed, obtaining clinical data and US-based Werfen Diagnostics FC levels collected within 30 days before colonoscopy or flexible sigmoidoscopy. Three independent inflammatory bowel disease specialist endoscopists blindly reviewed the most severe endoscopic images for grading MES. Results The median interval between FC collection and endoscopy was 2 days. Fecal calprotectin showed strong positive correlations with MES (Spearman’s r = 0.709; P < .01) and other clinical parameters. Fecal calprotectin cutoff of 60 mcg/g effectively distinguished MES 0 from MES 1-3 (sensitivity, 0.78; specificity, 0.97; area under the receiver operating characteristic curve [AUC], 0.901) and predicted clinical remission (Total Mayo Score ≤2 and no subscore >1; sensitivity, 0.83; specificity, 0.98; AUC, 0.921). Fecal calprotectin cutoff of 110 mcg/g effectively differentiated MES 0-1 from MES 2-3 (sensitivity, 0.86; specificity, 0.87; AUC, 0.915), while a cutoff of 310 mcg/g distinguished MES 0-2 from MES 3 (sensitivity, 0.80; specificity, 0.76; AUC, 0.820). Conclusions This study supports the reliability and applicability of FC as a valuable marker of endoscopic inflammation, particularly in distinguishing MES 0 from MES 1-3 using the FC cutoff of 60 mcg/g. Sensitivity analysis demonstrated robust results.

Abstract Background Patients with inflammatory bowel disease (IBD) and primary sclerosing cholangitis (PSC) frequently undergo restorative proctocolectomy with ileal pouch-anal anastomosis (IPAA) for medically refractory disease or colonic dysplasia/neoplasia. Subtotal colectomy with ileosigmoid or ileorectal anastomosis may have improved outcomes but is not well studied. Due to increased risk for colorectal cancer in PSC-IBD, there is hesitancy to perform subtotal colectomy. We aim to describe the frequency of colorectal dysplasia/neoplasia following IPAA vs subtotal colectomy in PSC-IBD patients. Methods We completed a retrospective study from 1972 to 2022 of patients with PSC-IBD who had undergone total proctocolectomy with IPAA or subtotal colectomy. We abstracted demographics, disease characteristics, and endoscopic surveillance data from the EMR. Results Of 125 patients (99 IPAA; 26 subtotal), the indication for surgery was rectal sparing medically refractory disease (51% vs 42%), dysplasia (37% vs 30%) and neoplasia (11% vs 26%) in IPAA vs subtotal colectomy patients, respectively. On endoscopic surveillance of IPAA patients, 2 (2%) had low-grade dysplasia (LGD) in the ileal pouch and 2 (2%) had LGD in the rectal cuff after an average of 8.4 years and 12.3 years of follow-up, respectively. One (1%) IPAA patient developed neoplasia of the rectal cuff after 17.8 years of surgical continuity. No subtotal colectomy patients had dysplasia/neoplasia in the residual colon or rectum. Conclusions In patients with PSC-IBD, there was no dysplasia or neoplasia in those who underwent subtotal colectomy as opposed to the IPAA group. Subtotal colectomy may be considered a viable surgical option in patients with rectal sparing PSC-IBD if adequate endoscopic surveillance is implemented.

Abstract Background Ileal pouch–anal anastomosis (IPAA) is the standard restorative procedure following proctocolectomy in patients with inflammatory bowel disease (IBD) who require colectomy. However, removal of the diseased colon does not eliminate the risk of pouch neoplasia. We aimed to assess the incidence of pouch neoplasia in IBD patients following IPAA. Methods All patients at a large tertiary center with International Classification of Diseases–Ninth Revision/International Classification of Diseases–Tenth Revision codes for IBD who underwent IPAA and had subsequent pouchoscopy were identified using a clinical notes search from January 1981 to February 2020. Relevant demographic, clinical, endoscopic, and histologic data were abstracted. Results In total, 1319 patients were included (43.9% women). Most had ulcerative colitis (95.2%). Out of 1319 patients, 10 (0.8%) developed neoplasia following IPAA. Neoplasia of the pouch was seen in 4 cases with neoplasia of the cuff or rectum seen in 5 cases. One patient had neoplasia of the prepouch, pouch, and cuff. Types of neoplasia included low-grade dysplasia (n = 7), high-grade dysplasia (n = 1), colorectal cancer (n = 1), and mucosa-associated lymphoid tissue lymphoma (n = 1). Presence of extensive colitis, primary sclerosing cholangitis, backwash ileitis, and rectal dysplasia at the time of IPAA were significantly associated with increased risk of pouch neoplasia. Conclusions The incidence of pouch neoplasia in IBD patients who have undergone IPAA is relatively low. Extensive colitis, primary sclerosing cholangitis, and backwash ileitis prior to IPAA and rectal dysplasia at the time of IPAA raise the risk of pouch neoplasia significantly. A limited surveillance program might be appropriate for patients with IPAA even with a history of colorectal neoplasia.

Mucormycosis is a rare and often fatal invasive fungal infection mostly seen in immune-compromised individuals. A high index of clinical suspicion is necessary, so that effective preemptive therapy can be started, as timely intervention is crucial. In this series we present three cases of invasive mucormycosis in patients with underlying inflammatory bowel disease that had received therapy with immunomodulators prior to the infection. All three had varied clinical manifestations. We also review the literature of invasive mucormycosis in patients with inflammatory bowel disease.