Barkin, Jodie A.

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.

INTRODUCTION: Capsule endoscopy (CE) and deep enteroscopy (DE) can be useful for diagnosing and treating suspected small-bowel disease. Guidelines and detailed recommendations exist for the use of CE/DE, but comprehensive quality indicators are lacking. The goal of this task force was to develop quality indicators for appropriate use of CE/DE by using a modified RAND/UCLA Appropriateness Method. METHODS: An expert panel of 7 gastroenterologists with diverse practice experience was assembled to identify quality indicators. A literature review was conducted to develop a list of proposed quality indicators applicable to preprocedure, intraprocedure, and postprocedure periods. The panelists reviewed the literature; identified and modified proposed quality indicators; rated them on the basis of scientific evidence, validity, and necessity; and determined proposed performance targets. Agreement and consensus with the proposed indicators were verified using the RAND/UCLA Appropriateness Method. RESULTS: The voting procedure to prioritize metrics emphasized selecting measures to improve quality and overall patient care. Panelists rated indicators on the perceived appropriateness and necessity for clinical practice. After voting and discussion, 2 quality indicators ranked as inappropriate or uncertain were excluded. Each quality indicator was categorized by measure type, performance target, and summary of evidence. The task force identified 13 quality indicators for CE and DE. DISCUSSION: Comprehensive quality indicators have not existed for CE or DE. The task force identified quality indicators that can be incorporated into clinical practice. The panel also addressed existing knowledge gaps and posed research questions to better inform future research and quality guidelines for these procedures.

INTRODUCTION: Chronic pancreatitis (CP) is a debilitating chronic disease and significantly impacts patient's quality of life. There is evidence that cannabinoids reduce markers of inflammation and fibrosis in pancreatic stellate cells; Cannabis is becoming increasingly popular and there are currently 33 states in the US that have approved medical cannabis while 10 states have approved cannabis for recreational use. We investigated the national trends in prevalence, mortality, length of stay (LOS), hospitalization charges and cost of chronic pancreatitis patients and compared between cannabis-exposed (CE) and non-cannabis-exposed (non-CE). METHODS: The National Inpatient Sample (NIS) database from 2005 to 2014 was queried for all patients with a primary discharge diagnosis of CP as per the International Classification of Diseases 9 th revision (ICD-9) code 5771. Active exposure to cannabis was ascertained based on ICD-9 code 304.3X and 305.2X. We compared CE vs. non-CE patients. Outcomes included in-hospital mortality, length of stay (LOS), inflation adjusted charges and cost. Propensity match analysis for age, gender, race, median income quartile, hospital characteristics and Elixhauser comorbidity index and multivariable logistic regression models were performed using STATA 14 software. RESULTS: Over 31,481 patients with CP as the primary diagnosis were analyzed. Cannabis-exposure prevalence was 1.4% (447 patients). The mean age of CP patients was 49. Patients exposed to cannabis were younger (42 vs 49-year-old, P < 0.001) and mostly males (69% vs 49.7%, P < 0.001). After adjusting for these factors, CE patients had lower total charges compared to non-CE (US$ 21,589 vs. 30,291 P < 0.001) (Figure 1a). CE patients were also hospitalized for fewer number of days when compared to non-CE patients (3.84 vs 5.19 days). There was a significant downward trend in the prevalence of chronic pancreatitis admissions ( P < 0.001) amongst non-CE patients while there was an upward trend in the prevalence of chronic pancreatitis admissions amongst CE patients (Figure 2a, b). Interestingly, after matching for age, gender and comorbidities – CE patients had lower inpatient mortality ( P = 0.059). CONCLUSION: In patients admitted with a primary diagnosis of CP, CE patients had fewer length of stay, hospitalization cost and inpatient mortality. The interplay of these factors remains unknown and studies looking at cannabis strength/dose, route and consumption frequency are needed.

INTRODUCTION: Chronic pancreatitis (CP) does not currently have a cure and it leads to multiple complications (pain, exocrine pancreatic insufficiency, steatorrhea, bone disease), its management is still a challenge. There is evidence that stimulating the endocannabinoid system may reduce inflammation and fibrosis in pancreatic stellate cells. Cannabis is the most frequently used recreational drug in the US and in recent years its legalization has increased. There are currently multiple States in the US that have approved medical cannabis for CP. We investigate the prevalence and outcomes of CP-related complications amongst cannabis-exposed (CE) and non-cannabis-exposed (non-CE) CP patients. METHODS: The National Inpatient Sample (NIS) database from 2005 to 2014 was queried for all patients with a primary or secondary discharge diagnosis of chronic pancreatitis as per the International Classification of Diseases 9 th revision (ICD-9) code 577.1 and a complication related to chronic pancreatitis. Active exposure to cannabis was ascertained based on ICD-9 code 304.3X and 305.2X. We compared CE vs. non-CE patients. Outcomes included pancreatic cancer diagnosis, biliary stricture, pancreatic duct stricture, cholangitis, endoscopic retrograde cholangiopancreatography (ERCP) use for either diagnostic or therapeutic purpose. Propensity match analysis for age, gender, race, median income quartile, hospital characteristics and Elixhauser comorbidity index and multivariable logistic regression models were performed using SAS software (STATA 14). RESULTS: 109,326 patients with CP were analyzed (Figure 1). Prevalence of CE was 2.2% (2360 patients). The mean age of CP patients was 49. When comparing CE vs. non-CE, the CP-related complications amongst matched cohorts were as follows chronic abdominal pain 5.2% vs 0.3% ( P < 0.001), steatorrhea/diarrhea 1.2% vs 13.5% ( P < 0.001), biliary stricture 0.3% vs. 7.1% ( P < 0.001), pancreatic cancer 0.4% vs. 11.8% ( P < 0.001), cholangitis (0.1% vs 2.6%; P < 0.001), pancreatic cancer (0.4 vs 11.8; P < 0.001). Cannabis users also required less diagnostic ERCP (1.4% vs 5.5%; P < 0.001) and therapeutic ERCP (3.5% vs 9.3%; P < 0.001) (Figure 2). CONCLUSION: In CP patients admitted to the hospital, CE patients had lower rates of CP-related complications and importantly pancreatic cancer. These effects could possibly be through the effect of cannabis in the endocannabinoid system as previously shown in mice studies in Germany. More studies are needed to corroborate our findings.