Abstract Background Clinical guidelines for Inflammatory Bowel Disease (IBD) are essential for standardizing care, but their length, technical language, and inconsistent recommendations make them difficult for busy clinicians to use at the point of care. Manually comparing and reconciling multiple guidelines is labor-intensive and often impractical in real-world clinical practice. We aimed to develop and evaluate a proof-of-concept tool using large language models (LLMs) with retrieval-augmented generation (RAG) to improve guideline readability by harmonizing recommendations, highlighting consensus and controversy, and generating concise, actionable statements. Methods We designed an LLM-RAG pipeline (GPT-4o) to automatically segment guideline documents into manageable units, enrich them with metadata and summaries, and retrieve relevant content in response to clinical queries. The system synthesizes recommendations across guidelines, presenting areas of consensus and disagreement in a structured format. Four major international IBD guidelines (ACG, ECCO, BSG, ACPGBI) were analyzed across eight common clinical questions spanning Crohn’s disease and ulcerative colitis. Tool-generated outputs were benchmarked against expert summaries and evaluated by four independent reviewers using 5-point Likert scales for completeness, accuracy, relevance, coherence, and conciseness. Results The tool consistently improved guideline readability by distilling complex text into shorter, structured responses. It achieved mean scores of 4.34 (95% CI, 4.20–4.48) for consensus recognition and 4.61 (95% CI, 4.46–4.77) for disagreement detection. Completeness, accuracy, and relevance all scored >4.0. Although conciseness was lower (3.84, 95% CI, 3.50–4.19), reviewers noted that outputs captured essential information while substantially reducing textual burden. Outline generation performance was moderate (3.25, 95% CI, 2.85–3.65), reflecting challenges in extracting all relevant subtopics. In 7 of 8 clinical scenarios (87.5%), the tool’s recommendations aligned with expert conclusions. Conclusion This proof-of-concept study demonstrates that an LLM-RAG framework can systematically reconcile international IBD guidelines and present them in a more readable, clinically usable format. By reducing complexity and making consensus and controversy explicit, such tools can help clinicians access key evidence more efficiently, support faster decision-making at the bedside, and reduce practice variation. With further refinement, this approach could contribute to “living guidelines” that are continuously updated and more accessible to end-users, ultimately enhancing patient care.
75AGA Clinical Practice Update on Management of Inflammatory Bowel Disease in Elderly Patients: Expert Review
AGA Clinical Practice Update on Management of Inflammatory Bowel Disease in Elderly Patients: Expert Review
Issues in the Development of Practice Guidelines for Inflammatory Bowel Disease
APractice guidelines for inflammatory bowel disease (IBD) should address the unique needs and challenges of the patients, to improve not only the quality of medical care but also the quality of life.
Read more41National Burden of Pediatric Hospitalizations for Inflammatory Bowel Disease
: The objective of the present study was to quantify the national pediatric inpatient inflammatory bowel disease (IBD) burden in terms of the number of IBD-related hospitalizations, the number of days spent in the hospital, and hospitalization costs. : Hospitalizations for children and adolescents 20 years and younger with a primary diagnosis of either Crohn disease (CD) or ulcerative colitis (UC) were selected from the 2006 Kids' Inpatient Database (KID). Length of the hospital stay in days (LOS) and charges for the hospitalization were found directly in the Kids' Inpatient Database, and cost was calculated using the hospital's cost-to-charge ratio. Predictor variables included patient characteristics, such as age and severity of illness, and hospital characteristics. Ordinary-least-squares regressions were developed and estimated to explain hospitalization costs. : In 2006, there were 10,777 IBD-related hospitalizations. The total and mean costs for CD were $66.3 million and $10,176 (95% confidence interval [CI] $9647-$10,705), and for UC were $48.6 million and $11,836 (95% CI $10,760-$12,912). For CD, 0- to 5-year-old patients had the highest mean LOS (8.10, 95% CI 5.53-10.67, days) and mean cost ($13,894, 95% CI $9053-$18,735), whereas, for UC, 11- to 15-year-old patients had the highest mean LOS (7.49, 95% CI 6.88-8.10, 95% CI 5.53-10.67, days) and mean cost ($13,407, 95% CI $11,704-$15,110). : For a pediatric disease with a rather low prevalence rate, the estimated annual inpatient pediatric burden of IBD is a sizeable $152.4 million (2010 US$) and 64,985 days spent in the hospital. As medications and outpatient treatments improve for the treatment of IBD, there is an opportunity for significant reduction in inpatient burden.
Read moreP1055 ChatGPT in clinical practice: A preliminary assessment against ECCO 2025 guidelines for Inflammatory Bowel Disease
Background Inflammatory bowel diseases (IBD) present a major challenge in gastroenterology, requiring personalized management based on up-to-date guidelines, such as those published by the European Crohn’s and Colitis Organisation (ECCO) in July 2025. The emergence of artificial intelligence (AI), particularly ChatGPT, raises questions about its potential role in clinical decision support. This study aims to evaluate the reliability of ChatGPT in providing responses aligned with ECCO 2025 guidelines for IBD. Methods Forty-four questions were posed to ChatGPT across six domains: initial diagnosis (n = 7), patient follow-up (n = 9), imaging and endoscopy (n = 10), colorectal cancer screening (n = 8), disease activity scores (n = 8), and management of pregnant women (n = 2). Each response was reviewed by an IBD expert and categorized into four groups: (1) correct and complete, (2) correct but incomplete, (3) mixed correct and incorrect, (4) incorrect. Results ChatGPT’s performance varied by topic. It was highly reliable in standardized areas, with 85.7% correct and complete responses for initial diagnosis and 100% adherence to ECCO 2025 recommendations for colorectal cancer screening. Responses regarding imaging in Crohn’s disease were 80% correct. However, in areas requiring individualized approaches, such as patient follow-up, only 11% of responses were complete, with frequent errors in surveillance intervals and underestimation of intestinal ultrasound. Responses on disease activity scores were often incomplete, lacking calculation methods and thresholds. Guidance on pregnant women was generally accurate. Conclusion These findings highlight the need for regular updates of AI models to incorporate recent clinical practice evolutions, particularly for personalized patient management. ChatGPT can serve as a useful decision-support tool, but it cannot replace clinical expertise, especially for complex or individualized IBD care. Conflict of interest: Dr. Amine, Meriem: aucun conflit d’intérêt
Read more14Financial Conflicts of Interest in Inflammatory Bowel Disease Guidelines.
Industry payments can lead to financial conflicts of interest (FCOI) among authors of clinical practice guidelines (CPGs). Guidelines for inflammatory bowel disease (IBD) may be at particularly high risk. We determined the prevalence of FCOI in IBD CPGs produced by various gastroenterology societies. We conducted a cross-sectional analysis of FCOI disclosure among CPGs related to the management of IBD. We ascertained the prevalence and types of FCOI for each guideline and determined adherence to National Academy of Medicine (NAM) standards. FCOI disclosures were compared between societies producing CPGs. We identified 11 relevant CPGs with 173 total authors. There were 117 (68%) authors who declared a payment. A total of 107 (62%) authors declared FCOI related to a medication recommended in the guideline. There was a significant difference (P < 0.001) between the proportion of authors with FCOI between countries or regions. Authors of US CPGs had a significantly lower FCOI prevalence (19%) compared with other societies. Authors of UK CPGs had a significantly lower FCOI prevalence (56%) compared with Canadian (84%) and European (94%) CPGs. Three (27%) guidelines adhered to both NAM standards. A substantial portion of authors of IBD CPGs had FCOI. Our study found a significant difference in FCOI prevalence based on CPG sponsor nationality. Most CPGs for IBD did not adhere to NAM standards for FCOI disclosure.
Read moreP067 Immunosuppressive therapy in inflammatory bowel disease patients is associated with reactivation of Herpes Zoster: A tertiary center experience
BACKGROUND: Herpes Zoster (HZ), also known as shingles, is the reactivation of the varicella zoster virus (VZV). The incidence of HZ is 4 per 1,000 person-years. Though HZ can occur at any age and in any population, the incidence increases with age and is up to ten times higher in immunocompromised patients. Vaccine guidelines for inflammatory bowel disease (IBD) patients on immunosuppressive therapy recommend obtaining age appropriate non-live attenuated vaccinations while strongly considering risks and benefits when administering the live-attenuated vaccines. Currently, CDC guidelines recommend the new non-live HZ vaccine, Shingrix, in patients over the age of 50. As this is a non-live vaccine it is safe to administer in patients on immunosuppressive therapy. The purpose of our study was to identify risk factors associated with the development of HZ among IBD patients. METHODS: Using our institution’s electronic research data warehouse, we performed a case-control study including IBD patients enrolled in the prospectively maintained IBD patient database at the University of Chicago IBD Center between January 1, 2005 and January 1, 2017. Controls included individuals presenting to the general gastroenterology and hepatology clinics. The diagnosis of HZ was identified using ICD codes (053.9, 053.19, B029, B028) and documentation of a characteristic rash at the corresponding clinic visit. Demographic variables, disease-related and therapy-related factors including HZ vaccination were recorded. Data were analyzed using Wilcoxon rank-sum test for continuous variables and Fischer’s exact test for dichotomous variables. RESULTS: We identified 88 unique patients encounters (57 IBD, 34 non-IBD) with a diagnosis of HZ. The non-IBD controls primarily included individuals with a history of liver disease (n = 21). The IBD patients were predominantly Caucasian (80%) and of younger age when compared to the control population (P < 0.001). Among the 57 IBD patients, 20 (35%) had active disease and 51 (89%) were on active immunosuppression. There were no other statistically significant demographic features between the groups with regards to active smoking or prior HZ vaccination. Only 6 (19%) IBD patients who were over the age of 50 were vaccinated. IBD patients were more likely to be on active immunosuppression or have a history of immunosuppression (P < 0.001) compared to controls. Despite a high level of active disease and immunosuppression, IBD patients had higher albumin and hemoglobin levels compared to the controls. Following the onset of HZ, there was no significant difference in the onset of post-herpetic neuralgia. CONCLUSION(S): Active immunosuppression in IBD patients is a risk for HZ, but no other variables were identified. The disease course with respect to development of post-herpetic neuralgia is not different compared to controls. Only a small number of eligible patients received vaccination for HZ and none of these developed HZ. Further studies should identify independent risk factors for vaccination or expand the eligibility of vaccination to larger cohorts of patients in order to prevent the onset of HZ.
Read morePMO-236 Are guidelines followed in histology reporting in inflammatory bowel disease (IBD)?
IntroductionIBD has 240 000 suffers in the UK. Diagnosis is made on consideration of clinical, macroscopic, microscopic and radiological findings to classify Crohns disease (CD), ulcerative colitis (UC) and IBD...
Read more309Beyond Gene Discovery in Inflammatory Bowel Disease: The Emerging Role of Epigenetics
Beyond Gene Discovery in Inflammatory Bowel Disease: The Emerging Role of Epigenetics
1232Diagnosis and Management of Primary Sclerosing Cholangitis
Diagnosis and Management of Primary Sclerosing Cholangitis
97Similar functional results and complications after ileal pouch-anal anastomosis in patients with indeterminate vs ulcerative colitis.
Patients who undergo ileal pouch-anal anastomosis (IPAA) for indeterminate colitis (IC) have a pouch complication and pouch loss rate only slightly higher than that associated with ulcerative colitis (UC). The functional outcome in patients with IC is no different from that in patients with UC. Retrospective review of prospectively gathered data comparing complication rates and outcomes of patients with IC vs UC who have undergone IPAA at a single institution during 19 years. University teaching hospital. Between July 1, 1982, and July 1, 2001, 723 patients underwent IPAA, 644 for colonic inflammatory bowel disease. A further breakdown of the latter group revealed 79 patients (12.3%) with IC and 565 (87.7%) with UC. These 2 patient populations were compared with regard to postoperative complications, pouch loss, and functional outcome. Patients with IC and UC were compared with regard to pouch complications, such as J-pouch leak, fistula, cuff abscess, stricture, redo IPAA, Crohn diagnosis, and pouch loss. They were also compared with regard to 24-hour stool frequency and nighttime incontinence at 1, 3, 6, and 9 months after surgery. Approximately 98% of patients had 1 year of follow-up and 89% had long-term follow-up (mean, 78.5 months). Patients with IC were compared with those with UC with regard to pouch complications, such as cuff abscess (1.3% vs 1.6%), J-pouch leak (5.1% vs 2.3%), intra-abdominal abscess (0% vs 1.1%), stricture (7.6% vs 4.8%), and fistula (2.5% vs 1.6%). These 2 groups were also compared with regard to small bowel obstruction (6.3% vs 5.5%), pouchitis (34.2% vs 25.0%), eventual diagnosis of Crohn disease (1.3% vs 0.7%), redo IPAA (1.3% vs 0.9%), and eventual pouch loss (2.5% vs 1.2%). An evaluation of functional results revealed no significant differences between the 2 groups with regard to 24-hour stool frequency or nighttime incontinence. The pathologists classified patients with IC into 3 groups: IC but favor UC (group 1), IC but favor Crohn (group 2), and IC (group 3). Most of the postoperative complications occurred in group 1 patients, but the only pouch loss occurred in those in group 2. The incidences of pouch complications after IPAA were slightly higher in the IC group compared with the UC group, but the differences were not statistically significant. Functional results were the same in both groups. Pouch loss was high in group 2 patients, but was otherwise not significantly higher in the IC group overall (P =.36). Most patients with IC can undergo IPAA and expect an outcome equivalent to that of patients with UC.
Read more96Short and long-term effectiveness and safety of vedolizumab in inflammatory bowel disease: results from the ENEIDA registry.
Effectiveness of vedolizumab in real world clinical practice is unknown. To evaluate the short and long-term effectiveness of vedolizumab in patients with inflammatory bowel disease (IBD). Patients who received at least 1 induction dose of vedolizumab were included. Effectiveness was defined based on Harvey-Bradshaw index (HBI) in Crohn's disease (CD) and Partial Mayo Score (PMS) in ulcerative colitis (UC). Short-term response was assessed at week 14. Variables associated with short-term remission were identified by logistic regression analysis. The Kaplan-Meier method was used to evaluate the long-term durability of vedolizumab treatment. Cox model was used to identify factors associated with discontinuation of treatment and loss of response. 521 patients were included (median follow-up 10months [interquartile range 5-18months]). At week 14, 46.8% had remission and 15.7% clinical response. CD (vs UC), previous surgery, higher CRP concentration and disease severity at baseline were significantly associated with impaired response. The rate of vedolizumab discontinuation was 37% per patient-year of follow-up (27.6% in UC and 45.3% in CD, P<0.01). CD (vs UC), anaemia at baseline, steroids during induction and CRP concentration were associated with lower durability of treatment. Seven per cent of patients developed adverse events, infections being the most frequent. Over 60% of IBD patients respond to vedolizumab. Many patients discontinue treatment over time. CD and disease burden impair both short- and long-term response. Vedolizumab seems to be safe in clinical practice.
Read more83The American Society of Colon and Rectal Surgeons Clinical Practice Guidelines for the Surgical Management of Ulcerative Colitis.
The American Society of Colon and Rectal Surgeons Clinical Practice Guidelines for the Surgical Management of Ulcerative Colitis.
Read more18A Systematic Review of Inflammatory Bowel Disease Epidemiology and Health Outcomes in Sexual and Gender Minority Individuals
A Systematic Review of Inflammatory Bowel Disease Epidemiology and Health Outcomes in Sexual and Gender Minority Individuals
Read more6Inflammatory Bowel Disease Clinical
Inflammatory Bowel Disease Clinical
P-049: Reproducibility of serologic antibody activity at diagnosis and after treatment in pediatric ulcerative colitis and Crohn’s disease
P-049: Reproducibility of serologic antibody activity at diagnosis and after treatment in pediatric ulcerative colitis and Crohn’s disease
Read more
Copyright 2026 Cactus Communications. All rights reserved.
