ABSTRACTObjectiveDifferentiating ulcerative colitis (UC) from Crohn's disease (CD) is challenging, particularly for nonexperts. Although artificial‐intelligence‐based image analysis has advanced endoscopic diagnosis, large language models of inflammatory bowel disease (IBD) require clinical validation. We evaluated the ability of ChatGPT to distinguish UC from CD using colonoscopy (CS) images with and without clinical information.MethodsWe retrospectively analyzed 386 and 161 patients with UC and CD, respectively, with active disease who underwent CS between April 2001 and May 2025. A representative endoscopic image showing severe activity at the initial flare was selected by a nonspecialist. Data were collected on lesion continuity and perianal disease. ChatGPT was asked to (1) classify UC or CD and (2) estimate UC probability using images alone or images plus clinical information. The IBD specialists performed task (1) under the same conditions. Their diagnostic performance was compared.ResultsThe median age of the patients was 36.5 and 28 years in the UC and CD groups, respectively. The diagnostic accuracy without clinical information was 75.6% for ChatGPT and 84.9% for specialists, which increased to 87.4% and 88.7% with clinical information, respectively. The odds ratios for correct diagnosis markedly increased when clinical data were used. Receiver operator curve analysis of ChatGPT showed area under the curves of 0.750 without clinical information and 0.948 with clinical information.ConclusionChatGPT accurately discriminated between UC and CD, with diagnostic accuracy markedly increased via the integration of clinical information, suggesting applicability in clinical practice despite being less accurate than IBD specialists.

Glucagon-like peptide-1 receptor agonists (GLP-1 RAs) are widely prescribed for diabetes and obesity. Recent studies suggest they may negatively affect bowel preparation quality before colonoscopy (CLN), leading to inadequate bowel preparation (IBP) and repeat procedures. We conducted a systematic review and meta-analysis to assess this association. PubMed, Embase and Cochrane databases, along with abstracts from Digestive Disease Week 2024 and the American College of Gastroenterology Meeting 2024, were searched. Outcomes included IBP, repeat CLNs, and the mean difference in Boston Bowel Preparation Scale (BBPS) scores between GLP-1 RA users and non-users. Adjusted odds ratios (OR), for age, sex, body mass index, and diabetes, were pooled. Twelve studies including 123,858 patients (57,699 GLP-1 RA users) were analyzed. GLP-1 RA use was associated with higher IBP risk (OR, 1.55; 95% CI, 1.11-2.16); adjusted analyses confirmed this (OR, 2.35; 95% CI, 2.02-2.74). BBPS scores were lower among GLP-1 RA users (mean difference, -0.68; 95% CI, -0.77 to -0.58). No association with repeat CLNs was observed (OR, 1.5; 95% CI, 0.88-2.56). GLP-1 RA use is linked to inadequate bowel preparation but not repeat CLNs. Further prospective studies are warranted to further evaluate this finding.

Colorectal cancer (CRC) remains a leading cause of cancer-related death. Many of these deaths could be prevented by screening. The German screening program was updated in April 2025, enabling men and women aged 50 and above to choose between fecal immunochemical testing (FIT) once every two years or up to 2 screening colonoscopies (CS) at an interval of 10 years apart. In this study, we compare the expected long-term outcomes for these strategies as well as for a combination of the two, assuming that full use is made of the tests that are offered. We used COSIMO, a validated multi-stage simulation model for CRC, to assess expected outcomes assuming full adherence for simulated cohorts of 100 000 men and women aged 50-85. We calculated and compared the expected cumulative numbers of CRC cases and CRC-related deaths with FIT-based screening, colonoscopy-based screening, and no screening. On the assumption of full adherence, the two screening strategies yielded similar reductions of CRC case numbers (69% for FIT, 77% for CS) and deaths from CRC (82% for both). Even stronger reductions were found if CS at age 50 and 60 was followed by FIT at ages 70, 72, and 74 (81% reduction in CRC cases, 89% reduction in deaths from CRC). The two screening strategies currently offered in Germany are highly effective to a similar extent. Our analysis yields relevant information for informed choices between the alternative screening offers.

Abstract Background Magnetic resonance enterography (MRE) and colonoscopy (CS) are used to monitor disease activity in patients with inflammatory bowel disease (IBD). Intestinal ultrasound (IUS) has emerged as a non-invasive point of care tool for evaluation of disease activity in IBD. Several studies demonstrate that IUS has comparable accuracy to MRE and CS.1,2 We aimed to evaluate the utility of IUS in influencing management change in IBD and the cost-effectiveness of a newly established intestinal ultrasound service in a tertiary IBD unit. Methods A retrospective single-centre review was performed of all IUS examinations conducted for IBD disease activity assessment at a tertiary centre between January 2024 to October 2025. Data collected included patient demographics, diagnosis, prior surgery, impact of IUS on management, and avoidance of additional imaging or colonoscopy. The estimated cost in Australian dollars (AUD) of MRE ($560), CS ($2000) and IUS ($212) were derived from published Australian data to calculate system-wide cost savings. Results A total of 438 IUS examinations were analysed. Of these, 234 (53.4%) were in female patients, with a median age 44 years (IQR: 30-57), 371 (85%) with Crohn’s disease, 57(13%) with ulcerative colitis and 10 (2%) with pouch-disorders. 191 (43.6%) of patients had undergone a prior intestinal surgery. Two-hundred and twenty-five (51.4%) IUS examinations demonstrated active disease. Clinicians altered clinical management based on 175 out of 438 IUS examinations (39.9%). IUS based management avoided 199 MREs and 139 colonoscopies. The total savings from MRE avoided was $111,440, and total savings from CS avoided was $278,000. The total expenditure on IUS was $92,856. The net total cost savings amounted to $296,584. Conclusion IUS is a valuable and cost-effective investigation offering rapid, non-invasive and patient-centred assessment of IBD disease activity. Integration of IUS into routine clinical pathways substantially reduces downstream healthcare utilization by limiting unnecessary invasive and high-cost investigations, improving workflow efficiency and optimizing resource allocation.

We retrospectively evaluated the safety and diagnostic utility of small bowel capsule endoscopy (SBCE) in 45 patients (66 procedures) who developed gastrointestinal symptoms after allogeneic hematopoietic cell transplantation (allo-HCT). Despite a high proportion of patients with poor performance status (≥2: 43 procedures) and thrombocytopenia (platelet counts <20,000/µl in 10 procedures, <50,000/µl in 25 procedures), which are generally considered high-risk conditions for conventional esophagogastroduodenoscopy (EGD) and colonoscopy (CS), SBCE demonstrated a 0% adverse event rate and 89.2% complete small bowel observation rate, which are comparable to outcomes previously reported in non-transplant patients. Evaluation of all three gastrointestinal regions (stomach, small bowel, and colon), including exploratory observation, was feasible in 55 of 66 procedures, and small bowel lesions were identified in 28 procedures. In 6 of these (10.9%), lesions were confined exclusively to the small bowel, making them difficult to detect using conventional EGD and CS, and SBCE findings guided treatment decisions. In conclusion, SBCE can be safely performed in patients with gastrointestinal symptoms after allo-HCT and may provide unique diagnostic value, particularly in the evaluation of small bowel lesions.

ABSTRACTSpontaneous regression of endoscopically invasive colorectal cancer (CRC) after biopsy has been rarely reported. We report three cases of endoscopically invasive CRC with spontaneous regression after biopsy and a review of the literature regarding spontaneous regression of CRC with somatic mismatch repair deficiency (MMR‐d). Case 1 involved a 54‐year‐old man who underwent a colonoscopy (CS) after positive fecal immunohistochemical test. A 15‐mm elevated lesion with a depression was detected in the transverse colon, and biopsy results indicated adenocarcinoma. When surgical resection was performed 8 weeks later, the lesion was no longer present. Case 2 involved a 75‐year‐old man with a 10‐mm elevated lesion with a depression in the ascending colon during screening CS. Biopsy results indicated adenocarcinoma. CS was performed 9 weeks later to tattoo the lesion before surgery; however, it was no longer present at that time. Case 3 involved an 84‐year‐old man who underwent surveillance CS after polyp resection and a 12‐mm elevated lesion with a depression was observed in the rectum. Biopsy results indicated adenocarcinoma; therefore, endoscopic resection was scheduled. CS performed 8 weeks later showed the disappearance of the lesion. Mismatch repair deficiency was detected in two of these three patients. The literature search identified 12 cases with the evaluation of MMR, including our three cases, which showed spontaneously regressing colorectal cancer. All 12 lesions had depression; 11 were located on the proximal colon, and 11 cases showed MMR‐d.

Background and study aimsAnalyses of colonoscopy (CS) and esophagogastroduodenoscopy (EGD) complications is crucial for further promoting use of endoscopy. This study analyzed rates of severe complications of CS compared with those of EGD using big data.Patients and methodsAs a study population, we retrospectively used commercially anonymized health insurance claims data covering 3,050,954 patients from January 2010 to December 2020. Patients ≥ 50 years old who underwent CS or EGD without treatment were included in the study. The main outcomes were differences in rates of hemorrhage, perforation, and fatal events between EGD and CS, and risk factors of each complication comparing CS with EGD.ResultsAmong 290,470 CSs (male: 182,910, female: 107,560, median age [range]: 58 [50–75]) and 726,075 EGDs (male: 412,365, female: 313,710, 58 [50–75]), rates of hemorrhage, perforation, and fatal events for EGD and CS were 0.0069% vs. 0.0069% (P= 0.558), 0.0006% vs. 0.0024% (P= 0.008), and 0.00028% vs. 0.00034% (P= 0.648), respectively. Rates of hemorrhage for cases aged 50 to 64 and 65 to 75 years were 0.0059% vs. 0.0110% (P= 0.042) for EGD and 0.0061% vs. 0.0108% for CS (P= 0.264). Risks of hemorrhage for comparing CS to EGD were significant for biopsy (adjusted odds ratio [aOR] 95% confidence interval [CI] 2.75 [1.15–6.21];P= 0.017) and antithrombotics (aOR 12.48; 95% CI 1.80–247.14;P= 0.026). Those for perforation were significant for ages 50 to 64 years (aOR 9.58; 95% CI 2.17–66.10;P= 0.006) and male sex (11.76 [1.85–222.65],P= 0.025).ConclusionsCompared with EGD, CS had a higher rate of perforation but not hemorrhage. Complication rates in CS did not differ by age.

Evidence-based decision analysis guiding clinical guidelines for an organized population-based screening for colorectal cancer.

Sudden decrease of colonoscopy (CS) numbers can be related to the status of colorectal cancer (CRC). This study aimed to evaluate the statuses of CS and CRC according to big national disasters such as the Great East Japan Earthquake in 2011 and the COVID-19 epidemic in 2020. We retrospectively used the JMDC database of commercially anonymized health insurance claims data including 4,601,921 patients ≥ 50 years old from January 2010 to December 2022 (without health checkups of CS and esophagogastroduodenoscopy [EGD]). The main outcome was a yearly analysis for 2010-2022 about (1) rate of CS, (2) rate of CRC and rate of CRC per CS compared to those of EGD and gastric cancer (GC), and (3) rate of surgery for CRC. Additionally, a monthly analysis for those rates was performed to examine the detailed effect of the earthquake and COVID-19 infection. The rates of CS and EGD in 2010/2011/2012 were 3.10%/3.41%/3.42% and 6.94%/6.96%/7.00% and those in 2019/2020/2021 were 5.20%/4.74%/5.37% and 7.47%/6.42%/6.84%, respectively. The rates of CS and EGD decreased not in 2011 (The earthquake) but in 2020 (COVID-19). The rates of CRC and GC in 2019/2020/2021 were 0.199%/0.175%/0.195% and 0.110%/0.096%/0.099%, and both showed a decrease in 2020. Monthly analysis showed that the rate of CRC per CS had an increase in April and May in 2020 compared to that in March of 2020. The rate of surgery for CRC in 2019/2020/2021 was 0.087%/0.079%/0.087% with a deficiency in 2020. The rates of CS and CRC decreased in 2020 due to COVID-19.

We found a 15mm, 0-IIa + IIc polyp in the rectosigmoid with colonoscopy (CS), and performed endoscopic submucosal dissection (ESD) for it. The histopathologic specimen revealed that it was well-differentiated adenocarcinoma, T1b (SM2, 2000μm), Ly0, v0, BD1, pHM0, and pVM0. Despite the non-curative resection with SM-deep invasion, the patient chose careful follow-up with contrast-enhanced computed tomography and CS. A nodule was first detected on the left side just out of the lower rectum 3 and a half years after ESD. Since it enlarged gradually, we judged that it was local recurrence in form of lymph-node metastasis and performed additional surgery 5years after ESD. Pathological findings disclosed that the nodule was local recurrence as a tumor deposit (TD). One year after TD resection, lung metastasis was additionally founded and was resected surgically. If ESD accomplishes complete resection for T1b colorectal cancer and deep submucosal invasion is the only factor of non-curative resection, follow-up may be chosen instead of additional surgical resection. However, careful follow-up should be considered, because recurrence including TD may happen several years after ESD.

e15655 Background: LS is among the most common hereditary CA syndromes, characterized by autosomal dominant inheritance of mismatch repair deficiency with increased lifetime risk of multiple CA types. While intensive screening can lower risk of LS-associated CAs, additional preventive measures could be broadly beneficial for motivated patients (pts). Our recent study (Singhal S et al, JCO Precision Oncology 2024), however, found that pts with LS reported only modest uptake of daily ASA/NSAIDs, a proven prevention option. In this study, we examine perceptions of dietary interventions as an alternative CA prevention option in a multi-national cohort of pts w/LS. Methods: PREVENTLynch study recruited pts w/LS to complete an online survey about screening behaviors and perceptions of novel prevention options. Pts were recruited through the Fox Chase Cancer Center (FCCC) Risk Assessment Program Registry and invitations posted via LS advocacy websites. In addition to reporting demographic factors, personal history, and screening behaviors, pts rated five dietary interventions: resistant starch supplements (RS), vitamin supplements (VS), online nutritional feedback (ONF), intermittent fasting (IF), and low inflammatory index diet (LID) (scale 0-10, low-to-high). Pts evaluated each intervention for perceived inconvenience, concern for side effects, reassurance to reduce CA risk, and study participation interest. Perception scores were colonoscopy (CO) benchmarked. Differences were tested by rank sum testing (Wilcoxon). The study was IRB approved (FCCC #20-8014). Results: A total of 296 responses were received. Participants were diverse by age [8% &lt; 35 yr, 74% 35-65 yr, 18% &gt; 65 yr] and location (39 states; 15% non-US based) but predominantly female (84%) and non-Hispanic white (92%). VS (1.77), ONF (1.94) and RS (2.00) were significantly more convenient than CO (3.40) (p &lt; 0.001). Perceived side effects of ONF (1.81) (p &lt; 0.001) were lowest compared to CO (2.46), especially in US participants (1.73) vs non-US (2.31) (p &lt; 0.05). In contradistinction, CO reassurance (8.25) was significantly higher than all interventions (VS 5.04, RS 4.85, NF 5.72, OF 4.95, LI 5.04, all p &lt; 0.001). Notably, pts with neoplasia history had the lowest reassurance from IF (4.73, p &lt; 0.001), while non-US participants rated VS (3.49 vs 5.28), IF (4.08 vs 5.10) and LI (4.4 vs 5.24) (all p &lt; 0.001) significantly less favorably. Study participation interest was highest for RS (7.31) and NF (7.06) and lowest for IF (6.31). Conclusions: Dietary interventions show promise as low-risk adjuncts to CO surveillance with favorable perceived acceptability and side effects among LS pts. Our findings highlight the importance of considering pt preferences when developing and testing risk-reducing interventions to maximize real-world uptake and downstream effectiveness.

ObjectiveTo compare water-assisted colonoscopy (WAC) using the water immersion technique with conventional carbon dioxide insufflation colonoscopy (CC) in novice endoscopists, focusing on procedure time, safety and learning curves.MethodsWe conducted a prospective, randomised (1:1), single-centre trial at Chiang Mai University Hospital, Thailand. Six gastroenterology fellows with <150 prior colonoscopies received standardised training before performing elective screening colonoscopies using either WAC or CC techniques. Patients were randomly assigned to WAC or CC groups. The primary outcome was caecal intubation time (CIT). Secondary outcomes included technical failure, procedural difficulty, patient discomfort, complications, withdrawal time and adenoma detection rate (ADR).ResultsOf 250 randomised patients, 230 completed the protocol (WAC, n=113; CC, n=117). Mean CIT was comparable between groups (10.6±4.2 min vs 9.8±3.9 min; p=0.35). Technical failure occurred in 6.2% of WAC and 5.1% of CC procedures, with no significant differences in procedural difficulty ratings, analgesic requirements or patient discomfort scores. ADR was similar between arms (40.7% vs 33.3%; p=0.25). Learning curves demonstrated parallel, progressive reductions in CIT among fellows in both groups.ConclusionWAC is a safe and effective alternative to CC for novice endoscopists, with similar procedure times, learning curves and safety profiles. These findings support the inclusion of WAC in gastroenterology training programmes.Trial registration numberTCTR20230324001.

Screening colonoscopies (CS) performed before prostate stereotactic body radiation therapy (SBRT) allow for identifying synchronous malignancies and comorbid gastrointestinal (GI) conditions. Performing these procedures prior to radiation precludes the necessity of post-SBRT pelvic instrumentation, which may lead to severe toxicity and fistulization. We review compliance of CSs, incidence of GI pathology, and the impact of pretreatment CS findings on subsequent physician-reported toxicity and patient-reported quality of life (QoL). We reviewed an institutional database of patients treated for prostate cancer with SBRT including toxicity and QoL outcomes. A detailed review of pretreatment CS findings was reviewed including identification of diverticulosis, location of polyp resection, and presence of hemorrhoids. Pretreatment CS findings were then correlated with outcomes following SBRT. Identification of comorbid GI conditions was a common event, with the presence of diverticulosis in 49.5% (n = 100), hemorrhoids in 67% (n = 136), and polyps in 48% (n = 98). More than half of patients with polyps removed had at least 1 removed from the rectosigmoid. Pretreatment CS did not introduce a delay in SBRT start date. Grade 1 toxicity was significantly lower in patients who underwent CS closer to the initiation of SBRT. There was no increased risk of physician-graded toxicity in the presence of diverticulosis, hemorrhoids, or polyps. Patient-reported GI QoL pattern in our screening cohort mimicked that seen in the previously published nonscreened population. There was no overt QoL detriment observed in patients who had GI pathology identified before SBRT. GI pathology identified in our elderly patient population was commonly identified on pretreatment CS. Screening CS may optimize bowel health for patients heading into radiation therapy. Toxicity and QoL for patients with GI pathologies identified on pretreatment CS do not preclude the delivery of prostate SBRT. We advocate for pretreatment CS in patients eligible prior to SBRT.

Anesthesiologists are often tasked with overseeing sedation in non-surgical settings. We aim to determine whether adding adjuvant sedatives to propofol affects the recovery times and complication rates after endoscopy. We conducted a retrospective cohort study of adults (≥18) who received propofol while undergoing esophagogastroduodenoscopy (EGD) and/or colonoscopy (COL) at a large academic institution over a four-year period. Patients receiving propofol alone were compared against patients receiving propofol in combination with midazolam, fentanyl, ketamine, or dexmedetomidine. The primary outcome was PACU length of stay, adjusted for age, sex, and ASA Score. Secondary outcomes included incidence of PACU postoperative nausea and vomiting, hypoxemia (SpO2 < 90%), bradycardia (HR < 60 bpm), and escalation of care (hospital admission), reported in adjusted odds ratios and their 95% confidence intervals. Across the study period, 28,532 cases were included. Colonoscopies performed under propofol+fentanyl sedation were associated with significantly longer PACU LOS compared to propofol alone. Adjusted mean PACU LOS was significantly longer in patients receiving adjuvant fentanyl, compared to propofol alone (p < 0.01) and propofol + dexmedetomidine (p < 0.01). Patients receiving propofol alone exhibited a 9.4% incidence of bradycardia, 16.0% hypoxia, 0.89% PONV, and 0.40% hospitalization. Adjuvant fentanyl use was associated with higher odds of hypoxia across all procedure types (p < 0.05). Adjuvant dexmedetomidine was associated with higher rates of bradycardia, but lower rates of hypoxia, PONV, and hospitalization (p < 0.05). With the exception of fentanyl, combining propofol with other sedatives was not associated with longer recovery times. The incidence of complications differed significantly with the use of adjuvant fentanyl or dexmedetomidine.

18 Background: Despite availability of various screening options, nearly 40% of eligible U.S. adults were not up to date with the colorectal cancer (CRC) screening. Blood-based testing offers a promising complementary approach and may enhance patient adherence among unscreened individuals. In the PREEMPT CRC study, we evaluated clinical performance of an investigational blood-based screening test for detecting molecular signals of advanced colorectal neoplasia (ACN) in an average-risk population. Freenome blood-based CRC screening test met all primary endpoints demonstrating 79.2% sensitivity for CRC, 91.5% specificity for ACN, 90.8% negative predictive value (NPV) for ACN and 15.5% positive predictive value (PPV) for ACN. Sensitivity for advanced precancerous lesions (APLs) was 12.5%. To evaluate how the test would perform in the standard U.S. population, an analysis of test performance weighted to the U.S. census sex and age distribution was prespecified and performed. Methods: Between May 2020 and April 2022, the study enrolled participants aged 45-85 at average risk for CRC. Enrolled participants had a blood drawn before the bowel preparation for the standard of care screening colonoscopy (CS). CS and applicable histopathology reports underwent central pathologist review. Blood samples were processed blind to clinical findings. Primary endpoints included sensitivity for CRC, specificity for ACN, NPV for ACN and PPV for ACN. A secondary endpoint was sensitivity for APLs. Results: A subset of 32,731 sequentially enrolled participants were included in the clinical validation cohort. Out of those, 27,010 (82.5%) had evaluable blood samples and CS. The median age of the evaluable participants was 57.0 years, and 55.8% were women versus 50.5% in the U.S. Census. Age distribution included 11.0% participants in the 45-49 age group versus 15.3% in the U.S. Census, 33.0% in the 50-54 age group versus 15.6%, and 32.3% in the 55-64 age group versus 32.3%, 20.8% in the 65-74 age group versus 24.3%, 3.0% participants aged 75 or older versus 12.5%. After performance was weighted to match U.S. Census sex and age distributions, sensitivity for CRC was 81.1% (95% CI 71.3%-88.1%), specificity for those without ACN was 90.4% (95% CI 90.0%-90.7%), NPV for those without ACN was 90.5% (95% CI 90.5%-90.7%), and PPV for ACN was 15.5% (95% CI 13.8%-16.2%). Sensitivity for APL was 13.7% (95% CI 12.4%-15.0%). Conclusions: PREEMPT CRC is the largest study evaluating a CRC screening blood-based test to date. The study successfully met all primary endpoints, demonstrating acceptable clinical performance of the investigational blood-based test. The U.S. census sex-age adjusted clinical performance estimates showed improvement in CRC and APL sensitivity. This blood-based test may provide a convenient and effective option for CRC screening in the average-risk U.S. population. Clinical trial information: NCT04369053 .

Studies aimed to evaluate the expected impact of alternative screening strategies are essential for optimizing colorectal cancer (CRC) screening offers, but such studies are lacking in Germany, where two screening colonoscopies (CS) 10 years apart are offered for men from age 50 and women from age 55. Our aim was to explore whether and to what extent the efficacy of utilizing two CS could be enhanced by alternative starting ages and screening intervals. We modeled the expected numbers of CRC cases, CRC deaths, years of potential life lost (YPLL), and disability‐adjusted life years (DALYs) due to CRC in hypothetical cohorts of 100,000 men and women aged 45–85 using COSIMO, a validated Markov‐based multi‐state simulation model. Modeled strategies included combinations of starting ages (45/50/55/60) and CS (10/15/20 years). For men, CRC deaths could be slightly reduced by extending the interval to 15 years, with a second CS at 65. YPLL and DALYs would be reduced by decreasing starting age to 45 when combined with a 15‐year screening interval. For women, use of two CS at ages 50 and 65 would reduce all CRC burden parameters compared to the current earliest‐use offer at 55 and 65 years. Our results suggest that lowering the starting age of screening colonoscopy to 45 for men and 50 for women, combined with extending the CS screening interval to 15 years would have the potential to enable significant reductions in years of potential life lost, and disability‐adjusted life years compared to current screening offers in Germany.

Introduction: Around 15 million colonoscopies (CS) and 6-7 million esophagogastroduodenoscopy (EGDs) are performed annually in the United States. The prevalence of a clear understanding of CS and EGD among patients can vary significantly based on several factors, including communication, educational resources, and individual patient characteristics like level of education. Educational disparities exist, with 37% population having no more than a high school diploma and only 14% having advanced education. Previous studies showed that simplified instructions improved bowel preparation quality, and cancellation rates were reduced to half. However, there are no studies customizing these instructions per patient literacy level. With an aim to enhance awareness and comprehension, we aimed to explore the potential role of Chat Generative Pre-Trained Transformer (ChatGPT) to determine how it could assist in simplifying text for improved understanding. Methods: We used the American College of Gastroenterology patient education resources on CS and EGD, for their overview, indications, sedation, preparation, procedure, risks and alternative tests. We asked ChatGPT to modify the text so that someone who is at a 6th-grade level or below can understand it. To assess the education level of a specific text we compared the original and modified texts for their Flesch-Kincaid Grade Level (FKGL), Flesch Reading Ease Score (FRES), Reading Level, Average Words per Sentence, and Average Syllables per Word. We analyzed the statistical significance using a paired t-test. Results: The average original FKGL before and after modification by ChatGPT was: CS (12.38 and 7.12) and EGD (6.48 and 5.20). Using ChatGPT there was a significant change in FKGL, FRESe Score (FRES), Reading Level, Average Syllables per Word, and Total Words (Table 1). Noticeably, there was a significant reduction in text for the topic of bowel preparation for CS eliminating many medical terms compared to other topics. Conclusion: Our study showed that ChatGPT can make medical information about CS and EGD easier to understand and more usable to people with varying literacy levels. The modifications made by ChatGPT were statistically significant (P-value < 0.05), indicating successful text simplification. This demonstrates that AI can effectively convey information and tailor it to specific audiences. This pilot study would drive further research to address patient education despite the educational, gender, racial, ethnic, socioeconomic and regional disparities. Table 1. - Comparison of Patient Education Text before (Pre) and after (Post) ChatGPT's modification for Colonoscopy and Esophagogastroduodenoscopy using text assessment scores Sub-topic FKGL (Pre) FKGL (Post) FRES (Pre) FRES (Post) RL (Pre) RL (Post) Avg. W/S (Pre) Avg. W/S (Post) Avg. S/W (Pre) Avg. S/W (Post) Avg. Sentences (Pre) Avg. Sentences (Post) Avg. Words (Pre) Avg. Words (Post) Colonoscopy Overview 11.9 8.6 39.8 52.2 College 10th & 12 grade 14.5 10.7 1.8 1.7 31 23 448 247 Indications 13.9 7.5 38.6 66 College 8th & 9th grade 24.1 13.7 1.7 1.5 11 9 265 123 Alternative Screening Methods 12.1 6.9 32.4 62 College 8th & 9th grade 13.5 9.3 1.9 1.6 11 7 149 65 Bowel Preparation 10.5 6 47.3 69.8 College 8th & 9th grade 15.5 10 1.7 1.5 27 5 418 50 Complications 13.5 6.6 28.8 62.9 College 8th & 9th grade 17 8.4 1.9 1.6 7 9 119 76 p value (Paired t-test) 0.001* 0.002* NA 0.007* 0.004* 0.175 0.042* Esophagogastroduodenoscopy Overview 8.9 7.4 56.9 66.2 10th & 12 grade 8th & 9th grade 14.4 13.5 1.6 1.5 14 13 202 175 Indications 9.2 5.3 40 71.6 College 7th grade 6 8.2 1.9 1.5 26 11 155 90 Sedation 6.1 4.8 69.6 78.2 8th & 9th grade 7th grade 10.2 10 1.5 1.4 10 9 102 90 Preparation 8.8 5.5 51.9 76.6 10th & 12 grade 7th grade 11 11.6 1.7 1.4 8 7 88 81 Before Procedure 7.1 4.2 67 85.4 8th & 9th grade 6th grade 12.7 11.3 1.5 1.3 6 6 76 68 During Procedure 6.4 5.3 74.3 76.9 7th grade 7th grade 13.9 11.3 1.4 1.4 7 6 97 68 After Procedure 7 5.8 67.2 75.6 8th & 9th grade 7th grade 12.5 12.6 1.5 1.4 6 5 75 63 Complications 4.3 5.2 74.3 71.9 7th grade 7th grade 5.6 7.9 1.5 1.5 11 8 62 63 Alternative Screening Methods 7.6 5.5 65.6 81.8 8th & 9th grade 6th grade 14.1 14.8 1.5 1.3 11 6 155 89 p value (Paired t-test) 0.005* 0.007* NA 0.872 0.008* 0.082 0.017* Footnotes: (1) Abbreviations: Pre (Text before ChatGPT's modification), Post (Text after ChatGPT's modification), FKGL (Flesh-Kincaid Grade Level), FRES (Flesch Reading Ease Score), RL (Reading Level), Avg. (Average), W/S (Words per Sentence), S/W (Syllables per Word), NA (Not Applicable); (2) Bold* P-values are statistically significant (P<0.05)

Since a standard sedation protocol for pediatric colonoscopy (CS) has not been established, evidence on optimal sedative agents is needed. This study aimed to evaluate the efficacy and safety of thiamylal in sedation for pediatric CS compared to midazolam. Children from 7 to 16 years of age who underwent CS under sedation with intravenous thiamylal or midazolam at our hospital between June 2010 and March 2024 were included in this retrospective observational study. The primary outcome was the efficacy (success rate of CS without mid-awakening) of the drugs. Meanwhile, the secondary outcomes were the sedation level during CS, procedure time, recovery time, and adverse events related to sedation. Sixty children were included in the study. The success rate of CS without mid-awakening was significantly higher in the thiamylal group (90.6%) than in the midazolam group (64.3%; p = 0.03). The two groups had no significant differences in median sedation depth, procedure time, or recovery time. Adverse events related to sedation in thiamylal group (22%) and midazolam group (25%) were similar. No severe adverse events were reported. Intravenous thiamylal provides effective and safe sedation in children requiring CS, with little or no mid-awakening during the procedure.

Background and AimsThe utilization of artificial intelligence (AI) with computer‐aided detection (CADe) has the potential to increase the adenoma detection rate (ADR) by up to 30% in expert settings and specialized centers. The impact of CADe on serrated polyp detection rates (SDR) and academic trainees ADR & SDR remains underexplored. We aim to investigate the effect of CADe on ADR and SDR at an academic center with various levels of providers' experience.MethodsA single‐center retrospective analysis was conducted on asymptomatic patients between the ages of 45 and 75 who underwent screening colonoscopy. Colonoscopy reports were reviewed for 3 months prior to the introduction of GI Genius™ (Medtronic, USA) and 3 months after its implementation. The primary outcome was ADR and SDR with and without CADe.ResultsTotally 658 colonoscopies were eligible for analysis. CADe resulted in statistically significant improvement in SDR from 8.92% to 14.1% (P = 0.037). The (ADR + SDR) with CADe and without CADe was 58% and 55.1%, respectively (P = 0.46). Average colonoscopy (CSC) withdrawal time was 17.33 min (SD 10) with the device compared with 17.35 min (SD 9) without the device (P = 0.98).ConclusionIn this study, GI Genius™ was associated with a statistically significant increase in SDR alone, but not in ADR or (ADR + SDR), likely secondary to the more elusive nature of serrated polyps compared to adenomatous polyps. The use of CADe did not affect withdrawal time.

The treatment strategy for patients with ulcerative colitis (UC) in clinical remission who have not achieved mucosal healing is unclear. This study aimed to determine the risk factors of relapse in patients in clinical remission with endoscopic activity. This retrospective, single-center study included patients with UC who underwent colonoscopy (CS) and were in clinical remission with endoscopic activity. Characteristics were compared between patients who relapsed within 2 years after CS and those who did not. A Cox proportional hazards regression model was used to identify risk factors contributing to clinical relapse. Recent worsening in bowel symptoms was defined as increase in bowel frequency and/or increase in abdominal pain within approximately 1 month based on the descriptions in the medical charts. This study regarded 142 patients in clinical remission with an endoscopic activity of Mayo endoscopic subscore (MES) of ≥1 as eligible, and 33 (23%) patients relapsed during the observation period. Recent worsening of bowel symptoms was a significant risk factor for clinical relapse (hazard ratio [HR]: 3.02, 95% confidence interval [CI]: 1.34-6.84). This was particularly evident in patients with MES of 2 (HR: 5.16, 95% CI: 1.48-18.04), whereas no risk factors were identified in patients with MES of 1. The presence or absence of therapeutic intervention just after CS did not significantly affect clinical relapse. Recent worsening in bowel symptoms was a significant risk factor for clinical relapse in patients with UC who were in clinical remission with endoscopic activity.