Comparative outcomes of endoscopic mucosal resection for laterally spreading lesions in inflammatory bowel disease.

BACKGROUND: The role of endoscopic mucosal resection (EMR) for laterally spreading lesions (LSLs) in inflammatory bowel disease (IBD) remains controversial despite its effectiveness in the general population. We aimed to characterize outcomes of EMR for IBD-associated LSLs compared with controls without IBD. METHODS: We performed a retrospective observational cohort study of patients with IBD who underwent EMR and endoscopic follow-up for LSLs, compared with a control group without IBD. The primary outcome was histologic recurrence. Secondary outcomes included en bloc resection and adverse events. Factors associated with recurrence were identified using multivariate mixed effects logistic regression. RESULTS: 210 premalignant lesions in 155 patients were included. By histology, 91.0% were adenoma/low grade dysplasia or sessile serrated lesions. Median (IQR) lesion size was 25 (12-30) mm in the IBD group and 20 (12-30) mm in the control group. Recurrence was detected in 30.4% of IBD-associated lesions (7/23) compared with 20.9% of controls (39/187; odds ratio [OR] 2.51, 95%CI 0.59-10.71). En bloc resection was less common in the IBD group (2/23 [8.7%], 95%CI 1.1-28.0) versus controls (106/187 [56.7%], 95%CI 50.4-65.2). After adjusting for lesion size and histology, recurrence appeared more common in patients with IBD compared with controls (OR 3.08, 95%CI 1.04-9.13). CONCLUSIONS: Recurrence of LSLs after EMR appeared to be more frequent in patients with IBD. Given the added complexity, EMR in patients with IBD should be performed in expert centers with close endoscopic surveillance.

Artificial intelligence for gastric cancer in endoscopy: From diagnostic reasoning to market.

Recognition of gastric conditions during endoscopy exams, including gastric cancer, usually requires specialized training and a long learning curve. Besides that, the interobserver variability is frequently high due to the different morphological characteristics of the lesions and grades of mucosal inflammation. In this sense, artificial intelligence tools based on deep learning models have been developed to support physicians to detect, classify, and predict gastric lesions more efficiently. Even though a growing number of studies exists in the literature, there are multiple challenges to bring a model to practice in this field, such as the need for more robust validation studies and regulatory hurdles. Therefore, the aim of this review is to provide a comprehensive assessment of the current use of artificial intelligence applied to endoscopic imaging to evaluate gastric precancerous and cancerous lesions and the barriers to widespread implementation of this technology in clinical routine.

Balanced Solution versus Normal Saline in Predicted Severe Acute Pancreatitis: A Stepped Wedge Cluster Randomized Trial.

OBJECTIVE: To compare the effect of balanced multielectrolyte solutions(BMES) versus normal saline(NS) for intravenous fluid on chloride levels and clinical outcomes.in patients with predicted severe acute pancreatitis (pSAP). SUMMARY BACKGROUND DATA: Isotonic crystalloids are recommended for initial fluid therapy in acute pancreatitis, but whether the use of BMES in preference to NS confers clinical benefits is unknown. METHODS: In this multicenter, stepped-wedge, cluster-randomized trial, we enrolled patients with pSAP (APACHE II score ≥8 and C-reactive protein >150 mg/L) admitted within 72 hours of the advent of symptoms. The study sites were randomly assigned to staggered start dates for one-way crossover from the NS phase (NS for intravenous fluid) to the BMES phase(Sterofudin for intravenous fluid). The primary endpoint was the serum chloride concentration on trial day3. Secondary endpoints included a composite of clinical and laboratory measures. RESULTS: Overall, 259 patients were enrolled from eleven sites to receive NS(n=147) or BMES(n=112). On trial day3, the mean chloride level was significantly lower in patients who received BMES(101.8 mmol/L(SD4.8) versus 105.8 mmol/L(SD5.9), difference -4.3 mmol/L [95%CI -5.6 to -3.0 mmol/L];P<0.001). For secondary endpoints, patients who received BMES had less systemic inflammatory response syndrome(19/112,17.0% versus 43/147,29.3%, P=0.024) and increased organ failure-free days (3.9 d(SD2.7) versus 3.5days(SD2.7), P<0.001) by trial day7. They also spent more time alive and out of ICU(26.4 d(SD5.2) versus 25.0days(SD6.4), P=0.009) and hospital(19.8 d(SD6.1) versus16.3days(SD7.2), P<0.001) by trial day30. CONCLUSIONS: Among patients with pSAP, using BMES in preference to NS resulted in a significantly more physiological serum chloride level, which was associated with multiple clinical benefits(Trial registration number: ChiCTR2100044432).

ChatGPT4 Outperforms Endoscopists for Determination of Postcolonoscopy Rescreening and Surveillance Recommendations.

BACKGROUND & AIMS: Large language models including Chat Generative Pretrained Transformers version 4 (ChatGPT4) improve access to artificial intelligence, but their impact on the clinical practice of gastroenterology is undefined. This study compared the accuracy, concordance, and reliability of ChatGPT4 colonoscopy recommendations for colorectal cancer rescreening and surveillance with contemporary guidelines and real-world gastroenterology practice. METHODS: History of present illness, colonoscopy data, and pathology reports from patients undergoing procedures at 2 large academic centers were entered into ChatGPT4 and it was queried for the next recommended colonoscopy follow-up interval. Using the McNemar test and inter-rater reliability, we compared the recommendations made by ChatGPT4 with the actual surveillance interval provided in the endoscopist's procedure report (gastroenterology practice) and the appropriate US Multisociety Task Force (USMSTF) guidance. The latter was generated for each case by an expert panel using the clinical information and guideline documents as reference. RESULTS: Text input of de-identified data into ChatGPT4 from 505 consecutive patients undergoing colonoscopy between January 1 and April 30, 2023, elicited a successful follow-up recommendation in 99.2% of the queries. ChatGPT4 recommendations were in closer agreement with the USMSTF Panel (85.7%) than gastroenterology practice recommendations with the USMSTF Panel (75.4%) (P < .001). Of the 14.3% discordant recommendations between ChatGPT4 and the USMSTF Panel, recommendations were for later screening in 26 (5.1%) and for earlier screening in 44 (8.7%) cases. The inter-rater reliability was good for ChatGPT4 vs USMSTF Panel (Fleiss κ, 0.786; 95% CI, 0.734-0.838; P < .001). CONCLUSIONS: Initial real-world results suggest that ChatGPT4 can define routine colonoscopy screening intervals accurately based on verbatim input of clinical data. Large language models have potential for clinical applications, but further training is needed for broad use.

A machine learning-based choledocholithiasis prediction tool to improve ERCP decision making: a proof-of-concept study.

BACKGROUND: Previous studies demonstrated limited accuracy of existing guidelines for predicting choledocholithiasis, leading to overutilization of endoscopic retrograde cholangiopancreatography (ERCP). More accurate stratification may improve patient selection for ERCP and allow use of lower-risk modalities. METHODS: A machine learning model was developed using patient information from two published cohort studies that evaluated performance of guidelines in predicting choledocholithiasis. Prediction models were developed using the gradient boosting model (GBM) machine learning method. GBM performance was evaluated using 10-fold cross-validation and area under the receiver operating characteristic curve (AUC). Important predictors of choledocholithiasis were identified based on relative importance in the GBM. RESULTS: 1378 patients (mean age 43.3 years; 61.2% female) were included in the GBM and 59.4% had choledocholithiasis. Eight variables were identified as predictors of choledocholithiasis. The GBM had accuracy of 71.5% (SD 2.5%) (AUC 0.79 [SD 0.06]) and performed better than the 2019 American Society for Gastrointestinal Endoscopy (ASGE) guidelines (accuracy 62.4% [SD 2.6%]; AUC 0.63 [SD 0.03]) and European Society of Gastrointestinal Endoscopy (ESGE) guidelines (accuracy 62.8% [SD 2.6%]; AUC 0.67 [SD 0.02]). The GBM correctly categorized 22% of patients directed to unnecessary ERCP by ASGE guidelines, and appropriately recommended as the next management step 48% of ERCPs incorrectly rejected by ESGE guidelines. CONCLUSIONS: A machine learning-based tool was created, providing real-time, personalized, objective probability of choledocholithiasis and ERCP recommendations. This more accurately directed ERCP use than existing ASGE and ESGE guidelines, and has the potential to reduce morbidity associated with ERCP or missed choledocholithiasis.

Population-based evaluation of disparities in stomach cancer by nativity among Asian and Hispanic populations in California, 2011-2015.

BACKGROUND: Stomach cancer incidence presents significant racial/ethnic disparities among racial/ethnic minority groups in the United States, particularly among Asian and Hispanic immigrant populations. However, population-based evaluation of disparities by nativity has been scarce because of the lack of nativity-specific population denominators, especially for disaggregated Asian subgroups. Population-based stomach cancer incidence and tumor characteristics by detailed race/ethnicity and nativity were examined. METHODS: Annual age-adjusted incidence rates were calculated by race/ethnicity, sex, and nativity and tumor characteristics, such as stage and anatomic subsite, were evaluated using the 2011-2015 California Cancer Registry data. For Hispanic and Asian populations, nativity-specific population counts were estimated using the US Census and the American Community Survey Public Use Microdata Sample data. RESULTS: During 2011-2015 in California, 14,198 patients were diagnosed with stomach cancer. Annual age-adjusted incidence rates were higher among foreign-born individuals than their US-born counterparts. The difference was modest among Hispanics (∼1.3-fold) but larger (∼2- to 3-fold) among Chinese, Japanese, and Korean Americans. The highest incidence was observed for foreign-born Korean and Japanese Americans (33 and 33 per 100,000 for men; 15 and 12 per 100,000 for women, respectively). The proportion of localized stage disease was highest among foreign-born Korean Americans (44%); a similar proportion was observed among US-born Korean Americans, although numbers were limited. For other Asians and Hispanics, the localized stage proportion was generally lower among foreign-born than US-born individuals and lowest among foreign-born Japanese Americans (23%). CONCLUSIONS: Nativity-specific investigation with disaggregated racial/ethnic groups identified substantial stomach cancer disparities among foreign-born immigrant populations.

A Preliminary Controlled Trial of Endoscopic Ultrasound-guided Fiducial Markers to Guide Pancreas Surgery.

OBJECTIVE: Endoscopic ultrasound (EUS) is routinely used for fiducial marker placement (FMP) to guide stereotactic radiation of pancreatic tumors, but EUS-FMP explicitly to guide surgery has not been studied in a prospective, controlled manner. Multipurpose EUS systems have been developed that facilitate simultaneous EUS-FMP at the time of biopsy. We aimed to evaluate the feasibility of EUS-FMP to guide pancreatic resection. METHODS: In this prospective trial, we enrolled patients with resectable pancreas masses undergoing tissue sampling and placed preloaded fiducials immediately after biopsy. Intraprocedure confirmation of carcinoma, neuroendocrine, and nonlymphomatous neoplasia by rapid on-site evaluation and lesion size <4 cm was required. The main outcomes were the feasibility and ease of preoperative placement and intraoperative detection of the markers using predefined Likert scales. RESULTS: In 20 patients, EUS-FMP was successful before planned surgery and placement was technically straightforward (Likert Scale: 9.1 ± 1.3; range: 1, most challenging to 10, most facile). Intraoperative detection was feasible and improved when compared with a pre-established comparator of 5 representing an equivalent lesion without a marker (Likert Scale: 7.8 ± 2.2; range: 1, most difficult to 10, most facile; P = 0.011). The mean tumor size on EUS was 1.7 ± 0.9 (range: 0.5 to 3.6) cm. CONCLUSION: EUS-FMP is feasible and safe for resectable pancreatic tumors before surgery and may assist in perioperative detection. Preloaded fiducials may be considered for placement at the time of initial referral for EUS-fine needle biopsy.

Underwater versus conventional endoscopic mucosal resection for colorectal lesions: An updated meta-analysis of randomized controlled trials.

Background and study aims Colorectal malignancy is a leading cause of death. Conventional endoscopic mucosal resection (CEMR) is a strategy used to resect precancerous lesions that involves injecting fluid beneath a polyp to create a gap for resection. Underwater endoscopic mucosal resection (UEMR) is a newer method that forgoes injection, instead filling the intestinal cavity with water to facilitate polyp resection. Our aim was to compare the safety and efficacy of these approaches by synthesizing the most contemporary evidence. Methods PubMed, Embase, and Cochrane libraries were searched from inception through November 11, 2022 for randomized controlled trials (RCTs) comparing UEMR and CEMR for resection of colorectal lesions. The primary outcome was the rate of en bloc resection and secondary outcomes included recurrence, procedure time, and adverse events (AEs). Results A total of 2539 studies were identified through our systematic literature search. After screening, seven RCTs with a total of 1581 polyps were included. UEMR was associated with significantly increased rates of en bloc resection (RR 1.18 [1.03, 1.35]; I 2 = 76.6%) versus conventional approaches. No significant differences were found in procedure time, recurrence, or AEs. Conclusions UEMR is a promising effective technique for removal of colorectal lesions. The most contemporary literature indicates that it improves en bloc resection rate without increasing procedure time, recurrence, or AEs (PROSPERO ID CRD42022374935).