Endoscopic Ultrasound-Guided Rendezvous Technique Versus Precut Sphincterotomy as Salvage Technique in Patients With Benign Biliary Disease and Difficult Biliary Cannulation : A Randomized Controlled Trial.

BACKGROUND: The standard salvage technique used for difficult bile duct cannulation is precut sphincterotomy, whereas endoscopic ultrasound-guided rendezvous technique (EUS-RV) is a relatively newer method. Prospective comparative data between these 2 techniques as salvage for biliary access in patients with benign biliary disease and difficult bile duct cannulation is lacking. OBJECTIVE: To compare EUS-RV and precut sphincterotomy as salvage technique for difficult bile duct cannulation in benign biliary obstruction. DESIGN: Participant-masked, parallel-group, superiority, randomized controlled trial. (Clinical Trials Registry of India: CTRI/2020/07/026613). SETTING: Tertiary care academic institute from July 2020 to May 2021. PARTICIPANTS: All patients with benign biliary disease and difficult bile duct cannulation requiring salvage strategy. INTERVENTION: Patients were randomly assigned by computer-generated randomized blocks sequence in 1:1 fashion to either EUS-RV or precut sphincterotomy. Patients with failure in EUS-RV were crossed over to precut sphincterotomy and vice versa. MEASUREMENTS: The primary outcome measure was technical success. The other outcome measures included procedure time, radiation dose, and adverse events. RESULTS: In total, 100 patients were randomly assigned to EUS-RV (n = 50) and precut sphincterotomy (n = 50). The technical success rate (92% vs. 90%; P = 1.00; relative risk, 1.02 [95% CI, 0.90 to 1.16]), median procedure time (10.1 vs. 9.75 minutes), and overall complication rate (12% vs. 10%; relative risk, 1.20 [CI, 0.39 to 3.68]) were similar between the 2 groups. Five patients (10%) in the EUS-RV group and 5 patients (10%) in the precut sphincterotomy group had developed post-endoscopic retrograde cholangiopancreatography pancreatitis. All failed cases in either salvage group could be successfully cannulated when crossed over to the other group. LIMITATION: Single center study done by experts. CONCLUSION: Endoscopic ultrasound-guided rendezvous technique and precut sphincterotomy have similar success rates as salvage techniques in the technically challenging cohort of difficult bile duct cannulation for benign biliary disease, with acceptable complications rates. PRIMARY FUNDING SOURCE: None.

Computer-Aided Diagnosis for Leaving Colorectal Polyps In Situ : A Systematic Review and Meta-analysis.

BACKGROUND: Computer-aided diagnosis (CADx) allows prediction of polyp histology during colonoscopy, which may reduce unnecessary removal of nonneoplastic polyps. However, the potential benefits and harms of CADx are still unclear. PURPOSE: To quantify the benefit and harm of using CADx in colonoscopy for the optical diagnosis of small (≤5-mm) rectosigmoid polyps. DATA SOURCES: Medline, Embase, and Scopus were searched for articles published before 22 December 2023. STUDY SELECTION: Histologically verified diagnostic accuracy studies that evaluated the real-time performance of physicians in predicting neoplastic change of small rectosigmoid polyps without or with CADx assistance during colonoscopy. DATA EXTRACTION: The clinical benefit and harm were estimated on the basis of accuracy values of the endoscopist before and after CADx assistance. The certainty of evidence was assessed using the GRADE (Grading of Recommendations Assessment, Development and Evaluation) framework. The outcome measure for benefit was the proportion of polyps predicted to be nonneoplastic that would avoid removal with the use of CADx. The outcome measure for harm was the proportion of neoplastic polyps that would be not resected and left in situ due to an incorrect diagnosis with the use of CADx. Histology served as the reference standard for both outcomes. DATA SYNTHESIS: Ten studies, including 3620 patients with 4103 small rectosigmoid polyps, were analyzed. The studies that assessed the performance of CADx alone (9 studies; 3237 polyps) showed a sensitivity of 87.3% (95% CI, 79.2% to 92.5%) and specificity of 88.9% (CI, 81.7% to 93.5%) in predicting neoplastic change. In the studies that compared histology prediction performance before versus after CADx assistance (4 studies; 2503 polyps), there was no difference in the proportion of polyps predicted to be nonneoplastic that would avoid removal (55.4% vs. 58.4%; risk ratio [RR], 1.06 [CI, 0.96 to 1.17]; moderate-certainty evidence) or in the proportion of neoplastic polyps that would be erroneously left in situ (8.2% vs. 7.5%; RR, 0.95 [CI, 0.69 to 1.33]; moderate-certainty evidence). LIMITATION: The application of optical diagnosis was only simulated, potentially altering the decision-making process of the operator. CONCLUSION: Computer-aided diagnosis provided no incremental benefit or harm in the management of small rectosigmoid polyps during colonoscopy. PRIMARY FUNDING SOURCE: European Commission. (PROSPERO: CRD42023402197).

Artificial Intelligence for Real-Time Prediction of the Histology of Colorectal Polyps by General Endoscopists.

BACKGROUND: Real-time prediction of histologic features of small colorectal polyps may prevent resection and/or pathologic evaluation and therefore decrease colonoscopy costs. Previous studies showed that computer-aided diagnosis (CADx) was highly accurate, though it did not outperform expert endoscopists. OBJECTIVE: To assess the diagnostic performance of histologic predictions by general endoscopists before and after assistance from CADx in a real-life setting. DESIGN: Prospective, multicenter, single-group study. (ClinicalTrials.gov: NCT04437615). SETTING: 6 centers across the United States. PARTICIPANTS: 1252 consecutive patients undergoing colonoscopy and 49 general endoscopists with variable experience in real-time prediction of polyp histologic features. INTERVENTION: Real-time use of CADx during routine colonoscopy. MEASUREMENTS: The primary end points were the sensitivity and specificity of CADx-unassisted and CADx-assisted histologic predictions for adenomas measuring 5 mm or less. For clinical purposes, additional estimates according to location and confidence level were provided. RESULTS: The CADx device made a diagnosis for 2695 polyps measuring 5 mm or less (96%) in 1252 patients. There was no difference in sensitivity between the unassisted and assisted groups (90.7% vs. 90.8%; P = 0.52). Specificity was higher in the CADx-assisted group (59.5% vs. 64.7%; P < 0.001). Among all 2695 polyps measuring 5 mm or less, 88.2% and 86.1% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be resected and discarded without pathologic evaluation. Among 743 rectosigmoid polyps measuring 5 mm or less, 49.5% and 47.9% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be left in situ without resection. LIMITATION: Decision making based on CADx might differ outside a clinical trial. CONCLUSION: CADx assistance did not result in increased sensitivity of optical diagnosis. Despite a slight increase, the specificity of CADx-assisted diagnosis remained suboptimal. PRIMARY FUNDING SOURCE: Olympus America Corporation served as the clinical study sponsor.

QUAIDE - Quality assessment of AI preclinical studies in diagnostic endoscopy.

Artificial intelligence (AI) holds significant potential for enhancing quality of gastrointestinal (GI) endoscopy, but the adoption of AI in clinical practice is hampered by the lack of rigorous standardisation and development methodology ensuring generalisability. The aim of the Quality Assessment of pre-clinical AI studies in Diagnostic Endoscopy (QUAIDE) Explanation and Checklist was to develop recommendations for standardised design and reporting of preclinical AI studies in GI endoscopy.The recommendations were developed based on a formal consensus approach with an international multidisciplinary panel of 32 experts among endoscopists and computer scientists. The Delphi methodology was employed to achieve consensus on statements, with a predetermined threshold of 80% agreement. A maximum three rounds of voting were permitted.Consensus was reached on 18 key recommendations, covering 6 key domains: data acquisition and annotation (6 statements), outcome reporting (3 statements), experimental setup and algorithm architecture (4 statements) and result presentation and interpretation (5 statements). QUAIDE provides recommendations on how to properly design (1. Methods, statements 1-14), present results (2. Results, statements 15-16) and integrate and interpret the obtained results (3. Discussion, statements 17-18).The QUAIDE framework offers practical guidance for authors, readers, editors and reviewers involved in AI preclinical studies in GI endoscopy, aiming at improving design and reporting, thereby promoting research standardisation and accelerating the translation of AI innovations into clinical practice.

Artificial Intelligence to Predict the Risk of Lymph Node Metastasis in T2 Colorectal Cancer.

OBJECTIVE: To develop and externally validate an updated artificial intelligence (AI) prediction system for stratifying the risk of lymph node metastasis (LNM) in T2 colorectal cancer (CRC). SUMMARY BACKGROUND DATA: Recent technical advances allow complete local excision of T2 CRC, traditionally treated with surgical resection. Yet, the widespread adoption of this approach is hampered by the inability to stratify the risk of LNM. METHODS: Data from pT2 CRC patients undergoing surgical resection between April 2000 and May 2022 at one Japanese and one Italian center were analyzed. Primary goal was AI system development for accurate LNM prediction. Predictors encompassed seven variables: age, sex, tumor size and location, lympho-vascular invasion, histological differentiation, and carcinoembryonic antigen level. The tool's discriminating power was assessed via Area Under the Curve (AUC), sensitivity, and specificity. RESULTS: Out of 735 initial patients, 692 were eligible. Training and validation cohorts comprised of 492 and 200 patients, respectively. The AI model displayed an AUC of 0.75 in the combined validation dataset. Sensitivity for LNM prediction was 97.8% and specificity was 15.6%. The Positive and the Negative Predictive Value were 25.7% and 96% respectively. The False Negative (FN) rate was 2.2%, the False Positive was 84.4%. CONCLUSIONS: Our AI model, based on easily accessible clinical and pathological variables, moderately predicts LNM in T2 CRC. However, the risk of FN needs to be considered. The training of the model including more patients across Western and Eastern centers -differentiating between colon and rectal cancers- may improve its performance and accuracy.

Environmental risk factors for gallbladder cancer: field-wide systematic review and meta-analysis.

BACKGROUND AND AIMS: Cholelithiasis is the most well-recognized risk factor for gallbladder cancer (GBC), the predominant biliary-tract malignancy; however, credibility on other modifiable exposures remains uncertain. We performed a field-wide systematic review and meta-analysis on environmental factors associated with GBC. METHODS: We systematically searched Medline/PubMed and Embase up to May 8, 2023, to identify randomized and non-randomized studies examining environmental factors for GBC. We conducted random-effects meta-analyses focusing on longitudinal studies. Evidence from case-control studies was considered complementary. Evidence credibility was graded by prespecified criteria including the random-effects estimate, 95% confidence interval, P-value, statistical heterogeneity, small-study effects, and robustness to unmeasured confounding. RESULTS: We identified 215 eligible primary studies and performed 350 meta-analyses across seven domains: lifestyle; reproductive; metabolic; dietary; infections; interventions; contaminants, and occupational exposures. Based on longitudinal evidence, body-mass index (RR per 5-unit increase 1.27; 95% CI, 1.21‒1.33), hip circumference (RR per 5-cm increase 1.16; 1.11‒1.22), infection of bile ducts (RR 31.7; 24.8-40.6), high parity (RR 1.48, 1.30‒1.68), obesity (RR 1.70; 1.44‒2.01), overweight (RR 1.28; 1.14‒1.43), waist circumference (RR per 5-cm increase 1.14; 1.10‒1.18), and waist-to-height ratio (RR per 0.1 increase 1.49; 1.36‒1.64) were robustly associated with increased GBC risk, while high education (RR 0.63; 0.49‒0.82) was associated with reduced risk (moderate-to-high credibility). Another 39 significant associations showed lower credibility, including different exposure scenarios of tobacco smoking, alcohol consumption and insufficient physical activity. CONCLUSIONS: This study offers a detailed appraisal and mapping of the evidence on modifiable factors for GBC. Further high-quality prospective studies are essential to validate emerging associations and inform preventive strategies in high-incidence areas.

Combination of Mucosa-Exposure Device and Computer-Aided Detection for Adenoma Detection During Colonoscopy: A Randomized Trial.

BACKGROUND & AIMS: Both computer-aided detection (CADe)-assisted and Endocuff-assisted colonoscopy have been found to increase adenoma detection. We investigated the performance of the combination of the 2 tools compared with CADe-assisted colonoscopy alone to detect colorectal neoplasias during colonoscopy in a multicenter randomized trial. METHODS: Men and women undergoing colonoscopy for colorectal cancer screening, polyp surveillance, or clincial indications at 6 centers in Italy and Switzerland were enrolled. Patients were assigned (1:1) to colonoscopy with the combinations of CADe (GI-Genius; Medtronic) and a mucosal exposure device (Endocuff Vision [ECV]; Olympus) or to CADe-assisted colonoscopy alone (control group). All detected lesions were removed and sent to histopathology for diagnosis. The primary outcome was adenoma detection rate (percentage of patients with at least 1 histologically proven adenoma or carcinoma). Secondary outcomes were adenomas detected per colonoscopy, advanced adenomas and serrated lesions detection rate, the rate of unnecessary polypectomies (polyp resection without histologically proven adenomas), and withdrawal time. RESULTS: From July 1, 2021 to May 31, 2022, there were 1316 subjects randomized and eligible for analysis; 660 to the ECV group, 656 to the control group). The adenoma detection rate was significantly higher in the ECV group (49.6%) than in the control group (44.0%) (relative risk, 1.12; 95% CI, 1.00-1.26; P = .04). Adenomas detected per colonoscopy were significantly higher in the ECV group (mean ± SD, 0.94 ± 0.54) than in the control group (0.74 ± 0.21) (incidence rate ratio, 1.26; 95% CI, 1.04-1.54; P = .02). The 2 groups did not differ in term of detection of advanced adenomas and serrated lesions. There was no significant difference between groups in mean ± SD withdrawal time (9.01 ± 2.48 seconds for the ECV group vs 8.96 ± 2.24 seconds for controls; P = .69) or proportion of subjects undergoing unnecessary polypectomies (relative risk, 0.89; 95% CI, 0.69-1.14; P = .38). CONCLUSIONS: The combination of CADe and ECV during colonoscopy increases adenoma detection rate and adenomas detected per colonoscopy without increasing withdrawal time compared with CADe alone. CLINICALTRIALS: gov, Number: NCT04676308.

Accuracy of Computer-aided Diagnosis in Colonoscopy Varies According to Polyp Location: A Systematic Review and Meta-analysis.

BACKGROUND & AIMS: Computer-aided diagnosis (CADx) assists endoscopists in differentiating between neoplastic and non-neoplastic polyps during colonoscopy. This study aimed to evaluate the impact of polyp location (proximal vs. distal colon) on the diagnostic performance of CADx for ≤5 mm polyps. METHODS: We searched for studies evaluating the performance of real-time CADx alone (ie, independently of endoscopist judgement) for predicting the histology of colorectal polyps ≤5 mm. The primary endpoints were CADx sensitivity and specificity in the proximal and distal colon. Secondary outcomes were the negative predictive value (NPV), positive predictive value (PPV), and the accuracy of the CADx alone. Distal colon was limited to the rectum and sigmoid. RESULTS: We included 11 studies for analysis with a total of 7782 polyps ≤5 mm. CADx specificity was significantly lower in the proximal colon compared with the distal colon (62% vs 85%; risk ratio (RR), 0.74; 95% confidence interval [CI], 0.72-0.84). Conversely, sensitivity was similar (89% vs 87%); RR, 1.00; 95% CI, 0.97-1.03). The NPV (64% vs 93%; RR, 0.71; 95% CI, 0.64-0.79) and accuracy (81% vs 86%; RR, 0.95; 95% CI, 0.91-0.99) were significantly lower in the proximal than distal colon, whereas PPV was higher in the proximal colon (87% vs 76%; RR, 1.11; 95% CI, 1.06-1.17). CONCLUSION: The diagnostic performance of CADx for polyps in the proximal colon is inadequate, exhibiting significantly lower specificity compared with its performance for distal polyps. Although current CADx systems are suitable for use in the distal colon, they should not be employed for proximal polyps until more performant systems are developed specifically for these lesions.

Low Colorectal Cancer Risk After Resection of High-Risk Pedunculated Polyps.

BACKGROUND: Post-fecal immunochemical test (FIT) colonoscopy represents a setting with an enriched prevalence of advanced adenomas. Due to an expected higher risk of colorectal cancer (CRC), postpolypectomy surveillance is recommended, generating a substantially increased load on endoscopy services. The aim of our study was to investigate postpolypectomy CRC risk in a screening population of FIT+ subjects after resection of low-risk adenomas (LRAs) or high-risk adenomas (HRAs). METHODS: We retrieved data from a cohort of patients undergoing postpolypectomy surveillance within a FIT-based CRC screening program in Italy between 2002 and 2017 and followed-up to December 2021. Main outcomes were postpolypectomy CRC incidence and mortality risks according to type of adenoma (LRA/HRA) removed at colonoscopy as well as morphology, size, dysplasia, and location of the index lesion. We adopted as comparators FIT+/colonoscopy-negative and FIT- patients. The absolute risk was calculated as the number of incident CRCs per 100,000 person-years of follow-up. We used Cox multivariable regression models to identify associations between CRC risks and patient- and polyp-related variables. RESULTS: Overall, we included 87,248 post-FIT+ colonoscopies (133 endoscopists). Of these, 42,899 (49.2%) were negative, 21,650 (24.8%) had an LRA, and 22,709 (26.0%) an HRA. After a median follow-up of 7.25 years, a total of 635 CRCs were observed. For patients with LRAs, CRC incidence (hazard ratio [HR], 1.18; 95% confidence interval [CI], 0.92-1.53) was not increased compared with the FIT+/colonoscopy-negative group, while for HRAs a significant increase in CRC incidence (HR, 1.53; 95% CI, 1.14-2.04) was found. The presence of 1 or more risk factors among proximal location, nonpedunculated morphology, and high-grade dysplasia explained most of this excess CRC risk in the HRA group (HR, 1.85; 95% CI, 1.36-2.52). Patients with only distal pedunculated polyps without high-grade dysplasia, representing 39.2% of HRA, did not have increased risk compared with the FIT- group (HR, 0.87; 95% CI, 0.59-1.28). CONCLUSIONS: CRC incidence is significantly higher in patients with HRAs diagnosed at colonoscopy. However, such excess risk does not appear to apply to patients with only distal pedunculated polyps without high-grade dysplasia, an observation that could potentially reduce the burden of surveillance in FIT programs.

Distinguishing Features of Autoimmune Gastritis Depending on Previous Helicobacter pylori Infection or Positivity to Anti-Parietal Cell Antibodies: Results From the Autoimmune gastRitis Italian netwOrk Study grOup (ARIOSO).

INTRODUCTION: To describe the clinical features and the risk of developing gastric tumors in patients with autoimmune gastritis (AIG). METHODS: This was a retrospective, longitudinal, multicenter study conducted at 8 Italian tertiary referral centers. We retrieved clinical data from all histologically proven patients with AIG. Differences between Helicobacter pylori -exposed vs H. pylori -naive and anti-parietal cell antibody (PCA)-positive vs PCA-negative patients were investigated. The rate of gastric adenocarcinoma and type 1 gastric neuroendocrine neoplasm (gNEN) was assessed. A multivariable model for factors associated with gNEN was fitted. RESULTS: A total of 1,598 patients with AIG (median age 58 years, interquartile range 46-68; F:M ratio 2.7:1) were included. H. pylori -naive patients were more likely to have a first-degree family history of AIG (14.7% vs 8.9%; P = 0.012), type 1 diabetes mellitus (4.9% vs 2.3%; P = 0.025), and pernicious anemia (30.9% vs 21.1%; P = 0.003). PCA-positive patients had significantly more associated autoimmune diseases (59.0% vs 42.9%; P < 0.001) and were more likely to have been diagnosed by a case-finding strategy (15.3% vs 2.6%; P < 0.001). Overall, 15 cases (0.9%) of gastric adenocarcinoma and 153 cases (9.6%) of gNEN occurred, with a global rate of 0.12 (95% confidence interval [CI] 0.07-0.20) and 1.22 (95% CI 1.03-1.42) per 100 person/year, respectively. Having a vitamin B12/iron deficiency manifestation at AIG diagnosis was associated with a 16.44 (95% CI 9.94-27.20 P < 0.001) hazard ratio of gNEN. DISCUSSION: The "pure" AIG pattern has typical features of an autoimmune disease and seems to be unrelated to H. pylori . In a tertiary referral setting, the risk of developing overt gastric adenocarcinoma is low, while patients with vitamin B12 deficiency complications at onset may benefit from a more intense endoscopic follow-up for early gNEN detection.

Small bowel lesions in patients with iron deficiency anaemia without overt bleeding: a multicentre study.

The diagnostic work-up in iron deficiency anaemia (IDA) patients can be challenging when bleedings or malabsorption are not clinically manifest. Lesions on the small bowel mucosa may cause IDA. We evaluated the prevalence of lesions on the small bowel mucosa detected at Videocapsule Endoscopy (VCE) in IDA patients following negative upper and lower endoscopies. Clinical and endoscopic data collected in 5 centres were retrieved. Lesions with a high bleeding potential (P2) were computed, and predictive factors investigated at multivariate analysis. By considering data of 230 patients, the endoscopic examination detected a total of 96 (41.7%; 95% CI: 35.4-48.1) P2 lesions on the small bowel mucosa, including 4 (1.7%) cancers. The use of non-steroidal anti-inflammatory drugs was found to be the only associated factor at both univariate (OR: 5.7, 95% CI: 2.4-13.4; P <0.001) and multivariate (OR: 2.8; 95% CI: 1.7-3.9, P <0.01) analyses. Present study showed that evaluation of small bowel mucosa with VCE allows to disclose a potential cause of IDA in near half patients. The cooperation between haematologists and gastroenterologists in the diagnostic work-up may be useful.

Physician perceptions on the current and future impact of artificial intelligence to the field of gastroenterology.

BACKGROUND AND AIMS: The use of artificial intelligence (AI) has transformative implications to the practice of gastroenterology and endoscopy. The aims of this study were to understand the perceptions of the gastroenterology community toward AI and to identify potential barriers for adoption. METHODS: A 16-question online survey exploring perceptions on the current and future implications of AI to the field of gastroenterology was developed by the American Society for Gastrointestinal Endoscopy AI Task Force and distributed to national and international society members. Participant demographic information including age, sex, experience level, and practice setting was collected. Descriptive statistics were used to summarize survey findings, and a Pearson χ2 analysis was performed to determine the association between participant demographic information and perceptions of AI. RESULTS: Of 10,162 invited gastroenterologists, 374 completed the survey. The mean age of participants was 46 years (standard deviation, 12), and 299 participants (80.0%) were men. One hundred seventy-nine participants (47.9%) had >10 years of practice experience, with nearly half working in the community setting. Only 25 participants (6.7%) reported the current use of AI in their clinical practice. Most participants (95.5%) believed that AI solutions will have a positive impact in their practice. One hundred seventy-six participants (47.1%) believed that AI will make clinical duties more technical but will also ease the burden of the electronic medical record (54.0%). The top 3 areas where AI was predicted to be most influential were endoscopic lesion detection (65.3%), endoscopic lesion characterization (65.8%), and quality metrics (32.6%). Participants voiced a desire for education on topics such as the clinical use of AI applications (64.4%), the advantages and limitations of AI applications (57.0%), and the technical methodology of AI (44.7%). Most participants (42.8%) expressed that the cost of AI implementation should be covered by their hospital. Demographic characteristics significantly associated with this perception included participants' years in practice and practice setting. CONCLUSIONS: Gastroenterologists have an overall positive perception regarding the use of AI in clinical practice but voiced concerns regarding its technical aspects and coverage of costs associated with implementation. Further education on the clinical use of AI applications with understanding of the advantages and limitations appears to be valuable in promoting adoption.

Analyzing methods for reducing recurrence rates after EMR of large nonpedunculated colorectal polyps: an indirect pairwise comparison.

BACKGROUND AND AIMS: Despite advances in EMR techniques, a high polyp recurrence rate remains a challenge. Due to the scarcity of direct comparisons, we performed an indirect comparison of conventional EMR (EMR alone), underwater EMR (U-EMR), and EMR + adjuvant thermal ablation of polypectomy margins to assess polyp recurrence rates. METHODS: Electronic databases were searched from inception to January 12, 2023, for studies reporting polyp recurrence rates after EMR for large nonpedunculated polyps (>15 mm) with or without adjuvant techniques (snare tip soft coagulation [STSC]/argon plasma coagulation [APC]). An indirect comparison was performed by using the frequentist method. The p-score was calculated to identify preferred intervention. Publication bias was assessed by using a comparison-adjusted funnel plot. RESULTS: A total of 9 full articles were identified. On direct comparisons, EMR + STSC had 82% reduced odds (odds ratio, .18; 95% confidence interval, .13-.26; P < .001), whereas U-EMR alone had 77% reduced odds (odds ratio, .23; 95% confidence interval, .08-.67; P = .007) of polyp recurrence compared with EMR alone. On indirect comparison, all interventions had significantly lower odds of polyp recurrence compared with EMR alone. The p-score ranking showed that EMR + STSC seems a potential first method in reducing the odds of polyp recurrence, followed by U-EMR, EMR + APC, and EMR alone. CONCLUSIONS: EMR + STSC seems to provide favorable odds for reducing polyp recurrence postresection for large nonpedunculated polyps. Standardization of methods to detect residual polyp and prevent polyp recurrence at the time of EMR are required.

Consensus statements on the current landscape of artificial intelligence applications in endoscopy, addressing roadblocks, and advancing artificial intelligence in gastroenterology.

BACKGROUND AND AIMS: The American Society for Gastrointestinal Endoscopy (ASGE) AI Task Force along with experts in endoscopy, technology space, regulatory authorities, and other medical subspecialties initiated a consensus process that analyzed the current literature, highlighted potential areas, and outlined the necessary research in artificial intelligence (AI) to allow a clearer understanding of AI as it pertains to endoscopy currently. METHODS: A modified Delphi process was used to develop these consensus statements. RESULTS: Statement 1: Current advances in AI allow for the development of AI-based algorithms that can be applied to endoscopy to augment endoscopist performance in detection and characterization of endoscopic lesions. Statement 2: Computer vision-based algorithms provide opportunities to redefine quality metrics in endoscopy using AI, which can be standardized and can reduce subjectivity in reporting quality metrics. Natural language processing-based algorithms can help with the data abstraction needed for reporting current quality metrics in GI endoscopy effortlessly. Statement 3: AI technologies can support smart endoscopy suites, which may help optimize workflows in the endoscopy suite, including automated documentation. Statement 4: Using AI and machine learning helps in predictive modeling, diagnosis, and prognostication. High-quality data with multidimensionality are needed for risk prediction, prognostication of specific clinical conditions, and their outcomes when using machine learning methods. Statement 5: Big data and cloud-based tools can help advance clinical research in gastroenterology. Multimodal data are key to understanding the maximal extent of the disease state and unlocking treatment options. Statement 6: Understanding how to evaluate AI algorithms in the gastroenterology literature and clinical trials is important for gastroenterologists, trainees, and researchers, and hence education efforts by GI societies are needed. Statement 7: Several challenges regarding integrating AI solutions into the clinical practice of endoscopy exist, including understanding the role of human-AI interaction. Transparency, interpretability, and explainability of AI algorithms play a key role in their clinical adoption in GI endoscopy. Developing appropriate AI governance, data procurement, and tools needed for the AI lifecycle are critical for the successful implementation of AI into clinical practice. Statement 8: For payment of AI in endoscopy, a thorough evaluation of the potential value proposition for AI systems may help guide purchasing decisions in endoscopy. Reliable cost-effectiveness studies to guide reimbursement are needed. Statement 9: Relevant clinical outcomes and performance metrics for AI in gastroenterology are currently not well defined. To improve the quality and interpretability of research in the field, steps need to be taken to define these evidence standards. Statement 10: A balanced view of AI technologies and active collaboration between the medical technology industry, computer scientists, gastroenterologists, and researchers are critical for the meaningful advancement of AI in gastroenterology. CONCLUSIONS: The consensus process led by the ASGE AI Task Force and experts from various disciplines has shed light on the potential of AI in endoscopy and gastroenterology. AI-based algorithms have shown promise in augmenting endoscopist performance, redefining quality metrics, optimizing workflows, and aiding in predictive modeling and diagnosis. However, challenges remain in evaluating AI algorithms, ensuring transparency and interpretability, addressing governance and data procurement, determining payment models, defining relevant clinical outcomes, and fostering collaboration between stakeholders. Addressing these challenges while maintaining a balanced perspective is crucial for the meaningful advancement of AI in gastroenterology.

Endoscopic papillectomy for ampullary lesions of minor papilla.

BACKGROUND AND AIMS: Ampullary lesions (ALs) of the minor duodenal papilla are extremely rare. Endoscopic papillectomy (EP) is a routinely used treatment for AL of the major duodenal papilla, but the role of EP for minor AL has not been accurately studied. METHODS: We identified 20 patients with ALs of minor duodenal papilla in the multicentric database from the Endoscopic Papillectomy vs Surgical Ampullectomy vs Pancreatitcoduodenectomy for Ampullary Neoplasm study, which included 1422 EPs. We used propensity score matching (nearest-neighbor method) to match these cases with ALs of the major duodenal papilla based on age, sex, histologic subtype, and size of the lesion in a 1:2 ratio. Cohorts were compared by means of chi-square or Fisher exact test as well as Mann-Whitney U test. RESULTS: Propensity score-based matching identified a cohort of 60 (minor papilla 20, major papilla 40) patients with similar baseline characteristics. The most common histologic subtype of lesions of minor papilla was an ampullary adenoma in 12 patients (3 low-grade dysplasia and 9 high-grade dysplasia). Five patients revealed nonneoplastic lesions. Invasive cancer (T1a), adenomyoma, and neuroendocrine neoplasia were each found in 1 case. The rate of complete resection, en-bloc resection, and recurrences were similar between the groups. There were no severe adverse events after EP of lesions of minor papilla. One patient had delayed bleeding that could be treated by endoscopic hemostasis, and 2 patients showed a recurrence in surveillance endoscopy after a median follow-up of 21 months (interquartile range, 12-50 months). CONCLUSIONS: EP is safe and effective in ALs of the minor duodenal papilla. Such lesions could be managed according to guidelines for EP of major duodenal papilla.

Establishment of standards for the referral of large nonpedunculated colorectal polyps: an international expert consensus using a modified Delphi process.

BACKGROUND AND AIMS: Resection of colorectal polyps has been shown to decrease the incidence and mortality of colorectal cancer. Large nonpedunculated colorectal polyps are often referred to expert centers for endoscopic resection, which requires relevant information to be conveyed to the therapeutic endoscopist to allow for triage and planning of resection technique. The primary objective of this study was to establish minimum expected standards for the referral of large nonpedunculated colonic polyps for potential endoscopic resection. METHODS: A Delphi method was used to establish consensus on minimum expected standards for the referral of large colorectal polyps among a panel of international endoscopy experts. The expert panel was recruited through purposive sampling, and 3 rounds of surveys were conducted to achieve consensus. Quantitative and qualitative data were analyzed for each round. RESULTS: A total of 24 international experts from diverse continents participated in the Delphi study, resulting in consensus on 19 statements related to the referral of large colorectal polyps. The identified factors, including patient demographic characteristics, relevant medications, lesion factors, photodocumentation, and the presence of a tattoo, were deemed important for conveying the necessary information to therapeutic endoscopists. The mean scores for the statements, which were scored on a scale of 1 to 10, ranged from 7.04 to 9.29, with high percentages of experts considering most statements as a very high priority. Subgroup analysis according to continent revealed some variations in consensus rates among experts from different regions. CONCLUSIONS: The identified consensus statements can aid in improving the triage and planning of resection techniques for large colorectal polyps, ultimately contributing to the reduction of colorectal cancer incidence and mortality.

Efficacy and safety of endoscopic ultrasound-guided hepaticogastrostomy: a meta-regression analysis.

BACKGROUND: Endoscopic ultrasound-guided hepaticogastrostomy (EUS-HGS) is a valid option for EUS-guided biliary drainage that has been increasingly used in the last decade. The aims of this study were to provide a systematic review with meta-analysis and meta-regression of the features and outcomes of this procedure. METHODS: The MEDLINE, Scopus, Web of Science, and Cochrane databases were searched for literature pertinent to EUS-HGS. Meta-analysis of the proportions and meta-regression of potential modifiers of the main outcome measures were applied. The main outcome was technical success; secondary outcomes were clinical success and procedure-related adverse events (AEs). RESULTS: 33 studies, including 1644 patients, were included in the meta-analysis. Malignant biliary obstruction (MBO) was the underlying cause in almost all cases (99.6%); the main indications for EUS-HGS were duodenal/papillary invasion (34.8%), surgically altered anatomy (18.4%), and hilar stenosis (16.0%). The pooled technical success of EUS-HGS was 97.7% (95%CI 96.1%-99.0%; I 2 = 0%), the intention-to-treat clinical success rate was 88.1% (95%CI 84.7%-91.2%; I 2 = 33.9%), and procedure-related AEs occurred in 12.0% (95%CI 9.8%-14.5%; I 2 = 20.4%), with cholangitis/sepsis (2.8%) and bleeding (2.3%) the most frequent. The rate of procedure-related AEs was lower with the use of dedicated stents on univariable meta-regression analysis. Meta-regression showed that technical success and clinical success rates were modified by the centers' experience (>4/year). CONCLUSIONS: EUS-HGS represents an effective and safe procedure for EUS-guided biliary drainage in patients with MBO. Future studies should address the impact of center experience, patient selection, and the use of dedicated stents to improve performance of this technique.

Comparative diagnostic yield of different endoscopic techniques for tissue sampling of upper gastrointestinal subepithelial lesions: a network meta-analysis.

BACKGROUND: There is limited evidence on the comparative diagnostic performance of endoscopic tissue sampling techniques for subepithelial lesions. We performed a systematic review with network meta-analysis to compare these techniques. METHODS: A systematic literature review was conducted for randomized controlled trials (RCTs) comparing the sample adequacy and diagnostic accuracy of bite-on-bite biopsy, mucosal incision-assisted biopsy (MIAB), endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA), and EUS-guided fine-needle biopsy (FNB). Results were expressed as relative risk (RR) and 95%CI. RESULTS: Eight RCTs were identified. EUS-FNB was significantly superior to EUS-FNA in terms of sample adequacy (RR 1.20 [95%CI 1.05-1.45]), whereas none of the other techniques significantly outperformed EUS-FNA. Additionally, bite-on-bite biopsy was significantly inferior to EUS-FNB (RR 0.55 [95%CI 0.33-0.98]). Overall, EUS-FNB appeared to be the best technique (surface under cumulative ranking [SUCRA] score 0.90) followed by MIAB (SUCRA 0.83), whereas bite-on-bite biopsy showed the poorest performance. When considering lesions <20 mm, MIAB, but not EUS-FNB, showed significantly higher accuracy rates compared with EUS-FNA (RR 1.68 [95%CI 1.02-2.88]). Overall, MIAB ranked as the best intervention for lesions <20 mm (SUCRA score 0.86 for adequacy and 0.91 for accuracy), with EUS-FNB only slightly superior to EUS-FNA. When rapid on-site cytological evaluation (ROSE) was available, no difference between EUS-FNB, EUS-FNA, and MIAB was observed. CONCLUSION: EUS-FNB and MIAB appeared to provide better performance, whereas bite-on-bite sampling was significantly inferior to the other techniques. MIAB seemed to be the best option for smaller lesions, whereas EUS-FNA remained competitive when ROSE was available.

Endoscopic submucosal dissection and endoscopic mucosal resection for Barrett's-associated neoplasia: a systematic review and meta-analysis of the published literature.

BACKGROUND: The role of endoscopic submucosal dissection (ESD) in the treatment of Barrett esophagus-associated neoplasia (BEN) has been evolving. We examined the efficacy and safety of ESD and endoscopic mucosal resection (EMR) for BEN. METHODS: A database search was performed for studies reporting efficacy and safety outcomes of ESD and EMR for BEN. Pooled proportional and comparative meta-analyses were performed. RESULTS: 47 studies (23 ESD, 19 EMR, 5 comparative) were included. The mean lesion sizes for ESD and EMR were 22.5 mm and 15.8 mm, respectively; most lesions were Paris type IIa. For ESD, pooled analysis showed rates of en bloc, R0, and curative resection, and local recurrence of 98%, 78%, 65%, and 2%, respectively. Complete eradication of dysplasia and intestinal metaplasia were achieved in 94% and 59% of cases, respectively. Pooled rates of perforation, intraprocedural bleeding, delayed bleeding, and stricture were 1%, 1%, 2%, and 10%, respectively. For EMR, pooled analysis showed rates of en bloc, R0, and curative resection, and local recurrence of 37%, 67%, 62%, and 6%, respectively. Complete eradication of dysplasia and intestinal metaplasia were achieved in 94% and 75% of cases. Pooled rates of perforation, intraprocedural bleeding, delayed bleeding, and stricture were 0.1%, 1%, 0.4%, and 8%, respectively. The mean procedure times for ESD and EMR were 113 and 22 minutes, respectively. Comparative analysis showed higher en bloc and R0 resection rates with ESD compared with EMR, with comparable adverse events. CONCLUSION: ESD and EMR can both be employed to treat BEN depending on lesion type and size, and center expertise.

Over-the-scope clip as first-line treatment of peptic ulcer bleeding: a multicenter randomized controlled trial (TOP Study).

BACKGROUND: First-line over-the-scope (OTS) clip treatment has shown higher efficacy than standard endoscopic therapy in acute nonvariceal upper gastrointestinal bleeding (NVUGIB) from different causes. We compared OTS clips with through-the-scope (TTS) clips as first-line mechanical treatment in the specific setting of peptic ulcer bleeding. METHODS: We conducted an international, multicenter randomized controlled trial on consecutive patients with suspected NVUGIB. Patients with Forrest Ia-IIb gastroduodenal peptic ulcer were randomized 1:1 to OTS clip or TTS clip treatment. The primary outcome was the rate of 30-day rebleeding after successful initial hemostasis. Secondary outcomes included the rates of successful initial hemostasis and overall clinical success, defined as the composite of successful initial hemostasis and no evidence of 30-day rebleeding. RESULTS: 251 patients were screened and 112 patients were randomized to OTS (n = 61) or TTS (n = 51) clip treatment. The 30-day rebleeding rates were 1.6% (1/61) and 3.9% (2/51) in patients treated with OTS clips and TTS clips, respectively (Kaplan-Meier log-rank, P = 0.46). Successful initial hemostasis rates were 98.4% (60/61) in the OTS clip group and 78.4% (40/51) in the TTS clip group (P = 0.001). Overall clinical success rates were 96.7% (59/61) with OTS clips and 74.5% (38/51) with TTS clips (P = 0.001). CONCLUSIONS: Low rates of 30-day rebleeding were observed after first-line endoscopic treatment of acute peptic ulcer bleeding with either OTS or TTS clips. However, OTS clips showed higher efficacy than TTS clips in achieving successful initial hemostasis and overall clinical success.