This systematic review evaluates current computer vision models and their applications in laparoscopic cholecystectomy. Using PRISMA guidelines, we analyzed studies reporting on primary computer vision model applications in laparoscopic cholecystectomy, from inception to March 2026. A total of 85 studies were included: workflow analysis (n = 26), anatomy recognition and segmentation (n = 14), safety assessment (n = 14), instrument detection (n = 12), tissue/image characterization (n = 7), event detection and scene understanding (n = 6), and surgical performance assessment (n = 6). The performance of the computer vision models in the studies was heterogeneous, with accuracy, F1-score, mean average precision, Dice coefficient, mean absolute error, and area under the receiver operating characteristic curve being commonly reported. Despite strong model performances in several studies, implementation in the clinical setting remains a challenge. We highlight the need for standardized model performance reporting, broader external and multi-institutional validation of models, and coordinated frameworks for safe and effective implementation of computer vision models in laparoscopic cholecystectomy.

Introduction Patients with surgically altered gastrointestinal anatomy undergoing endoscopic retrograde cholangiopancreatography (ERCP) pose challenges due to anatomical distortions. Various patient and endoscopic factors, such as sex and positioning, may impact procedural success. It is unclear how these factors may impact the technical success of ERCP among patients with altered anatomy. Objective We aimed to determine the patient and endoscopic factors that were associated with technical success of ERCP. Methods We conducted a retrospective single-centre study using data from 2010 to 2020 that included patients with hepaticojejunostomy, Roux-en-Y anastomosis, Billroth-1, or Billroth-2 anatomy at a single tertiary care centre in Toronto, Canada. We extracted data from a database. The primary outcome was technical success of the ERCP, defined as successful navigation to the papilla or surgical anastomosis, selective cannulation and cholangiography or pancreatography. Penalized logistic regression with elastic net regularization was used to identify significant predictors of technical success. Effect size was odds ratio with 95% confidence interval. The model was evaluated using the area under the curve (AUC) metric. Results Overall, there were 205 patients included in the analysis. In the multivariate analysis, the most significant contributors to predicting technical success of ERCP were expert endoscopic experience and non-Roux-en Y anatomy. The elastic net model demonstrated moderate predictive performance, with an AUC of 0.656. Conclusions The findings emphasize the importance of tailored procedural planning to optimize ERCP success in patients with altered anatomy.

Abstract Introduction and objectives Endoscopic ampullectomy is the preferred treatment for selected periampullary lesions, yet up to 10.6% of patients may experience delayed bleeding post‐procedure. This study aims to identify predictors for bleeding, which remain poorly understood. Methods This was a single‐center retrospective cohort study of adult patients who underwent endoscopic ampullectomy (EA) between January 2011 and September 2023. The primary outcome was the risk factors for delayed bleeding, defined as post‐procedural bleeding that necessitated either an emergency department visit, hospital admission, blood transfusion, or re‐intervention. Secondary outcomes included adverse events, such as perforation and pancreatitis. Results A total of 113 patients underwent EA, and 25 (22.1%) experienced delayed bleeding. Of these, 20 (80%) required repeat endoscopy, six (24%) needed blood transfusions, and three (12%) were managed conservatively. Multivariable logistic regression analysis identified international normalized ratio ≥1.2 (odds ratio [OR] 3.32, 95% confidence interval [95% CI] 1.03–10.74, p = 0.05), presence of high‐grade dysplasia or intramucosal cancer (OR 3.76, 95% CI 1.20–11.81, p = 0.03), female sex (OR 3.14, 95% CI 1.11–8.93, p = 0.03), size of lesion (OR 1.04, 95% CI 1.01–1.08, p = 0.03) and procedure duration (OR 0.98, 95% CI 0.97–0.99, p = 0.04) as independent predictors of delayed bleeding. Conclusion Several factors, including features of high‐grade dysplasia‐intramucosal cancer, international normalized ratio ≥1.2, female sex, lesion size, and procedure duration are associated with delayed post‐ampullectomy bleeding. These factors should be taken into consideration when strategizing the reduction of post‐ampullectomy bleeding.

Abstract Background Endoscopic Retrograde Cholangiopancreatography (ERCP) has one of the highest adverse event rates among endoscopic procedures, close to 10%, including pancreatitis, bleeding, and perforation. To minimize complications and improve procedure success, understanding risk factors of adverse events is critical. Socioeconomic variables such as income, housing and education can influence health outcomes through access to resources, however, there is a literature gap regarding the effect of these variables on ERCP outcomes. Aims The purpose of this study is to investigate socioeconomic predictors of ERCP outcomes. Methods This study analyzed 6105 patients (51.4% female) who underwent ERCP at a tertiary care center between January 1, 2011 and December 31, 2020. Patient postal codes were translated to 2016 census division unique identifier codes which linked them to median monthly housing costs, household income, education levels, considered proxies for socioeconomic status. Multivariable logistic regression models were built to identify predictors of procedure success (achieving intended diagnostic or therapeutic goals) and adverse events (perforation, abdominal pain, pancreatitis, delayed/immediate bleeding). Data was analyzed using the “glm” package on R studio (Version 2023.06.1) and the adjusted P-value < 0.05 was considered for statistical significance. Results The multivariable logistic regression model demonstrated that better access to housing (OR:1.11 [1.01, 1.12], p=0.02) is associated with procedure success. Conversely, older age (OR: 0.86 [0.78, 0.93], p<0.01) and male sex (OR=0.81 [0.69, 0.95], p<0.0001) are associated with lower odds of procedure success. Higher housing costs (OR: 0.86 [0.75, 0.97], p=0.04) are associated with decreased adverse events, after adjusting for age and sex. Conclusions The findings of this study suggest socioeconomic differences may influence ERCP outcomes and should be further investigated in prospective studies. Funding Agencies None

Abstract Background The identification and removal of polyps are essential skills as they remove premalignant lesions found ad hoc during colonoscopy. Simulation training helps with trainee learning curves and help train novices in polyp identification and polypectomy skills acquisition. The cost of simulators, however, limits trainee access to simulation-based training. Aims To determine the interrater reliability between endoscopists in identifying the Paris Classification of low-cost simulated polyps. Methods Using the Paris classification, novel simulated polyps with various morphologies were developed. 5 endoscopists of varying experience levels (1 expert (>1000 endoscopies), 2 intermediates (500-1000 endoscopies), and 2 novices (<500 endoscopies)) completed a knowledge test. The knowledge test showed images of simulated polyps and the endoscopists identified the Paris classification (Figure 1). The primary outcome measure was the interrater reliability between endoscopists during the knowledge test. A two-way random effects intraclass correlation coefficient (ICC), with absolute agreement between the raters was used to estimate the interrater reliability. Another outcome measure was content validity which was assessed via survey completed by 3 experts and 21 novice endoscopists during a previous simulation course. Results The raters correctly identified all 1p polyps. The Average Measures ICC between all 5 raters was 0.961 (95% CI: 0.93-0.98) indicating excellent reliability. One rater correctly identified all 1s polyp and was removed from ICC analysis due to lack of variance. The Average Measures ICC for 1s polyps was 0.524 (95%CI: 0.15-0.76) indicating moderate reliability. All errors were misidentification of 1s for 2a polyps. The survey showed content validity in terms of setup, usefulness in trainee programs, realism, and perceived trainee improvement. Conclusions Excellent reliability for 1p polyps suggests its usefulness for training polypectomy. Further work is needed to differentiate 1s polyps from 2a polyps. A limitation to interrater reliability is the use of images instead of videos in the knowledge test. The content validity of the polyps suggests practicality for low-cost training to achieve trainee improvement. Further studies are needed to assess other polyp classifications and correlate endoscopist experience level with ability to identify the simulated polyps. Knowledge Test Scores of 5 Endoscopists ICC, intraclass correlation coefficient. (*)excluded from ICC analysis due to lack of variance. Figure 1. Simulated gel polyps based on Paris classification A-B) 1p, C-D) 1s. Funding Agencies None

Background and study aims:Endoscopic mucosal resection (EMR) remains an important treatment for high-grade dysplasia (HGD) and early esophageal adenocarcinoma (EAC) in Barrett's esophagus (BE). However, there are limited data regarding long-term recurrence rates. This study aimed to investigate the neoplasia recurrence rate following EMR with long-term follow-up. Methods:This was a retrospective cohort study at a tertiary-referral center in Canada. Patients with Barrett's neoplasia (HGD/EAC) treated with EMR between January 2001 and December 2023 were included. The primary outcome was long-term neoplasia recurrence rate after complete remission of neoplasia (CRN). Secondary outcomes were residual/metachronous neoplasia rate at first follow-up, CRN rate, and long-term rate of patients successfully managed by endoscopy. Results:A total of 552 patients (83.7% male, mean age 66.3 years) were included (HGD: 22.5%, EAC: 77.5%). After EMR, 475 patients were deemed to have had successful endoscopic resection (low lymph-node metastasis risk with tumor-free deep margin), 455 of whom underwent surveillance follow-up. At first follow-up, residual/metachronous neoplasia was observed in 20.9% (95/455), but 95.6% (435/455) eventually achieved CRN after undergoing a median of two EMR sessions (interquartile range: 1-4). As a primary outcome, the 5-year neoplasia recurrence rate was 10.5%, the 10-year rate was 21.6%, and the 15-year rate was 34.9%. During surveillance, neoplasia recurrence was observed in 38 patients, but 68.4% of them (26/38) were managed with endoscopic therapy. The overall rate of patients successfully managed by endoscopy was 93.0% (423/455). Conclusions:While the success rate of EMR for BE is excellent, this study highlights substantial long-term risk of neoplastic recurrence, underscoring the need for indefinite surveillance for patients who had HGD or EAC.

BACKGROUND:Chronic pancreatitis (CP) is a progressive inflammatory disease leading to irreversible pancreatic damage, resulting in exocrine and endocrine insufficiency. While surgical and endoscopic interventions can address morphological complications of CP, they may not directly address the systemic impacts of malnutrition, frailty, and sarcopenia-key contributors to morbidity and mortality in these patients. This systematic review and meta-analysis aimed to evaluate the prevalence of sarcopenia in CP patients. METHODS:A systematic search of MEDLINE and Embase databases (via Ovid, from inception to November 2024) was conducted following PRISMA guidelines. Studies reporting sarcopenia prevalence in CP, assessed by various diagnostic modalities, were included. Random-effects pooled proportion meta-analysis using the Freeman-Tukey double arcsine transformation were applied. Heterogeneity was assessed using the I2 statistic. RESULTS:Fifteen studies with 1365 CP patients were included. Most patients were male (68 %), with about half having a history of alcohol misuse and smoking (48 %, 52.5 %, respectively). About 47 % had pancreatic exocrine insufficiency, with 41 % being on pancreatic enzyme replacement therapy. Mortality was assessed in a single study and reported at 16 %. The pooled prevalence of sarcopenia was 40.9 % [95 % CI: 28.4 %-58.9 %]. The pooled mean difference for BMI between sarcopenic and non-sarcopenic patients was -2.62 (95 % CI: 3.22 to -2.01, p < 0.01). CONCLUSION:This highlights that approximately 41 % of patients with CP have sarcopenia, and that this seems to be associated with a low BMI. Given the known adverse impact of sarcopenia on overall health, future studies should focus on standardizing sarcopenia screening, assessment and exploring its interplay with outcomes in CP patients. PROSPERO:CRD42024611097.

Abstract Background Esophagogastroduodenoscopy (EGD) requires clear mucosal visualization for detecting lesions in the upper gastrointestinal (UGI) tract. Historically, studies have evaluated UGI cleanliness using non-validated scales. The validation of scoring methods for UGI cleanliness is necessary to be able to document EGD quality in a standardized and reproducible manner. Recently, there have been multiple published studies which describe the development of novel cleanliness scales for EGD, and there is a need to synthesize the currently available data. Aims To summarize and compare novel UGI cleanliness scales for EGD. Methods A literature search of MEDLINE and Web of Sciences from inception to September 2024 identified randomized and cohort studies that used UGI cleanliness scoring systems. Two reviewers screened abstracts/articles and extracted data. Baseline study characteristics and information about cleanliness scales were extracted. The primary outcome was characteristics and validity evidence for UGI cleanliness scales. Results Of 1729 articles screened, 65 were analyzed (Figure 1). 53 studies developed scales for EGD and 11 for capsule endoscopy. 27 articles described novel scales that were not based on prior studies. The primary objectives of these studies were to develop or validate an UGI cleanliness scale (5), evaluate devices (5), or assess intervention efficacies (17). Table 1 summarizes studies that developed a UGI cleanliness scale as a primary aim. Among the 38 studies which created or utilized UGI cleanliness scales based on other studies, the most highly cited scale (13) was proposed by Kuo et al. in 2002. This 4 point scale (1=optimal visibility, 4=poor visibility) evaluated the gastric antrum, lower body, upper body, and fundus. No validation studies were performed, but scores between multiple endoscopists showed a correlation with each other (r = 0.59-0.78, P < 0.001). Conclusions In this review, we have synthesized the current body of literature on UGI scales, highlighting their testing and validity. Future studies should compare the scores from UGI scales with clinical outcomes to determine the utility of standardized scales in improving EGD quality. Table 1: Summary of studies with UGI cleanliness scale validation/development as the primary outcome. Funding Agencies None

Aims Endoscopic resection is the standard of care for superficial esophageal neoplasms. Advances in techniques have allowed extensive resections resulting in circumferential defects, but this substantially increases the risk of stricture formation requiring ongoing intervention. Several prophylactic strategies have been described to mitigate the stricture risk, yet a comprehensive understanding of their usefulness remains uncertain. The aim of this study is to review and analyse the current literature with regards to stricture prophylaxis.

Background Endoscopic mucosal resection (EMR) and endoscopic submucosal dissection (ESD) are effective treatments for Barrett’s neoplasia. However, little is known about recurrence rates following these techniques. We compared long-term neoplasia recurrence rates following EMR and ESD. Methods This study included patients with Barrett’s neoplasia (high grade dysplasia/adenocarcinoma) treated between July 2019 and December 2023 at a tertiary referral center in Canada. Outcomes were residual neoplasia at first follow-up, complete remission of neoplasia (CRN), and neoplasia recurrence following CRN. Results 157 patients were included (87 EMR, 70 ESD). Compared with EMR, the ESD group had larger lesions (median 2 vs. 3 cm, P<0.05), more adenocarcinoma (85.1% vs. 94.3%, P = 0.07), and deeper submucosal invasion (T1a: 71.6% vs. 75.8%; T1b-SM1: 25.7% vs. 6.1%; T1b≥SM2: 2.7% vs. 18.2%; P<0.05). Among 124 patients with follow-up (71 EMR, 53 ESD), 84.9% of ESD-treated patients had curative resections (i.e. R0 resection with low risk for lymph node metastasis), whereas 94.4% of EMR-treated patients had deep margin R0 resection of low risk lesions. At first follow-up, residual neoplasia (14.1% vs. 11.3%) and CRN (97.2% vs. 100%) were similar in the EMR and ESD groups, but neoplasia recurrence following CRN was significantly higher with EMR (13% vs. 1.9%, P<0.05), with cumulative probability of recurrence at 3 years of 18.3% vs. 4.2%, respectively. Conclusions Neoplasia recurrence following CRN was significantly higher following EMR compared with ESD, suggesting that ESD may be superior to EMR in preventing neoplasia recurrence in Barrett’s esophagus.

Abstract Background Endoscopic Retrograde Cholangiopancreatography (ERCP) is a vital procedure for hepatobiliary disease management. Though it boasts high overall success rates, the impact of patient age on outcomes remains uncertain, especially amongst elderly patients. With an aging population, it is crucial to determine the efficacy and safety of ERCP in different age groups. Aims This study assesses ERCP success and complication rates across age groups. Our objective is to investigate whether ERCP remains a reliable and safe procedure for patients of all ages, particularly the elderly. Methods A database with retrospective data from consecutive patients undergoing ERCP at a Canadian tertiary care centre between 2011 and 2020 was utilized. Baseline patient characteristics and indications for ERCP were collected. Outcomes included procedural success, complications, and procedure duration. Patients were categorized into four age groups: ampersand:003C40, 40-65, 65-80, and ampersand:003E80, with a specific sub-analysis for patients ampersand:003C80 and ampersand:003E80. Results This study included 6132 patients. Significant disparities were observed in comorbid conditions (pampersand:003C0.0001), ASA status (pampersand:003C0.0001), and the use of anticoagulants or antiplatelet agents (pampersand:003C0.0001). The most common indications for ERCP were gallstones (45.1%), jaundice (19.2%), and ductal lesions (12.8%), with no significant variation among the age groups (p=0.5983). There was a significant difference in procedural success (p=0.0005), with declining success in older age groups (ampersand:003C40 = 91.3%, 40-65 = 87.4%, 65-80 = 86.2%, ampersand:003E80 = 84.9%), and this difference remained significant in the ampersand:003C80 and ampersand:003E80 sub-analysis (p=0.0133). While mean procedure duration was longer in older age groups (pampersand:003C0.0001), incidence of complications did not vary across all groups (p values [EH1] = 0.1532-0.7622) or patients ampersand:003C80 and ampersand:003E80 (p= 0.0769-0.7128). Conclusions ERCP maintains a high success rate and safety profile across all age groups; however, success rates decline and procedure times increase significantly in older patients. ERCP outcomes across age groups Funding Agencies None

Aims Endoscopic mucosal resection (EMR) and endoscopic submucosal dissection (ESD) are established techniques for endoscopic resection of Barrett's neoplasia, but consensus is lacking for which offers superior outcomes. This study compares the outcomes of EMR and ESD at a Canadian tertiary Barrett's referral center.