AbiMansour, Jad P.

Abstract Background and Aims EUS-guided gastroenterostomy (EUS-GE) is an effective option to palliate symptoms of gastric outlet obstruction (GOO). While the jejunum is conventionally targeted (EUS-GJ), targeting the duodenum (EUS-GD) may offer clinical advantages. Outcomes were compared for EUS-GJ and EUS-GD. Methods Adult patients who underwent EUS-GE for GOO between 2020 and 2024 were included and categorized as an EUS-GD if the stent entered the transverse or ascending duodenum or an EUS-GJ if the stent entered more distally. The primary outcome was clinical success (soft diet tolerance at 7 days). Secondary outcomes included adverse events (AEs), stent misdeployment, and unplanned endoscopic reintervention. Baseline demographic variables and outcomes were compared with statistical significance at p < 0.05. Results Of the 139 included patients (median age 67 years (IQR 61–74); 41% female), 105 underwent EUS-GJ and 34 underwent EUS-GD. Clinical success was 98% for EUS-GJ and 94% for EUS-GD (p = 0.25). The misdeployment rate was 7% for EUS-GJ and 0% for EUS-GD (p = 0.19). The AE rate was 22% for EUS-GJ and 12% for EUS-GD (p = 0.23). There were no significant differences for stent obstruction (EUS-GJ 12% vs. EUS-GD 6%), bleeding (2% vs. 6%), perforation (4% vs. 0%), stent migration (1% vs. 0%), infection (3% vs. 0%), and unplanned reintervention (14% vs. 9%). Conclusion Both EUS-GJ and EUS-GD demonstrate high clinical success with no significant differences in adverse event rates. These data can support intraprocedural decision-making for endoscopists performing EUS-GE.

Background: Self-expanding metal stents (SEMS) are recommended for the endoscopic palliation of distal malignant biliary obstruction (DMBO). Placement of SEMS during endoscopic retrograde cholangiopancreatography (ERCP) has been associated with an increased risk of post-ERCP pancreatitis (PEP). Objectives: The aim of this study is to evaluate rates of PEP in patients who underwent SEMS placement for pancreatic versus non-pancreatic malignancy. Design: Retrospective Cohort Study. Methods: Patients who underwent SEMS placement for DMBO between June 2017 and May 2021 were identified retrospectively from a procedural billing database. PEP incidence was compared between pancreatic and non-pancreatic DMBO groups and multivariate logistic regression was performed to identify risk factors for PEP. Results: A total of 488 individuals were identified, with 395 (80.9%) cases of DMBO due to pancreatic and 93 (19.1%) due to non-pancreatic malignancy. Stent types included 124 (25.4%) fully covered (FCSEMS) and 364 (74.6%) uncovered metal stents (UCSEMS). The overall rate of PEP in the cohort was 6.3% with no significant difference between pancreatic and non-pancreatic etiologies (6.1% vs 7.5%, p = 0.606). When adjusted for age <50 years old, female sex, and pancreatic stent placement, a non-pancreatic malignancy was not associated with an increased risk of PEP (OR 0.83, 95% CI 0.36–2.15). Conclusion: No statistically significant difference in PEP rates was seen after biliary sphincterotomy and SEMS placement for palliation of DMBO in patients with pancreatic versus non-pancreatic malignancies.

ABSTRACT Background Sampling techniques have poor accuracy for classifying biliary strictures as benign or malignant. Previously, a cholangioscopy artificial intelligence (AI) outperfromed sampling techniques based solely on analysis of previously recorded cholangioscopy footage. The aim of this trial was to compare the performance of a real-time cholangioscopy AI to both sampling techniques and human observers for the task of biliary stricture classification. Methods A cholangioscopy AI computer connected directly to a cholangioscope console. The computer analyzed the cholangioscopy video stream during procedures for suspected biliary strictures. The primary outcome of the study was comparison of the performance of cholangioscopy AI to sampling techniques – brush cytology and transpapillary forceps biopsy – for biliary stricture classification. Secondary outcomes included comparison of the AI classification performance to that of human observers (separated into junior-level and experienced-level cohorts) who reviewed the cholangioscopy footage. Results A total of 41 patients were enrolled in the trial and had biliary strictures analyzed by cholangioscopy AI. For the classification of strictures, the AI had greater classification accuracy than standard sampling techniques (87.8% versus 67.4%; p = 0.043). Additionally, the cholangioscopy AI was significantly more accurate for biliary stricture classification than both junior-level (87.8% versus 61.5%; p = 0.001) and experienced endoscopists (87.8% versus 63.15%; p = 0.011). Conclusions This trial demonstrates that sampling techniques and human assessment of biliary strictures are flawed and there may be a benefit to the use of a cholangioscopy AI system to aid in biliary stricture classification.

Background: Upper gastrointestinal bleeding (UGIB) is a common medical emergency associated with significant morbidity, mortality, and healthcare costs. Many patients undergo early endoscopy despite the absence of active bleeding. PillSense is a novel Food and Drug Administration (FDA)-cleared ingestible capsule that rapidly detects the presence of blood in the upper GI tract and may optimize triage decisions. Methods: We conducted a retrospective study evaluating the impact of PillSense on the management of suspected UGIB in an academic center. The primary outcome was the association between capsule results and clinical decision-making, including endoscopy deferral, prioritization, outpatient scheduling, and airway protection. Secondary outcomes included transfusion requirements, time-to-endoscopy, endoscopic intervention, and 30-day adverse events. Results: A total of 28 patients (mean age 64.4 ± 17.9 years, 82.7% male) were included. Compared with negative results, positive results were associated with higher transfusion requirements (median 3 (IQR 3–6) vs. 2 (IQR 1–3.25) units; p = 0.041) and shorter time-to-endoscopy (median 0.2 (IQR 0.01–1) vs. 2 (IQR 1–15.5) days; p = 0.017). In high-risk for sedated endoscopy patients, negative results were associated with EGD deferral in 53.8%, with no subsequent adverse events within 30 days. Endoscopic intervention was performed in 62.5% of positive-result patients versus 9.5% of negative-result patients. Conclusions: The PillSense results were associated with differences in triage and management of high-risk patients with suspected UGIB. Its rapid, accurate, and non-invasive results may reduce unnecessary urgent endoscopy procedures, improve resource utilization, and enhance patient safety, particularly in the highest-risk populations.

Abstract Clinicians struggle to accurately classify biliary strictures as benign or malignant. Current endoscopic retrograde cholangiopancreatography (ERCP)-based sampling modalities including brush cytology and forceps biopsy have poor sensitivity for pathologic confirmation of malignancy. Cholangioscopy allows for direct visualization and sampling of biliary pathology; however, this technology is also associated with inaccurate classification of biliary disease. Previously, an artificial intelligence (AI) system that analyzes cholangioscopy footage was found to be more accurate in diagnosing biliary malignancy than ERCP sampling techniques. The aim of this study was to validate this AI system on a new series of examinations. Three academic centers collected all available unedited cholangioscopy recordings. The videos were processed by the cholangioscopy AI system. After analyzing videos, the AI system provided predictions as to whether malignancy was present. AI performance in classifying strictures was compared with the performance of brush cytology and forceps biopsy. 112 cholangioscopy examinations (containing 4 817 081 images) were generated from 99 patients. Of those examinations, 61 (54.5%) were for investigation of biliary strictures (31 [50.8%] benign, 30 [49.2%] malignant). For the correct classification of strictures, the AI system was 80.0% sensitive and 90.3% specific. It was also significantly more accurate for stricture classification (85.2%) than brush cytology (52.5%; P<0.001), forceps biopsy (68.2%; P=0.04), and the combination of brush cytology and forceps biopsy (66.7%; P=0.02). A previously developed cholangioscopy AI system was found to continually outperform standard ERCP sampling modalities for accurate identification of malignancy, without additional retraining, in a multicenter validation cohort.

Gastric subepithelial lesions (SELs) represent a heterogenous group of mass lesions that arise from the gastric mucosa. Several endoscopic techniques can be used to manage gastric SELs once the decision is made to pursue resection, including endoscopic submucosal resection, endoscopic submucosal dissection, submucosal tunnel endoscopic resection, and endoscopic full-thickness resection. In addition to other clinical and anatomic factors, lesion size has important implications on the ability to obtain a complete resection while minimizing risk of adverse events. This article reviews technical considerations and available data regarding how size may impact the endoscopic approach to gastric SEL resection.