Marya, Neil B.

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.

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.

Abstract Cholecystectomy (CCY) is the standard treatment for acute cholecystitis. For non-surgical patients, percutaneous cholecystostomy tube (PT-GBD) is recommended but is associated with high readmission rates and poor quality of life. Endoscopic gallbladder decompression techniques, including endoscopic transpapillary gallbladder drainage (ET-GBD) and endoscopic ultrasound-guided gallbladder drainage (EUS-GBD), are alternatives. Studies comparing ET-GBD and EUS-GBD have shown EUS-GBD to have superior outcomes. However, these studies assessed ET-GBD mostly via single transcystic stent placement (SSET-GBD). This study aimed to compare outcomes of dual transcystic stents (DSET-GBD) and EUS-GBD in non-surgical candidates with acute cholecystitis. A multicenter analysis was conducted on patients who underwent ET-GBD or EUS-GBD between January 2019 and January 2023. Data were extracted from electronic medical records and outcomes including technical success, success, adverse events (AEs), and recurrence rates of cholecystitis were measured. Of 129 procedures (56 EUS-GBD; 73 ET-GBD), technical success was achieved in 87.5% of EUS-GBD and 86.3% of ET-GBD attempts. Immediate clinical success was achieved in 98.1% for EUS-GBD and 100% for DSET-GBD. AE rates were similar between the groups. Recurrent cholecystitis rates were 5.3% for EUS-GBD and 8.2% for DSET-GBD (P = 0.692). This study demonstrates that DSET-GBD has similarly low rates of recurrent acute cholecystitis compared with EUS-GBD. DSET-GBD should be considered as an alternative management strategy for management of acute cholecystitis in patients who are unable to undergo CCY.

Abstract Background The authors previously developed an artificial intelligence (AI) to assist cytologists in the evaluation of digital whole‐slide images (WSIs) generated from bile duct brushing specimens. The aim of this trial was to assess the efficiency and accuracy of cytologists using a novel application with this AI tool. Methods Consecutive bile duct brushing WSIs from indeterminate strictures were obtained. A multidisciplinary panel reviewed all relevant information and provided a central interpretation for each WSI as being “positive,” “negative,” or “indeterminate.” The WSIs were then uploaded to the AI application. The AI scored each WSI as positive or negative for malignancy (i.e., computer‐aided diagnosis [CADx]). For each WSI, the AI prioritized cytologic tiles by the likelihood that malignant material was present in the tile. Via the AI, blinded cytologists reviewed all WSIs and provided interpretations (i.e., computer‐aided detection [CADe]). The diagnostic accuracies of the WSI evaluation via CADx, CADe, and the original clinical cytologic interpretation (official cytologic interpretation [OCI]) were compared. Results Of the 84 WSIs, 15 were positive, 42 were negative, and 27 were indeterminate after central review. The WSIs generated on average 141,950 tiles each. Cytologists using the AI evaluated 10.5 tiles per WSI before making an interpretation. Additionally, cytologists required an average of 84.1 s of total WSI evaluation. WSI interpretation accuracies for CADx (0.754; 95% CI, 0.622–0.859), CADe (0.807; 95% CI, 0.750–0.856), and OCI (0.807; 95% CI, 0.671–0.900) were similar. Conclusions This trial demonstrates that an AI application allows cytologists to perform a triaged review of WSIs while maintaining accuracy.

Abstract Background and study aims Gastric outlet obstruction (GOO) is traditionally managed with surgical gastroenterostomy (surgical-GE) and enteral stenting (ES). Endoscopic ultrasound-guided gastroenterostomy (EUS-GE) is now a third option. Large studies assessing their relative risks and benefits with adequate follow-up are lacking. We conducted a comparative analysis of patients who underwent EUS-GE, ES, or surgical-GE for GOO. Patients and methods In this retrospective comparative cohort study, consecutive patients presenting with GOO who underwent EUS-GE, ES, or surgical-GE at two academic institutions were reviewed and independently cross-edited to ensure accurate reporting. The primary outcome was need for reintervention. Secondary outcomes were technical and clinical success, length of hospital stay (LOS), and adverse events (AEs). Results A total of 436 patients (232 EUS-GE, 131 ES, 73 surgical-GE) were included. The median duration of follow-up of the entire cohort was 185.5 days (interquartile range 55.25–454.25 days). The rate of reintervention in the EUS-GE group was lower than in the ES and surgical-GE groups (0.9 %, 12.2 %, and 13.7 %, P < 0.0001). Technical success was achieved in 98.3 %, 99.2 %, and 100 % (P = 0.58), and clinical success was achieved in 98.3 %, 91.6 %, and 90.4 % (P < 0.0001) in the EUS-GE, ES, and surgical-GE groups, respectively. The EUS-GE group had a shorter LOS (2 days vs. 3 days vs. 5 days, P < 0.0001) and a lower AE rate than the ES and surgical-GE groups (8.6 % vs. 38.9 % vs. 27.4 %, P < 0.0001). Conclusion This large cohort study demonstrates the safety and palliation durability of EUS-GE as an alternative strategy for GOO palliation in select patients.