Martin, John A.

Background: Fluorescence in situ hybridization (FISH) is recommended as part of multimodality sampling in the evaluation of biliary strictures, but can be false negative in 40%–50% cases. The aim of this study was to comprehensively assess predictors of false-negative FISH in patients with biliary strictures. Methods: Patients undergoing tissue sampling for biliary strictures from October 20 to February 22 were prospectively enrolled (NCT04572711). Procedural factors such as sampling techniques, order, and utilization of combination sampling were recorded. Results of an optimized pancreatobiliary FISH panel with locus-specific probes for 1q21, 7p12, 8q24, and 9p21 were reported per guidelines. Statistical analyses were performed using BlueSky Statistics v.10.3.1, R package v8.81. Results: Of 327 patients, 93 (28.5%) were diagnosed with malignancy. A false-negative pancreatobiliary fluorescence in situ hybridization (PB-FISH) was reported in 40 (43.1%) patients. A history of primary sclerosing cholangitis was associated with lower odds of having a false-negative PB-FISH (aOR=0.38, 95% CI=0.16–0.82, p=0.02), whereas a hilar stricture was associated with a significantly higher false-negative PB-FISH in those with cholangiocarcinoma (aOR=3.2 [1.4–7.9], p=0.009). Dilation of biliary strictures prior to brushing was not associated with a lower rate of false-negative PB-FISH. Conclusions: In this prospective study, hilar strictures were more likely to have false-negative PB-FISH. Dilation of strictures did not affect PB-FISH performance. These results can help guide PB-FISH interpretation.

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 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.

Background and Aims: Early identification of malignant biliary strictures (MBSs) is challenging, with up to 20% classified as indeterminants after preliminary testing and tissue sampling with endoscopic retrograde cholangiopancreatography. We aimed to evaluate the use of methylated DNA markers (MDMs) from biliary brushings to enhance MBS detection in a prospective cohort. Approach: Candidate MDMs were evaluated for their utility in MBS diagnosis through a series of discovery and validation phases. DNA was extracted from biliary brushing samples, quantified, bisulfite-converted, and then subjected to methylation-specific droplet digital polymerase chain reaction. Patients were considered to have no malignancy if the sampling was negative and there was no evidence of malignancy after 1 year or definitive negative surgical histopathology. Results: Fourteen candidate MDMs were evaluated in the discovery phase, with top-performing and new markers evaluated in the technical validation phase. The top 4 MDMs were TWIST1, HOXA1, VSTM2B, and CLEC11A, which individually achieved AUC values of 0.82, 0.81, 0.83, and 0.78, respectively, with sensitivities of 59.4%, 53.1%, 62.5%, and 50.0%, respectively, at high specificities for malignancy of 95.2%–95.3% for the final biologic validation phase. When combined as a panel, the AUC was 0.86, achieving 73.4% sensitivity and 92.9% specificity, which outperformed cytology and fluorescence in situ hybridization (FISH). Conclusions: The selected MDMs demonstrated improved performance characteristics for the detection of MBS compared to cytology and FISH. Therefore, MDMs should be considered viable candidates for inclusion in diagnostic testing algorithms.

Background: Reports suggest that the rate of adverse events (AEs) post-endoscopic sphincterotomy (ES) to be as high as 10%, with gastrointestinal bleeding being most common after post-endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis. Objective: The aim of this study was to characterize the incidence of bleeding in patients with thrombocytopenia following ES. Design: Retrospective observational cohort study. Methods: Patients with thrombocytopenia (defined as <150,000 platelets/μL) who underwent ES between May 2017 and December 2020 were identified at a tertiary care medical center. The incidence of immediate (intraprocedural oozing >5 min or requiring intervention) or delayed (clinical bleeding with associated hemoglobin drop within 14 days) post-ES bleeding was determined via manual chart review. Results: A total of 221 patients with a mean platelet count of 108,000 ± 13,000 platelets/μL underwent ERCP with ES. Immediate bleeding occurred in 11 (5%) patients with no significant drop in hemoglobin or transfusion requirement. Two patients (0.9%), both of whom were noted to have immediate bleeding, also developed delayed bleeding. Presence of malignancy was associated with an increased risk of bleeding (36.4% versus 11.4%, p = 0.037) while platelet count was not. Conclusion: In a cohort of patients with thrombocytopenia, rates of immediate and delayed bleeding are similar to previously reported AE rates of ES in the general patient population. Careful attention should be given to patients with a history of active malignancy as well as those who develop immediate bleeding as they appear to be at increased risk for bleeding complications.

Abstract Background and study aims Obtaining quality tissue during ERCP biliary stricture sampling is of paramount importance for a timely diagnosis. While single-operator cholangioscopy (SOC)-guided biopsies have been suggested to be the superior biliary tissue acquisition modality given direct tissue visualization, less is known about the specimen histological quality. We aimed to analyze the specimen quality of SOC biopsies and compare the new generation forceps with prior “legacy” forceps. Patients and methods Patients who underwent SOC from January 2017-August 2021 for biliary sampling were reviewed. In February 2020, the SOC-guided biopsy forceps were changed from legacy SpyBite to the SpyBite Max forceps (max). Specimens were assessed by blinded pathologists for crush artifact (none, mild, or severe) and gross size (greatest dimension in mm). Crush artifact and gross size were compared between the two groups. The diagnostic performance characteristics for cholangiocarcinoma (CCA), were assessed in an exploratory fashion. Results Eighty-one patients (max = 27, legacy = 54) with similar baseline characteristics were included in this study. On blinded pathological assessment, 58 % had crush artifact, without significant differences between the two groups (Max 63 % vs. Legacy 56 %; P = 0.64). A similar mean specimen size was found (max 3 mm vs. legacy 3.2 mm; P = 0.24). The overall prevalence of CCA was 40 %. The sensitivity, specificity, positive predictive value, and negative predictive value of the entire cohort using a combination of cytology, fluorescence in situ hybridization, and SOC-guided biopsies were 78.1 %, 91.8 %, 86.2 %, and 86.5 %, respectively. No difference between legacy or max groups was found. Conclusions A high rate of crush artifact was found in SOC-guided biopsy specimens. Further investigation regarding proper biopsy technique and handling is necessary to increase the diagnostic yield with SOC-guided biopsies.