Associations between income and survival in cholangiocarcinoma: A comprehensive subtype-based analysis.

Backgrounds/Aims: Socioeconomic determinants of health are incompletely characterized in cholangiocarcinoma (CCA). We assessed how socioeconomic status influences initial treatment decisions and survival outcomes in patients with CCA, additionally performing multiple sub-analyses based on anatomic location of the primary tumor. Methods: Observational study using the 2018 submission of the Surveillance, Epidemiology, and End Results (SEER)-18 Database. In total, 5,476 patients from 2004-2015 with a CCA were separated based on median household income (MHI) into low income (< 25th percentile of MHI) and high income (> 25th percentile of MHI) groups. Seventy-three percent of patients had complete follow up data, and were included in survival analyses. Survival and treatment outcomes were calculated using R-studio. Results: When all cases of CCA were included, the high-income group was more likely than the low-income to receive surgery, chemotherapy, and local tumor destruction modalities. Initial treatment modality based on income differed significantly between tumor locations. Patients of lower income had higher overall and cancer-specific mortality at 2 and 5 years. Non-cancer mortality was similar between the groups. Survival differences identified in the overall cohort were maintained in the intrahepatic CCA subgroup. No differences between income groups were noted in cancer-specific or overall mortality for perihilar tumors, with variable differences in the distal cohort. Conclusions: Lower income was associated with higher rates of cancer-specific mortality and lower rates of surgical resection in CCA. There were significant differences in treatment selection and outcomes between intrahepatic, perihilar, and distal tumors. Population-based strategies aimed at identifying possible etiologies for these disparities are paramount to improving patient outcomes.

Assessment of Pathology Domain-Specific Knowledge of ChatGPT and Comparison to Human Performance.

CONTEXT.­: Artificial intelligence algorithms hold the potential to fundamentally change many aspects of society. Application of these tools, including the publicly available ChatGPT, has demonstrated impressive domain-specific knowledge in many areas, including medicine. OBJECTIVES.­: To understand the level of pathology domain-specific knowledge for ChatGPT using different underlying large language models, GPT-3.5 and the updated GPT-4. DESIGN.­: An international group of pathologists (n = 15) was recruited to generate pathology-specific questions at a similar level to those that could be seen on licensing (board) examinations. The questions (n = 15) were answered by GPT-3.5, GPT-4, and a staff pathologist that recently passed their Canadian pathology licensing exams. Participants were instructed to score answers on a 5-point scale and to predict which answer was written by ChatGPT. RESULTS.­: GPT-3.5 performed at a similar level to the staff pathologist, while GPT-4 outperformed both. The overall score for both GPT-3.5 and GPT-4 was within the range of meeting expectations for a trainee writing licensing examinations. In all but one question, the reviewers were able to correctly identify the answers generated by GPT-3.5. CONCLUSIONS.­: By demonstrating the ability of ChatGPT to answer pathology-specific questions at a level similar to (GPT-3.5) or exceeding (GPT-4) a trained pathologist, this study highlights the potential of large language models to be transformative in this space. In the future, more advanced iterations of these algorithms with increased domain-specific knowledge may have the potential to assist pathologists and enhance pathology resident training.

Development and initial validation of a video-based peroral endoscopic myotomy assessment tool.

BACKGROUND AND AIMS: Video analysis has emerged as a potential strategy for performance assessment and improvement. We aimed to develop a video-based skill assessment tool for peroral endoscopic myotomy (POEM). METHODS: POEM was deconstructed into basic procedural components through video analysis by an expert panel. A modified Delphi approach and 2 validation exercises were conducted to refine the POEM assessment tool (POEMAT). Twelve assessors used the final POEMAT version to grade 10 videos. Fully crossed generalizability (G) studies investigated the contributions of assessors, endoscopists' performance, and technical elements to reliability. G coefficients below .5 were considered unreliable, between .5 and .7 as modestly reliable, and above .7 as indicative of satisfactory reliability. RESULTS: After task deconstruction, discussions, and the modified Delphi process, the final POEMAT comprised 9 technical elements. G analysis showed low variance for endoscopist performance (.8%-24.9%) and high interrater variability (range, 63.2%-90.1%). The G score was moderately reliable (≥.60) for "submucosal tunneling" and "myotomy" and satisfactorily reliable (≥.70) for "active hemostasis" and "mucosal closure." CONCLUSIONS: We developed and established initial content and response process validity evidence for the POEMAT. Future steps include appraisal of the tool using a wider range of POEM videos to establish and improve the discriminative validity of this tool.

A Prospective Multicenter Study Evaluating Learning Curves and Competence in Endoscopic Ultrasound and Endoscopic Retrograde Cholangiopancreatography Among Advanced Endoscopy Trainees: The Rapid Assessment of Trainee Endoscopy Skills Study.

BACKGROUND & AIMS: On the basis of the Next Accreditation System, trainee assessment should occur on a continuous basis with individualized feedback. We aimed to validate endoscopic ultrasound (EUS) and endoscopic retrograde cholangiopancreatography (ERCP) learning curves among advanced endoscopy trainees (AETs) by using a large national sample of training programs and to develop a centralized database that allows assessment of performance in relation to peers. METHODS: ASGE recognized training programs were invited to participate, and AETs were graded on ERCP and EUS exams by using a validated competency assessment tool that assesses technical and cognitive competence in a continuous fashion. Grading for each skill was done by using a 4-point scoring system, and a comprehensive data collection and reporting system was built to create learning curves by using cumulative sum analysis. Individual results and benchmarking to peers were shared with AETs and trainers quarterly. RESULTS: Of the 62 programs invited, 20 programs and 22 AETs participated in this study. At the end of training, median number of EUS and ERCP performed/AET was 300 (range, 155-650) and 350 (125-500), respectively. Overall, 3786 exams were graded (EUS, 1137; ERCP-biliary, 2280; ERCP-pancreatic, 369). Learning curves for individual end points and overall technical/cognitive aspects in EUS and ERCP demonstrated substantial variability and were successfully shared with all programs. The majority of trainees achieved overall technical (EUS, 82%; ERCP, 60%) and cognitive (EUS, 76%; ERCP, 100%) competence at conclusion of training. CONCLUSIONS: These results demonstrate the feasibility of establishing a centralized database to report individualized learning curves and confirm the substantial variability in time to achieve competence among AETs in EUS and ERCP. ClinicalTrials.gov: NCT02509416.