ChatGPT4 Outperforms Endoscopists for Determination of Postcolonoscopy Rescreening and Surveillance Recommendations.

BACKGROUND & AIMS: Large language models including Chat Generative Pretrained Transformers version 4 (ChatGPT4) improve access to artificial intelligence, but their impact on the clinical practice of gastroenterology is undefined. This study compared the accuracy, concordance, and reliability of ChatGPT4 colonoscopy recommendations for colorectal cancer rescreening and surveillance with contemporary guidelines and real-world gastroenterology practice. METHODS: History of present illness, colonoscopy data, and pathology reports from patients undergoing procedures at 2 large academic centers were entered into ChatGPT4 and it was queried for the next recommended colonoscopy follow-up interval. Using the McNemar test and inter-rater reliability, we compared the recommendations made by ChatGPT4 with the actual surveillance interval provided in the endoscopist's procedure report (gastroenterology practice) and the appropriate US Multisociety Task Force (USMSTF) guidance. The latter was generated for each case by an expert panel using the clinical information and guideline documents as reference. RESULTS: Text input of de-identified data into ChatGPT4 from 505 consecutive patients undergoing colonoscopy between January 1 and April 30, 2023, elicited a successful follow-up recommendation in 99.2% of the queries. ChatGPT4 recommendations were in closer agreement with the USMSTF Panel (85.7%) than gastroenterology practice recommendations with the USMSTF Panel (75.4%) (P < .001). Of the 14.3% discordant recommendations between ChatGPT4 and the USMSTF Panel, recommendations were for later screening in 26 (5.1%) and for earlier screening in 44 (8.7%) cases. The inter-rater reliability was good for ChatGPT4 vs USMSTF Panel (Fleiss κ, 0.786; 95% CI, 0.734-0.838; P < .001). CONCLUSIONS: Initial real-world results suggest that ChatGPT4 can define routine colonoscopy screening intervals accurately based on verbatim input of clinical data. Large language models have potential for clinical applications, but further training is needed for broad use.

Increasing Antibiotic-Resistant Infections With Inpatient Endoscopic Retrograde Cholangioscopies (ERCP) Is Associated With Higher Mortality in the United States: A Cross-sectional Cohort Study.

GOALS: This study aims to investigate associated mortality with inpatient endoscopic retrograde cholangiopancreatography (ERCP) with and without resistant infections. The co-primary objective compares frequencies of inpatient ERCP with resistant infections to overall hospitalizations with resistant infections. BACKGROUND: The risks of inpatient antibiotic-resistant organisms are known, but the associated mortality for inpatient ERCP is unknown. We aim to use a national database of hospitalizations and procedures to understand trends and mortality for patients with antibiotic-resistant infections during inpatient ERCP. STUDY: The largest publicly available all-payer inpatient database in the United States (National Inpatient Sample) was used to identify hospitalizations associated with ERCPs and antibiotic-resistant infections for MRSA, VRE, ESBL, and MDRO. National estimates were generated, frequencies were compared across years, and multivariate regression for mortality was performed. RESULTS: From 2017 to 2020, national weighted estimates of 835,540 inpatient ERCPs were generated, and 11,440 ERCPs had coincident resistant infections. Overall resistant infection, MRSA, VRE, and MDRO identified at the same hospitalization of inpatient ERCPs were associated with higher mortality (OR CI(95%): Overall: 2.2(1.77-2.88), MRSA: 1.90 (1.34-2.69), VRE: 3.53 (2.16-5.76), and MDRO: 2.52 (1.39-4.55)). While overall hospitalizations with resistant infections have been decreasing annually, there has been a yearly increase in admissions requiring ERCPs with simultaneous resistant infections ( P =0.001-0.013), as well as infections with VRE, ESBL, and MDRO ( P =0.001-0.016). Required Research Practices for Studies Using the NIS scoring was 0, or the most optimal. CONCLUSIONS: Inpatient ERCPs have increasing coincident resistant infections and are associated with higher mortality. These rising infections during ERCP highlight the importance of endoscopy suite protocols and endoscopic infection control devices.

A Preliminary Controlled Trial of Endoscopic Ultrasound-guided Fiducial Markers to Guide Pancreas Surgery.

OBJECTIVE: Endoscopic ultrasound (EUS) is routinely used for fiducial marker placement (FMP) to guide stereotactic radiation of pancreatic tumors, but EUS-FMP explicitly to guide surgery has not been studied in a prospective, controlled manner. Multipurpose EUS systems have been developed that facilitate simultaneous EUS-FMP at the time of biopsy. We aimed to evaluate the feasibility of EUS-FMP to guide pancreatic resection. METHODS: In this prospective trial, we enrolled patients with resectable pancreas masses undergoing tissue sampling and placed preloaded fiducials immediately after biopsy. Intraprocedure confirmation of carcinoma, neuroendocrine, and nonlymphomatous neoplasia by rapid on-site evaluation and lesion size <4 cm was required. The main outcomes were the feasibility and ease of preoperative placement and intraoperative detection of the markers using predefined Likert scales. RESULTS: In 20 patients, EUS-FMP was successful before planned surgery and placement was technically straightforward (Likert Scale: 9.1 ± 1.3; range: 1, most challenging to 10, most facile). Intraoperative detection was feasible and improved when compared with a pre-established comparator of 5 representing an equivalent lesion without a marker (Likert Scale: 7.8 ± 2.2; range: 1, most difficult to 10, most facile; P = 0.011). The mean tumor size on EUS was 1.7 ± 0.9 (range: 0.5 to 3.6) cm. CONCLUSION: EUS-FMP is feasible and safe for resectable pancreatic tumors before surgery and may assist in perioperative detection. Preloaded fiducials may be considered for placement at the time of initial referral for EUS-fine needle biopsy.

A functional genomics screen identifying blood cell development genes in Drosophila by undergraduates participating in a course-based research experience.

Undergraduate students participating in the UCLA Undergraduate Research Consortium for Functional Genomics (URCFG) have conducted a two-phased screen using RNA interference (RNAi) in combination with fluorescent reporter proteins to identify genes important for hematopoiesis in Drosophila. This screen disrupted the function of approximately 3500 genes and identified 137 candidate genes for which loss of function leads to observable changes in the hematopoietic development. Targeting RNAi to maturing, progenitor, and regulatory cell types identified key subsets that either limit or promote blood cell maturation. Bioinformatic analysis reveals gene enrichment in several previously uncharacterized areas, including RNA processing and export and vesicular trafficking. Lastly, the participation of students in this course-based undergraduate research experience (CURE) correlated with increased learning gains across several areas, as well as increased STEM retention, indicating that authentic, student-driven research in the form of a CURE represents an impactful and enriching pedagogical approach.

MRI Automated T1 Signal Intensity Detection of Diffuse Brain Manganese Accumulation in Cirrhosis.

BACKGROUND AND PURPOSE: Cirrhosis is associated with diffuse brain manganese deposition, which results in increased signal intensity (SI) in the brain on T1-weighted images, most often visualized in the globus pallidus. The purpose of this study was to determine if automated image intensity measurements can detect SI differences in the basal ganglia and other regions reported to have manganese deposition in patients with cirrhosis compared with controls. METHODS: T1 FSPGR images were acquired on 28 patients with cirrhosis and 28 age-sex-matched controls. FreeSurfer T1 SI values were obtained for the globus pallidus, putamen, cerebral white matter, cerebral cortex, and brainstem. SI ratios were computed for globus pallidus normalized to white matter and brainstem. SI values and SI ratios were compared between groups using t-tests. RESULTS: Among people with cirrhosis, T1 SI was significantly increased in the globus pallidus, putamen, cerebral white matter, cerebral cortex, and brainstem (P< .001), and the globus pallidus to brainstem ratio was significantly increased (P< .001). No significant difference was seen for globus pallidus to cerebral white matter T1 SI ratio (P = .38). CONCLUSIONS: Automatic assessment of T1 SI allows for rapid, objective identification of widespread T1 shortening associated with manganese deposition in cirrhosis, consistent with the global deposition of neurotoxic manganese seen in pathology studies. This automated T1 assessment may have broader utility for other conditions beyond cirrhosis impacting T1 SI.

Evaluation of current treatment recommendations for chronic hepatitis B: a 2011 update.

BACKGROUND AND AIM: Guidelines for the treatment of chronic hepatitis B have been recently updated in the 2009 European Association for the Study of the Liver consensus statement, the 2008 US Panel, the 2008 Asian-Pacific consensus statement, and the 2009 American Association for the Study of Liver Disease practice guidelines. We sought to determine whether these guidelines identified patients who developed hepatocellular carcinoma (HCC) or who died of non-HCC liver-related deaths for antiviral therapy. METHODS: The criteria described in the new treatment guidelines were matched to the database of 369 hepatitis B surface antigen-positive patients, in whom 30 developed HCC and 37 died of non-HCC liver-related deaths during a mean follow up of 84 months. RESULTS: Using criteria for antiviral therapy as stated by the four current guidelines, 19-30% of patients who died of non-HCC liver-related complications, and 23-53% of patients who developed HCC, would have been excluded for antiviral therapy. If baseline serum albumin levels of ≤ 3.5 g/dL or platelet counts of ≤ 130,000 mm(3) were included into the treatment criteria, then 85-94% of patients who developed liver-related complications would have been recommended for antiviral therapy. Also, the addition of precore A1896 mutants and basal core promoter T1762/A1764 mutants would have identified 98.5-100% of these patients. CONCLUSION: The updated treatment guidelines for hepatitis B still excluded patients who developed serious liver-related complications. The inclusion of baseline serum albumin and platelet counts to current criteria would have identified a majority of these patients for antiviral therapy. These tests should be included into hepatitis B treatment strategies.