Mohamed, Mouhand F H

Abstract Background Large language models (LLMs) offer promise for systematic review data extraction, but performance in complex multidisciplinary domains and utility for clinical statement generation remain insufficiently described. Objectives To evaluate Google NotebookLM for AI-assisted data extraction and RAND/UCLA consensus statement generation in a systematic review of IBD, obesity, and cardiometabolic comorbidities. Methods Studies were organized into domain-specific notebooks; structured prompts generated standardized evidence tables. Two independent reviewers validated outputs against full-text articles using a four-category error classification. Cell-level accuracy and critical accuracy (cells free of major factual errors) were the primary metrics; workflow time was compared against a published conventional extraction benchmark. Concordance between AI-generated and expert-finalized statements was assessed. Results Across 57 articles, 1,710 data cells were extracted; 151 (8.83%) were flagged, yielding 91.17% cell-level accuracy. Major factual errors occurred in only 4 cells (0.23%), for a critical accuracy of 99.77%. Most errors were minor omissions (59.6%) or incomplete extractions (30.5%); domain error rates ranged from 7.08% to 11.33%. The pipeline required 17.7 versus a projected 165.1 person-hours (89.3% reduction). PICO-structured prompting generated 70 candidate statements; 58 of 112 finalized panel statements (51.8%) were AI-derived, and 85.7% were retained in the finalized set. Conclusion Google NotebookLM demonstrates feasibility as a primary extraction and synthesis tool in a multidisciplinary systematic review, with extractive incompleteness as the principal limitation and substantial time savings over conventional approaches. Its novel application to RAND/UCLA consensus statement generation extends AI-assisted evidence synthesis to clinical consensus generation workflow.

Background and aims Percutaneous endoscopic gastrostomy (PEG) is an essential procedure for patients who require long-term enteral nutrition but are unable to eat orally. However, it carries a risk of bleeding, particularly in patients on anticoagulation or dual antiplatelet therapy (DAPT). This study aimed to assess the bleeding risk associated with continuing anticoagulation or DAPT during PEG placement. Methods Using the TriNetX US Collaborative Network Database, we analyzed four cohorts: patients on anticoagulants, patients not on anticoagulants, patients on DAPT, and patients on aspirin (ASP), focusing on gastrostomy-related bleeding within 7 and 30 days, along with secondary outcomes such as mortality and the need for blood transfusion or endoscopic reintervention. Results Our analysis showed no statistically significant difference in the 7-day bleeding risk between the anticoagulant and no anticoagulant groups. However, a higher 30-day bleeding risk was observed in the anticoagulant group (0.9 vs. 0.4%, P = 0.007). There was no significant difference in the incidence of severe bleeding events requiring endoscopic intervention or blood transfusion. In addition, the difference in the bleeding risk between the DAPT and ASP groups was not statistically significant within 7 and 30 days. Conclusion These findings suggest that while anticoagulant use increases the risk of minor post-PEG bleeding, it does not lead to a higher incidence of severe bleeding. Additionally, the continuation of DAPT was not associated with statistically significant increase in bleeding risk. This study provides valuable insights into the management of antithrombotic therapy in patients undergoing PEG.

INTRODUCTION: The impact of glucagon-like peptide-1 receptor agonists (GLP-1RAs) on colonoscopy bowel preparation is unclear. METHODS: We searched multiple databases for studies comparing bowel preparation quality between GLP-1RA users and the control group. Using a random-effects model, we calculated pooled odds ratios and mean differences with 95% confidence intervals (CIs). Inadequate bowel preparation (IBP) rate was the primary outcome, and Boston Bowel Preparation Scale mean score was the secondary outcome. RESULTS: Five studies with 10,833 patients (n = 5,434 GLP-1RAs vs n = 5,399 control) were included. The IBP rate was higher in the GLP-1RAs group compared with the control group (odds ratios 2.10, 95% CI 1.41–3.13, P = 0.0003). Furthermore, the mean Boston Bowel Preparation Scale score was lower in the GLP1-RAs group compared with the control group (mean differences −0.34; 95% CI −0.51, −0.17; P = 0.0001). DISCUSSION: Our findings suggest that using GLP-1RA increases the risk of IBP.

INTRODUCTION: Data on the risk of post-polypectomy bleeding after endoscopic mucosal resection (EMR) in patients with cirrhosis are limited. METHODS: This retrospective cohort study used the US Collaborative Network to assess post-polypectomy bleeding risk after colorectal EMR in patients with cirrhosis compared with controls. Using one-to-one propensity score matching, the primary outcome measured was bleeding within 30 days post-EMR. The bleeding risk was further stratified by cirrhosis severity (compensated and decompensated). RESULTS: After propensity score matching, each cohort included 2,381 patients. Patients with cirrhosis had a higher risk of post-polypectomy bleeding (odds ratio [OR] 1.38, 95% confidence interval [CI] 1.05–1.82, P = 0.02). However, endoscopic reinterventions for hemostasis were similar between cirrhosis and control cohorts (OR 1.20, 95% CI 0.71–2.05, P = 0.50). The post-polypectomy bleeding risk was significantly higher in patients with decompensated cirrhosis (OR 1.65, 95% CI 1.12–2.42, P = 0.01), while those with compensated cirrhosis showed no increased risk of post-polypectomy bleeding (OR 1.15, 95% CI 0.85–1.54, P = 0.37). DISCUSSION: The post-polypectomy bleeding risk was higher in patients with decompensated cirrhosis, while the bleeding risk was not increased in those with compensated disease. Optimizing patients with cirrhosis, especially with decompensated disease, before colorectal EMR and monitoring for post-procedure bleeding remain important. A conservative, supportive approach to managing bleeding in patients with cirrhosis may be as effective as in those without cirrhosis.