Rai, Victoria

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.

INTRODUCTION: Limited guidance exists for the postdischarge care of patients with ulcerative colitis hospitalized for moderate-severe flares. METHODS: RAND methodology was used to establish appropriateness of inpatient and postdischarge steroid dosing, discharge criteria, follow-up, and postdischarge biologic or small molecule initiation. A literature review informed on the panel's voting, which occurred anonymously during 2 rounds before and after a moderated virtual session. RESULTS: Methylprednisolone 40–60 mg intravenous every 24 hours or hydrocortisone 100 mg intravenous 3 times daily is appropriate for inpatient management, with methylprednisolone 40 mg being appropriate if intolerant of higher doses. It is appropriate to discharge patients once rectal bleeding has resolved (Mayo subscore 0–1) and/or stool frequency has returned to baseline frequency and form (Mayo subscore 0–1). It is appropriate to discharge patients on 40 mg of prednisone after observing patients for 24 hours in hospital to ensure stability before discharge. For patients being discharged on steroids without in-hospital biologic or small molecule therapy initiation, it is appropriate to start antitumor necrosis factor (TNF) therapy after discharge for anti-TNF-naive patients. For anti-TNF-exposed patients, it is appropriate to start vedolizumab or ustekinumab for all patients and tofacitinib for those with a low risk of adverse events. It is appropriate to follow up patients clinically within 2 weeks and with lower endoscopy within 4–6 months after discharge. DISCUSSION: We provide recommendations on the inpatient and postdischarge management of patients with ulcerative colitis hospitalized for moderate-severe flares.