Devi, Jalpa

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 Obesity and related cardiometabolic comorbidities, including hypertension, dyslipidaemia, diabetes, metabolic dysfunction-associated steatotic liver disease and atherosclerotic cardiovascular disease, are increasingly prevalent among individuals with inflammatory bowel disease (IBD). These conditions influence disease activity, therapeutic response, surgical outcomes and overall quality of life, yet evidence remains fragmented. The M odulate O besity and relate D metabolic compl I cations F or Y ielding improvements in IBD outcomes (MODIFY-IBD) initiative aims to synthesise evidence and generate consensus recommendations to guide practice and future research in this area. This study describes a protocol for a structured evidence synthesis and Research ANd Development/University of California, Los Angeles (RAND/UCLA) Appropriateness Method (RUAM) consensus process. Methods and analysis We will conduct three systematic reviews and a structured evidence synthesis organised into three domains: (1) the impact of obesity on IBD outcomes, (2) the burden of cardiometabolic complications in IBD and (3) the management of overweight, obesity and cardiometabolic comorbidities in IBD. A multidisciplinary international panel of gastroenterologists, surgeons, endocrinologists, hepatologists, cardiologists and dietitians will assess each statement using the RAND/UCLA appropriateness method. Panellists will rate the appropriateness of each statement (only those that fall within their area of expertise) on a 1–9 scale (1–3=inappropriate, 4–6=uncertain and 7–9=appropriate), with medians rounded up (eg, 6.5=appropriate). Agreement will be assessed using the RAND Disagreement Index (DI<1.0=agreement). Ethics and dissemination This study will not involve direct patient participation, as it is based on evidence synthesis and expert consensus; therefore, formal research ethics committee approval will not be required. Patient representatives will contribute to the consensus process to provide contextual perspectives but no identifiable data will be collected. Findings will be disseminated through publication in peer-reviewed journals, presentation at major gastroenterology and IBD conferences and communication with professional societies. A lay summary and patient-friendly infographic will also be developed to facilitate translation of recommendations into clinical practice. PROSPERO registration numbers CRD420251178843: a systematic review of the impact of obesity on inflammatory bowel disease outcomes. CRD420251178799: a systematic review of cardiometabolic complications in inflammatory bowel disease. CRD420251174653: management of overweight, obesity and cardiometabolic comorbidities in inflammatory bowel disease: a systematic review.

Abstract Background We aimed to evaluate the effectiveness and safety of risankizumab (RZB) for Crohn’s disease (CD) in routine clinical practice. Methods We performed a retrospective review of a multicenter consortium of CD patients treated with RZB. Co-primary outcomes were week 12 clinical remission (Harvey Bradshaw Index [HBI] score of ≤4 or physician global assessment in those without HBI or with ileostomy) and 6-month endoscopic remission (Simplified Endoscopic Mucosal Assessment for Crohn’s Disease of 0-1 or absence of ulcers). Secondary outcomes included steroid-free clinical remission, clinical response, radiographic response, cumulative clinical and endoscopic remission rates at 6 and 12 months, and adverse events. Results A total of 309 patients were included (median disease duration 14 years [IQR, 6-24]; median follow-up 7.1 months [IQR, 4.1-10.3]). Most patients (85.8%) were advanced therapy (AT)-exposed, and 169 (54.7%) had prior ustekinumab (UST) exposure. Week 12 clinical remission rates were 49.7% (98/197) overall, and 44.2% (50/113) vs 57.1% (48/84) in UST-exposed vs naïve patients (P = .073). Among those with active disease on baseline endoscopy (n = 122) who had an available follow-up at 6 months, 52.4% (22/42) achieved endoscopic remission. Cumulative rates of clinical and endoscopic remission at 12 months were 65.0% and 49.5%, respectively. Cumulative 12-month endoscopic remission was 33.9% (19/56) in UST-exposed and 68.1% (32/47) in UST-naïve patients (P &lt; .001). Risankizumab was well-tolerated with no new safety signals identified. Conclusions In this large multicenter cohort of patients with CD, RZB was well-tolerated and effective in achieving favorable clinical and endoscopic outcomes in both AT-exposed and naïve populations, including those with exposure to UST.

Abstract Background There is limited data on the clinical effectiveness of upadacitinib (UPA), an oral selective inhibitor of Janus kinase 1 (JAKi), in patients with perianal Crohn's disease (pCD). The objective of this study was to evaluate the real-world effectiveness of UPA in pCD. Methods This retrospective analysis utilized data on adults (&gt;17 years) who initiated UPA at 45 mg/day for active pCD across 10 centers in the United States and Canada. Standardized data extraction and entry protocols were followed. The primary outcome was clinical response, defined as a ≥3-point reduction in Perianal Disease Activity Index (PDAI) between baseline and follow-up. Secondary outcomes included normalization of CRP (&lt;5 mg/L) or hsCRP (&lt;1 mg/L), clinical remission (PDAI ≤4), and rates of hospitalization, antibiotic use, corticosteroid initiation, and new pCD-related surgeries. Fistula healing on MRI pelvis fistula protocol was defined as an absence of T2-weighted hyperintensity and post-contrast enhancement on T1-weighted images. Predictive analyses used Cox proportional hazards models to evaluate baseline factors influencing time to PDAI remission, including BMI, CRP, albumin, PDAI, pCD disease duration, Montreal location and prior biologic exposure (&lt;2 vs 2+). Results A total of 81 patients were treated with UPA for pCD (median age 35 years and 54.3% male). Most had ileocolonic disease (65.4%), with 54% presenting with complex fistulas. Of these, 92.6% had prior anti-TNF exposure, and 91 (88.9%) had prior exposure to 2+ biologics (Table 1). During a median follow-up of 4 months, clinical response (PDAI) was achieved in 17.3%. Improvement was observed in pain and restriction of activities (27.2%), restriction of sexual activity (13.6%), reduction in number of fistulas (11.1%), degree of induration (11.1%), and discharge (35.8%). Median CRP reduction was 21.05% [IQR: 0.00–74.53], and 21.0% achieved a ≥50% reduction in CRP. MRI healing was limited to 17.7% (6/34). Proctitis decreased from 23.5% at baseline to 7.4% at follow-up. During follow-up, hospitalizations occurred in 9.9%, 14.8% required antibiotics, 8.6% underwent examination under anesthesia in 8.6%, seton placement in 6.2%, and abscess drainage in 6.2%. Patients with ileocolonic disease showed the highest remission (54%) and response (15%) rates, while MRI healing was limited across all Montreal locations (7.4%). Lower baseline CRP (p &lt; 0.05) and PDAI scores (p &lt; 0.01) predicted shorter time to remission. Number of prior biologic exposures (p =0.2) and Montreal location (p = 0.7) were not predictive of time to PDAI remission (Figure 1). Conclusion UPA in a real-world cohort is effective in the management of treatment-refractory pCD. Randomized trials are needed to confirm these observations.