Deepak, Parakkal

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.

Due to increasingly nuanced Crohn disease therapy selection and disease evaluation, radiologic assessment of transmural healing, although aspirational, may be more complete than endoscopic assessment of mucosal healing, which is the current treatment target.

This consensus by the Society of Abdominal Radiology Inflammatory Bowel Disease Disease Focused Panel provides an updated imaging-based definition of small bowel Crohn disease stricture for CT and MR enterography.

INTRODUCTION: Many patients with chronic pouchitis and Crohn's-like disease of the pouch (CLDP) are treated with biologics; however, the comparative effectiveness of advanced therapies in this population has not been systematically evaluated. We sought to compare the effectiveness of antitumor necrosis factor α (anti-TNF) therapies and ustekinumab in patients with chronic inflammatory conditions of the pouch. METHODS: We conducted a prospective, multicenter, cohort study. We included patients with chronic pouchitis and CLDP initiating treatment with anti-TNF therapies or ustekinumab. The primary outcome was clinical remission at 6 months after induction. We also evaluated clinical remission at 6 months among patients with chronic pouchitis and CLDP separately. RESULTS: Among 132 patients, 106 (80%) had a diagnosis of CLDP and 82 (62%) initiated therapy with ustekinumab. A significantly higher proportion of patients with CLDP treated with ustekinumab were in clinical remission at 6 months as compared with patients treated with anti-TNF therapy (62% vs 40%, P = 0.027); however, there was no significant difference among patients with chronic pouchitis ( P = 0.946). There was no independent statistical significance in the odds of remission at 6 months among patients with CLDP among patients receiving ustekinumab compared with anti-TNF therapy (adjusted odds ratio 1.91, 95% confidence interval 0.69–5.30) after adjusting for presence of a fistula, number of preoperative advanced therapies, and number of advanced therapies after IPAA. DISCUSSION: These data suggest the potential benefit of ustekinumab in patients with CLDP and should prompt future novel effectiveness evaluations in this population.

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 < .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 and Aims Over 10% of patients with Crohn’s disease require permanent ileostomy. We aimed to summarize the existing data on diagnosis, definitions of recurrence, and management of Crohn’s disease patients with permanent ileostomy. Methods MEDLINE, Embase, and CENTRAL databases were searched from inception to February 6, 2024. Randomized controlled trials, cohort and cross-sectional studies, and case series of more than 5 patients reporting on postoperative recurrence or the need for surgery in patients with Crohn’s disease and permanent ileostomy were included. Search results were independently screened, and full text of all titles meeting eligibility criteria was obtained. Outcomes of interest included diagnostic techniques, recurrence definitions, and management approaches. We estimated pooled rates (with 95% confidence interval [CI]) of recurrence. Results Thirty cohort studies including 2055 Crohn’s patients with permanent ileostomy were included (53% female, median age at the time of ileostomy creation 32 years, the most common reason for ileostomy was refractory disease). The postoperative recurrence rate was 27% (95% CI, 21.3–33.3, 26 studies, 451/1805 patients). Modalities for diagnosis of Crohn’s disease recurrence were symptoms (15 studies), endoscopy (4 studies), histology from endoscopic biopsies (2 studies), imaging (5 studies), and surgery (22 studies). The reported definitions of recurrence for each modality were heterogeneous. Conclusions There is a lack of standardized monitoring tools and criteria for diagnosing recurrence in patients with Crohn’s disease and permanent ileostomy. The results of this systematic review will form the basis of a global expert recommendation exercise focused on developing management standards and trial endpoints for this condition.

Lay Summary In this prospective, multicenter observational study of highly refractory patients with Crohn’s disease of the pouch, risankizumab achieved the primary outcome of clinical remission in 50% and the more stringent secondary outcome of antibiotic- and steroid-free remission in 30.8% at 12 weeks.

Abstract Background and Aims Perianal fistuliing Crohn’s disease [PFCD] is an aggressive phenotype of Crohn’s disease defined by frequent relapses and disabling symptoms. A novel consensus classification system was recently outlined by the TOpCLASS consortium, which seeks to unify disease severity with patient-centred goals but has not yet been validated. We aimed to apply this to a real-world cohort and to identify factors that predict transition between classes over time. Methods We identified all patients with PFCD and at least one baseline and one follow-up pelvic MRI [pMRI]. TOpCLASS classification, disease characteristics, and imaging indices were collected retrospectively at time periods corresponding with respective MRIs. Results We identified 100 patients with PFCD, of whom 96 were assigned TOpCLASS Classes 1–2c at baseline. Most patients [78.1%] started in Class 2b, but changes in classification were observed in 52.1% of all patients. Male sex [72.0%, 46.6%, 40.0%, p = 0.03] and prior perianal surgery [52.0% vs 44.6% vs 40.0%, p = 0.02] were more frequently observed in those with improved class compared to unchanged and worsened class. Baseline pMRI indices were not associated with changes in classification; however, greater improvements in mVAI, MODIFI-CD, and PEMPAC were seen among those who improved. Linear mixed effect modelling identified only male sex [-0.31, 95% CI -0.60 to -0.02] with improvement in class. Conclusion The TOpCLASS classification highlights the dynamic nature of PFCD over time. However, our ability to predict transitions between classes remains limited and requires prospective assessment. Improvement in MRI index scores over time was associated with a transition to lower TOpCLASS classification.

Abstract Background Pivotal trials have shown that ustekinumab is effective in ulcerative colitis (UC). However, the population included in these trials do not represent the cohort of patients treated in the real world. In this study, we aimed to describe the effectiveness and safety of ustekinumab in a clinical cohort of patients with UC. Methods We performed a multicenter retrospective cohort study and included patients with active UC starting ustekinumab. Variables collected included demographics, clinical data, and disease activity (measured using partial Mayo score [PMS] and endoscopic Mayo score) at follow-up. The primary outcomes were cumulative rates of steroid-free clinical and biochemical remission (SFCBR), defined as a PMS <2 while off steroids and a normal C-reactive protein and/or fecal calprotectin. Results A total of 245 patients met inclusion criteria. The median time of follow-up was 33 (interquartile range, 17-53) weeks, and 214 (87.3%) had previous exposure to a biologic and/or tofacitinib. Rates of SFCBR, clinical remission, and endoscopic remission at 6 and 12 months were 12.0% (n = 16 of 139), 29.0% (n = 71 of 175), and 18.0% (n = 7 of 39), and 23.8% (n = 15 of 63), 54.3% (n = 57 of 105), and 31.0% (n = 9 of 29), respectively. Non-Hispanic White race, higher baseline PMS, and the use of concomitant corticosteroids were independently associated with failure to achieve SFCBR. Of the 73 that were dose escalated, 28.4% did not respond, 49.3% experienced a benefit, and 21.6% achieved remission. Conclusions In a population enriched with refractory UC, ustekinumab was well tolerated and induced remission in a significant number of patients. Larger studies with a longer follow-up are warranted.

Abstract Background Extraintestinal manifestations (EIMs) of inflammatory bowel diseases (IBDs) are a common and debilitating feature of disease, occurring in up to 40% of patients with IBD, yet predicting who may develop them is difficult. The goal of our study was to better characterize which patients may be at highest risk of developing not only 1 EIM, but also multiple EIMs, across both diseases. Methods A retrospective study of participants enrolled in the SPARC IBD (Study of Prospective Adult Research Cohort with IBD) registry was performed, and demographic and clinical data were analyzed. A total of 1211 patients with data available on EIMs were included, and differences among variables with vs without EIMs were assessed. Results A total of 329 participants with at least 1 EIM were identified, compared with 882 participants without any EIMs. Crohn’s disease patients and women were more likely to have 2 or more EIMs (P = .005 and P ≤ .001, respectively). Participants with ocular manifestations were likeliest to have at least 2 EIMs (P ≤ .001). Even when diagnosis was controlled for, involvement of the right colon (P = .021) was predictive of IBD-associated arthritis across both diseases in a multivariate generalized linear model. Conclusions This is the first comprehensive large-cohort assessment of how EIMs relate to one another at the individual vs systems levels. Further, our analysis is the first to recognize specific locations of colon involvement associated with EIMs of IBD, regardless of IBD type. These results are important in identifying patients at risk of developing future EIMs and may help with risk stratification when choosing treatments.