There is insufficient evidence to confirm the efficacy of ustekinumab (UST) in promoting fistula closure in perianal fistulizing Crohn’s disease (CD) patients. We aimed to evaluate the efficacy of UST in a real-world setting. The data were retrospectively analyzed. Intestinal clinical and endoscopic changes were evaluated. Fistula radiological outcomes were determined using the Van Assche score. A total of 108 patients were included, 43.5% of whom had complex perianal fistulas. Intestinal clinical and endoscopic remission was achieved in 65.7% and 31.5% of patients, respectively. The fistula clinical remission and response rates were 40.7% and 63.0%, respectively, with a significant reduction in Perianal Crohn’s disease Activity Index [5.0(3.0, 8.0) vs. 7.5(5.0, 10.0), p < 0.001] and Crohn’s Anal Fistula Quality of Life [23.5(9.3, 38.8) vs. 49.0(32.3, 60.0), p < 0.001]. Radiological healing, partial response, no change, and deterioration were observed in 44.8%, 31.4%, 13.4%, and 10.4% of patients, respectively. The cut-off UST trough concentration for predicting fistula clinical remission was 2.11 μg/mL with an area under the curve of 0.795, a sensitivity of 93.3%, and a specificity of 67.6%. UST is efficacious in promoting radiological fistula closure in patients with perianal fistulizing CD. A UST trough concentration over 2.11 μg/mL was correlated with a higher likelihood of perianal fistula clinical remission.

Background and Aims: Inflammatory bowel disease (IBD) requires effective treatment options. Upadacitinib, a Janus kinase 1 (JAK1) inhibitor, has shown effectiveness in trials for Crohn’s disease (CD) and ulcerative colitis (UC). This study evaluates its real-world effectiveness and safety. Methods: We conducted a multicenter retrospective cohort study in tertiary care centers, involving patients treated with upadacitinib from January 2023 to September 2024. The study included adult patients aged 18 years or older, diagnosed with UC or CD, who received at least 8 weeks of upadacitinib therapy. Treatment outcomes were evaluated using established clinical, endoscopic, imaging, histological, and laboratory parameters. Results: A total of 236 IBD patients received upadacitinib treatment. In 80 UC patients at 8 weeks, 64.0% achieved steroid-free remission, 57.6% clinical remission, and 81.8% response. Endoscopic remission was 35.8% (p = 0.039), with 63.3% response and 35.8% mucosal healing. Histological remission reached 29.2% (p = 0.009). For 156 CD patients at 12 weeks, 76.8% achieved steroid-free remission (p < 0.001), 77.8% clinical remission (p < 0.001), and 81.0% response. Mean CDAI decreased from 214.9 to 117.5 (p < 0.001). Endoscopic remission was 19.4%, with 48.9% response and 4.9% mucosal healing. Radiological remission was 9.1% with 85.7% response. Intestinal ultrasound showed 5.7% remission and 56.7% response. Conclusions: Upadacitinib demonstrates significant real-world effectiveness and safety in IBD, particularly in biologic-resistant cases, as evidenced by high rates of steroid-free remission and clinical response. These outcomes are likely due to its targeted JAK1 inhibition, which effectively reduces inflammation and promotes mucosal healing. Future research should focus on long-term safety, comparative effectiveness with other biologics, and its application in diverse patient populations. These findings support the integration of upadacitinib into IBD management strategies.

Background/Objectives: The development of anti-drug antibodies (ADA) significantly diminishes the clinical efficacy of infliximab (IFX) in Crohn’s disease (CD). This study aimed to develop and validate an interpretable machine learning (ML) framework for predicting ADA risk during IFX induction therapy using multidimensional clinical and laboratory data. Methods: We conducted a retrospective analysis of 606 CD patients who initiated IFX induction between January 2023 and August 2024 at the Sixth Affiliated Hospital of Sun Yat-sen University. Predictor selection was performed through univariate analysis and least absolute shrinkage and selection operator (LASSO) regression, with significant features further evaluated via multivariate logistic regression. Seven ML models were developed and evaluated mainly based on area under the curve (AUC), F1 score, and Brier score. Model interpretability was enhanced using SHapley Additive exPlanations (SHAP). Results: Among the 606 CD patients, 145 (23.93%) developed ADA during IFX induction. Independent predictors included serum trough levels of IFX (TLI), erythrocyte sedimentation rate (ESR), history of delayed treatment, prior exposure to anti-TNF agents, and concomitant use of immunosuppressants (IMM). The XGBoost algorithm outperformed others, with an AUC of 0.899, accuracy of 0.851, F1 score of 0.640, and Brier score of 0.102 in validation. SHAP analysis identified TLI and ESR as the most influential predictors, with history of delayed treatment and prior exposure to anti-TNF agents showing moderate impact, while concomitant use of IMM was associated with a protective effect. Conclusions: We developed an interpretable ML model that effectively predicts ADA formation in CD patients undergoing IFX induction therapy, facilitating early risk stratification and personalized treatment planning. This approach integrates advanced analytics with clinical practice to support precision medicine in CD management.