Abstract Background Crohn’s disease (CD) has a variable clinical course and a heterogeneous therapeutic response. Clinical decision support tools (CDSTs) for vedolizumab (VDZ) and ustekinumab (UST) have been developed to guide personalized treatment, but comparative evidence—particularly regarding the UST-CDST—remains limited. We aimed to compare the predictive performance of both CDSTs in CD. Methods We conducted a retrospective, multicenter study (9 centers), including CD patients treated with UST or VDZ. For each patient, the UST-CDST and VDZ-CDST were applied and categorized into low, intermediate, or high probability of response. The primary outcome was steroid-free clinical remission (SFCR) at week 52. Secondary outcomes included need for surgery, hospitalization and phenotypic progression. Model discrimination was evaluated with ROC/AUC, and predictors assessed via multivariable Cox regression. Results Of 711 screened patients, CDSTs were applicable in 440 UST: 74.5% (n = 328); VDZ: 25.5% (n = 112). In multivariable Cox models, VDZ-CDST independently predicted SFCR only in VDZ-patients (HR 2.00; 95% CI 1.19–3.35), while UST-CDST predicted SFCR only in UST-patients (HR 1.54; 95% CI 1.23–1.94). VDZ-CDST identified SFCR with an AUC of 0.70 in VDZ-patients and 0.59 in UST-patients, whereas UST-CDST achieved an AUC of 0.63 and 0.68, respectively. Both scores significantly discriminated the risk of surgery, hospitalization and phenotypic progression in both biologics. Agreement between the two CDSTs was 75%. Conclusion Both UST-CDST and VDZ-CDST demonstrated significant predictive performance for clinical response and disease progression in CD, with superior performance for their target biologic. These findings support the integration of CDSTs into clinical practice promoting a personalized treatment in Crohn’s disease. References: Dulai, P. S., Boland, B. S., Singh, S., Chaudrey, K., Koliani-Pace, J. L., Kochhar, G., Parikh, M. P., Shmidt, E., Hartke, J., Chilukuri, P., Meserve, J., Whitehead, D., Hirten, R., Winters, A. C., Katta, L. G., Peerani, F., Narula, N., Sultan, K., Swaminath, A., Bohm, M., … Cao, C. (2018). Development and Validation of a Scoring System to Predict Outcomes of Vedolizumab Treatment in Patients With Crohn’s Disease. Gastroenterology, 155(3), 687–695.e10. https://doi.org/10.1053/j.gastro.2018.05.039 Dulai, Parambir, et al. “637 Clinical prediction model and decision support tool for ustekinumab in Crohn’s disease.” Official journal of the American College of Gastroenterology| ACG 114 (2019): S373. Conflict of interest: Ms. Camões Neves, Joana: No conflict of interest Costa, Dalila Amélia Amorim: No conflict of interest Gonçalves, Nuno: No conflict of interest Melo, Beatriz: No conflict of interest Cristiano, Margarida: No conflict of interest Portela, Francisco: No conflict of interest Portugal, Margarida: No conflict of interest Fernandes, Daniela: No conflict of interest Catarina, Garcia: No conflict of interest Teixeira, Pedro: No conflict of interest Neves, Andre: No conflict of interest Mendes, Ivo: No conflict of interest Vaz Conde, Patrícia: No conflict of interest Damasceno, José: No conflict of interest Guimaraes, Andreia: No conflict of interest Arroja, Bruno: No conflict of interest Goncalves, Raquel: No conflict of interest Leal, Tiago Filipe: No conflict of interest
Neves et al. (Thu,) studied this question.