Abstract
BACKGROUND: Ustekinumab (UST) is recommended as the first-line treatment for patients with moderate to severe Crohn's disease (CD). However, the efficacy of certain patients may be suboptimal and necessitate intensive treatment or modification of the treatment regimen. We sought to establish a nomogram model to predict the short-term effectiveness of UST in moderate to severe CD patients. METHODS: We established a derivation cohort comprising patients diagnosed with CD and treated with UST at the Sixth Affiliated Hospital of Sun Yat-sen University from May 2020 to July 2023. The patient data, including demographic and clinical characteristics as well as treatment details, were systematically collected. The achievement of clinical remission (defined as Crohn's Disease Activity Index, CDAI < 150, without corticosteroid usage) after induction therapy was the endpoint observed during follow-up. Potential predictors were identified through the Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis. Subsequently, a multivariate logistic regression analysis was conducted to construct a nomogram model. The predictive accuracy and discriminative power of the model were assessed by Receiver Operating Characteristics (ROC) curves and calibration curves. Decision curve analysis (DCA) was employed to assess the clinical application value of the model. RESULTS: 162 patients were included in the derivation cohort. The predictor's selection was according to the minimum criteria. Prognostic factors, including duration, body mass index (BMI), smoking, extraintestinal manifestations (EIMs), perianal lesions (P), history of Vedolizumab therapy, and albumin levels (ALB), were identified and included in the nomogram. The model showed good discrimination and calibration on internal validation based on the bootstrap method (C-index: 0.843, 95% confidence interval: 0.768-0.903). Moreover, DCA demonstrated that the nomogram was clinically beneficial. CONCLUSION: We constructed a practical tool to assist clinicians in identifying moderate to severe CD patients who are expected to have a good clinical response to UST, promoting personalized treatment and the development of precision medicine.