Prediction of scleroderma renal crisis in patients of SSc: insight from the CRDC cohort study.

Abstract

Early personalized identification of SSc patients at risk of scleroderma renal crisis (SRC) can help provide better treatment and improve outcomes. This study aimed to create and validate a new multi-predictor Nomogram to predict SRC risk and compare it to an existing model. A retrospective multicentre observational study was conducted using clinical data from SSc patients with SRC registered in the Chinese Rheumatism Data Center (CRDC) database. Each SSc patient with SRC was matched with four SSc patients without SRC, registered consecutively afterward, as controls. Differences between the two groups were analysed using Student's t-test, Mann-Whitney U test, χ2 test, or Fisher's exact test. Key risk factors were identified using univariate and multivariate logistic regression, as well as LASSO regression. The Nomogram's performance was assessed with receiver operating characteristic curves, calibration plots, decision curve analysis (DCA), and bootstrap resampling for internal and external validation. Net reclassification improvement (NRI) and integrated discrimination improvement (IDI) were used to compare models. The Nomogram incorporated predictive factors such as myocardial involvement, SSc subtype, anaemia, platelet count, and disease duration. The area under the ROC curve showed strong discrimination in both the training and validation datasets. Calibration curves and the Hosmer-Lemeshow test indicated good agreement between predicted and actual outcomes. DCA demonstrated greater clinical net benefit. The NRI and IDI results showed significant improvement over the previous model. A Nomogram with improved predictive performance compared with the previous one was developed in a larger sample size in China.