Development and external validation of a prediction model for venous thromboembolism in systemic lupus erythematosus

ObjectivePatients with systemic lupus erythematosus (SLE) have an increased risk of venous thromboembolism (VTE). We conducted this study to develop a risk score algorithm for VTE in patients with SLE that provides individualised risk estimates.MethodsWe developed a clinical prediction model of VTE in 4502 patients with SLE based on the Chinese SLE Treatment and Research group cohort (CSTAR) from January 2009 to January 2020 and externally validated in 3780 patients with SLE in CSTAR from January 2020 to January 2022. Baseline data were obtained and VTE events were recorded during the follow-up. The prediction model was developed to predict VTE risk within 6 months in patients with SLE, using multivariate logistic regression and least absolute shrinkage and selection operator. SLE-VTE score and nomogram were established according to the model.ResultsA total of 4502 patients included in the development cohort, 135 had VTE events. The final prediction model (SLE-VTE score) included 11 variables: gender, age, body mass index, hyperlipidaemia, hypoalbuminaemia, C reactive protein, anti-beta 2GPI antibodies, lupus anticoagulant, renal involvement, nervous system involvement and hydroxychloroquine, with area under the curve of 0.947 and 0.808 in the development (n=4502) and external validation cohort (n=3780), respectively. According to the net benefit and predicted probability thresholds, we recommend annual screening of VTE in high risk (>= 1.03%) patients with SLE.ConclusionVarious factors are related to the occurrence of VTE in patients with SLE. The proposed SLE-VTE risk score can accurately predict the risk of VTE and help identify patients with SLE with a high risk of VTE who may benefit from thromboprophylaxis.