Verification and optimization of the VTE risk stratification system for multiple myeloma

Venous thromboembolism (VTE) is a common complication in multiple myeloma (MM), particularly within the first six months of treatment initiation and disease relapse. This study optimized the MM-VTE risk stratification system to enable early and accurate identification of VTE risk. We retrospectively analyzed 433 newly diagnosed MM (NDMM) patients from Fu Xing Hospital, Capital Medical University, who were divided into derivation (n = 332) and validation (n = 101) cohorts. Independent risk factors were identified using univariate and multivariate analyses. The optimized MM-VTE risk stratification system was constructed by integrating the identified independent risk factors and thromboprophylaxis status. Model performance was assessed using the area under the curve (AUC). Internal validation was performed with bootstrap resampling, and external validation was conducted using the validation cohort. In the derivation cohort, the 6-month VTE incidence was 8.43% (28/332). Independent risk factors included female sex, bed rest at diagnosis, and platelet count above the upper limit of normal. The optimized MM-VTE risk stratification system was developed by integrating these factors and thromboprophylaxis. The AUC for the IMWG score was 0.605, and the AUCs for the MM-VTE risk stratification system before and after optimization were 0.660 and 0.742, respectively. In the validation cohort, the AUCs of the MM-VTE risk stratification system before and after optimization were 0.659 and 0.730, respectively.The optimized MM-VTE risk stratification system demonstrated improved discriminatory performance in our cohort, offering a potentially more reliable and clinically accessible tool for guiding thromboprophylaxis in Chinese patients.