[Construction and evaluation of a thrombosis risk prediction model in patients with primary immune thrombocytopenia]

Objective: To analyze the risk factors for thrombosis in patients with primary immune thrombocytopenia (ITP) , construct a prediction model for thrombosis, and evaluate its performance. Methods: The clinical data of 334 ITP patients hospitalized at Qilu Hospital of Shandong University from January 2018 to December 2022 were retrospectively analyzed. Logistic regression was used to identify independent risk factors for thrombosis and construct the prediction model. Results: Among 334 ITP patients, 40 (12.0% ) developed thrombosis, including 18 males and 22 females. The incidence rates of arterial thrombosis, venous thrombosis, and mixed thrombosis were 9.58% (32/334) , 1.80% (6/334) , and 0.60% (2/334) , respectively. Univariate analysis showed that age, ITP duration >1 year, comorbid hypertension, coronary heart disease, diabetes, and PLT were risk factors for thrombosis in ITP patients (all P<0.05) . Multivariate analysis revealed that age, ITP duration >1 year, comorbid coronary heart disease, and PLT were independent risk factors for thrombosis (all P<0.05) . The area under the ROC curve for the nomogram prediction model was 0.80 (95% CI: 0.72-0.88) , and the calibration curve showed good consistency between the predicted and actual thrombosis rates in ITP patients. The Hosmer-Lemeshow goodness-of-fit test showed χ(2)=5.838, P=0.665. Conclusion: This study developed a nomogram prediction model for thrombosis in ITP patients, which can help identify high-risk patients.