Abstract Objective:To analyze the chronic risk factors of childhood immune thrombocytopenia (ITP),and to provide basis for early judging the prognosis and treatment of the disease. Methods: A total of 161 inpatients diagnosed with ITP in the Department of Pediatrics, the Affiliated Huaian No.1 People’s Hospital of Nanjing Medical University from January 2019 to December 2021 were selected as the research subjects, and they were followed up for more than one year. According to the course of the disease, they were divided into non-chronic ITP group (84 cases) and chronic ITP group (77 cases). Multivariate logistic regression was conducted to analyze the independent risk factors of chronic ITP. The efficacy of the model was evaluated by receiver operating characteristic curve (ROC) , calibration curve and decision curve analysis(DCA) . Results:①Independent risk factors for chronic ITP included age, Th/Tc, serum cystatin C and C3（P＜0.05）. ②The areas under the ROC curves to predict chronic ITP by age, Th/Tc, serum cystatin C and C3 and their combination were 0.725(95％CI:0.647~0.804), 0.741(95％CI:0.665~0.817), 0.706(95％CI:0.626~0.785), 0.635(95％CI:0.550~0.720), 0.853(95％CI:0.794~0.911), respectively. ③The calibration curve is close to the ideal curve. ④The DCA curves showed better performance of the prediction model in the 0.1~0.85 threshold probability range. Conclusion: Age, Th/Tc, serum cystatin C and C3 were independent influencing factors in children with chronic ITP, and their combination showed a better predictive value for the prognosis.