Development and validation of a predictive model for chronic or persistent immune thrombocytopenia in children incorporating anti-glycoprotein IIb antibody: a retrospective cohort study utilizing LASSO regression and bootstrap stability analysis - Report - MDSpire
Advertisement
Development and validation of a predictive model for chronic or persistent immune thrombocytopenia in children incorporating anti-glycoprotein IIb antibody: a retrospective cohort study utilizing LASSO regression and bootstrap stability analysis
Clinical Report: Predictive Framework for Chronic Immune Thrombocytopenia in Pediatrics
Overview
This study developed a predictive model for chronic immune thrombocytopenia (cITP) in pediatric patients, integrating clinical factors and anti-glycoprotein IIb antibodies. The model demonstrated good discrimination and calibration, facilitating early risk stratification for children at risk of chronic progression.
Background
Pediatric immune thrombocytopenia (ITP) is an autoimmune disorder that can lead to chronic disease in 20%–30% of cases. Early identification of children at risk for chronic ITP is essential for personalized management and to reduce treatment-related complications. Current prognostic models lack the incorporation of platelet-specific immunological markers, highlighting the need for improved predictive frameworks.
Data Highlights
The study analyzed 381 children with newly diagnosed ITP, identifying 14 stable predictors for chronic progression. The final model included age, recent infection or vaccination history, platelet count, and anti-GPIIb antibody status.
Key Findings
Fourteen highly stable predictors for chronic ITP were identified.
The top three predictors were platelet count (100%), recent infection or vaccination history (100%), and anti-GPIIb antibody status (99.9%).
The final model showed good discrimination in the test set with an AUC of 0.743.
Calibration was satisfactory with a Hosmer–Lemeshow P value of 0.859.
The model achieved a negative predictive value of 94.7% at a low-risk threshold (predicted probability ≤ 15%).
Decision curve analysis indicated a positive net benefit across threshold probabilities of 0%–60%.
Clinical Implications
The predictive model developed in this study can assist clinicians in identifying pediatric patients unlikely to progress to chronic ITP. This early risk stratification may facilitate more personalized management strategies and reduce unnecessary treatment interventions.
Conclusion
The integration of anti-GPIIb antibody status into the predictive model enhances the ability to stratify risk for chronic ITP in pediatric patients, supporting early intervention strategies.
