Development of a Risk Assessment Model for Predicting Red Blood Cell Transfusion in Neonatal Patients.

Background: The goal was to develop a risk assessment model for predicting red blood cell (RBC) transfusion in neonatal patients to assist hospital blood supply departments in providing small portions of RBCs to those requiring RBC transfusion on time.

Methods: Clinical information was collected from 1,201 children admitted to the neonatal unit. Clinical factors associated with predicting RBC transfusion were screened, and prediction models were developed using stepwise and multifactorial logistic regression analyses, followed by the evaluation of prediction models using receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA).

Results: Overall, 81 neonatal patients were transfused with RBCs, and the variables of gestational age at birth, age < 1 month, receipt of mechanical ventilation, and infant anemia were included in the final prediction model. The area under the curve of the prediction model was 0.936 (0.921 - 0.949), which was significantly higher than that of the individual indicators of gestational age at birth, age at admission < 1 month, receipt of mechanical ventilation, and infant anemia (p < 0.001). DCA showed a standardized net benefit for the possible risk of infant RBC transfusion at 0.1 - 1.0.

Conclusions: We developed a risk assessment model to predict the risk of RBC transfusion in neonatal patients that can effectively assess the risk of RBC transfusion in children.