Zhang Y, Wen J, Zeng M, Zhang L, Pang Y. A Nomogram Prediction Model for Persistent Pulmonary Hypertension of the Newborn in Neonates Hospitalized for the First Time After Birth.
Pediatr Emerg Care 2024;
40:e195-e201. [PMID:
38718806 DOI:
10.1097/pec.0000000000003167]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 08/30/2024]
Abstract
OBJECTIVE
Persistent pulmonary hypertension of the newborn (PPHN) is one of the critical neonatal diseases associated with high morbidity and mortality. This study attempted to conduct a nomogram prediction model for performing early identification of PPHN and providing effective information for clinical practice.
METHODS
A total of 456 newborns who first admitted to the hospital after birth were included in the analysis, including 138 newborns with PPHN and 318 newborns without PPHN (as controls). The optimal predictive variables selection was performed based on LASSO (least absolute shrinkage and selection operator) regression and multivariate logistic regression. Using the selected variables, a nomogram prediction model was developed. To validate the model, the model was assessed using the receiver operating characteristic curve, calibration plot, and clinical impact curve.
RESULTS
Six predictors, namely, gestational age, neonatal respiratory distress syndrome, the levels of hemoglobin and creatine kinase-MB, gestational thyroid dysfunction, and Pa o2 , were identified by LASSO and multivariate logistic regression analysis from the original 30 variables studied. The constructed model, using these predictors, exhibited favorable predictive ability for PPHN, with an area under the receiver operating characteristic of 0.897 (sensitivity = 0.876, specificity = 0.785) in the training set and 0.871 (sensitivity = 0.902, specificity = 0.695) in the validation set, and was well calibrated, as indicated by the PHosmer-Lemeshow test values of 0.233 and 0.876 for the training and validation sets, respectively.
CONCLUSIONS
The model included gestational age, neonatal respiratory distress syndrome, the levels of hemoglobin and creatine kinase-MB, gestational thyroid dysfunction, and Pa o2 had good prediction performance for predicting PPHN among newborns first admitted to the hospital after birth.
Collapse