Developing and evaluating a predictive model for neonatal hyperbilirubinemia based on gene polymorphism and clinical risk factors.

Background: Neonatal hyperbilirubinemia (NHB) is one of the most common diseases in the neonatal period. Without timely diagnosis and treatment, it can lead to long-term complications. In severe cases, it may even result in fatality. The gene and clinical risk factors play important roles in the development and progression of NHB.

Methods: In this study, we conducted a cohort study and analyzed 3258 newborns from the Jilin Women And Children Health Hospital in northern China, including 372 children with hyperbilirubinemia. We established a predictive model using a logistic regression model based on clinical risk factors and the polymorphism of the G211A locus in the gene of newborns. Furthermore, the performance of the prediction model was evaluated using the ROC curve.

Results: The logistic regression model indicates that the following factors are associated with an increased risk of NHB: the time when stool turns yellow [ ≤ 0.001, 1.266 (95% : 1.125-1.425)]; neonatal cephalohematoma [ ≤ 0.001, 33.642 (95% : 21.823-51.861)]; hemolytic disease of newborn [ ≤ 0.001, 33.849 (95% : 18.589-61.636)]; neonatal weight loss [ ≤ 0.001, 11.275 (95% : 7.842-16.209)]; neonatal premature rupture of membranes (PROM) history [ = 0.021, 1.422 (95% : 1.056-1.917)]; genetic polymorphism at the gene G211A locus. Gestational age is a protective factor [ ≤ 0.001, 0.766 (95% : 0.686-0.855)]. Compared to natural labor, cesarean section is a protective factor [ = 0.011, 0.711 (95% : 0.546-0.926)], while assisted delivery is a risk factor [ = 0.022, 2.207 (95% : 1.121-4.346)]. The area under the curve (AUC) of this prediction model is 0.804 (95% : 0.777-0.831), indicating good discrimination ability and value for predicting the risk of NHB after birth.

Conclusion: We have developed and evaluated a predictive model that combines gene polymorphism and clinical risk factors for the first time. By using this nomogram and taking into account the results of serum total bilirubin measurement or transcutaneous bilirubin measurement, early prediction of the risk of neonatal hyperbilirubinemia can be achieved.