A LASSO-based nomogram for predicting acute bilirubin encephalopathy in newborns with severe hyperbilirubinemia.

Background: To develop and validate a nomogram for predicting acute bilirubin encephalopathy (ABE) in newborns with severe hyperbilirubinemia. Methods: A retrospective analysis was conducted on 287 newborns with severe hyperbilirubinemia who visited the neonatal department of Shenzhen Children's Hospital from January 2015 to December 2022. A simple random sampling method was used to divide the subjects into a training group (200 cases) and a validation group (87 cases) at a ratio of 7:3, collecting general information and biochemical indicators of the neonates. LASSO regression and cross-validation were performed using RStudio (4.2.3) to select optimal predictors. A multivariate logistic regression model was then constructed and visualized as a nomogram. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA). Results: LASSO regression combined with multivariate logistic analysis identified six potential predictors selected by LASSO. Among these, four were independently associated with ABE in the multivariate model: delivery method (OR = 3.563, 95%CI: 1.391-9.145), birth trauma-related hemorrhage (OR = 3.024, 95%CI: 1.156-7.816), total bilirubin (OR = 1.012, 95%CI: 1.006-1.019), and reticulocyte percentage (OR = 1.185, 95%CI: 1.019-1.478) (all Conclusion: The nomogram developed in this study demonstrates good accuracy and predictive value, providing a reference for clinical individualized prediction of ABE risk in newborns with severe hyperbilirubinemia.