Abstract: 【Abstract】 Objective To analyze the influencing factors of neonatal hyperbilirubinemia (NHB), and construct and verify the prediction model based on these factors. Methods A retrospective study was conducted, including 155 neonates with NHB admitted to Tangshan Maternal and Child Health Hospital from February 2022 to February 2023 as the NHB group, and 186 healthy neonates born during the same period as the non-NHB group. Multivariate logistic regression analysis was used to evaluate the associations between neonatal intestinal microflora, intestinal barrier function, immune-related nutrients, and the risk of NHB. Multivariate logistic regression analysis was used to evaluate the associations between neonatal intestinal microflora, intestinal barrier function, immune-related nutrients, and the risk of NHB. A nomogram prediction model was constructed, and its performance was assessed using the C-index, receiver operating characteristic (ROC) curve, and calibration curve in R 4.2.3 software. Statistical analysis was performed using independent- samples t-test and χ 2 -test. Results Compared with the non-NHB group, the proportion of neonates with gestational age < 37 weeks and amniotic fluid contamination were higher (all P<0.05); the abundances of Bifidobacterium, Lactobacillus, and Escherichia coli in the intestinal microbiota were all higher (all P<0.001); the levels of diamine oxidase(DAO), D-lactic acid, and bacterial endotoxin in intestinal barrier function were all higher (all P<0.001); and the levels of vitamin A, arginine, zinc in immune-related nutrients were all lower (all P<0.001). The results of multivariate Logistic regression showed that intestinal microbiota (Bifidobacterium, Lactobacillus, Escherichia coli) elevation, intestinal barrier function (DAO, D-lactic acid, bacterial endotoxin) elevation, and immune-related nutrients (vitamin A, arginine, zinc) reduction were all independent risk factors for the occurrence of NHB (all P<0.05). ROC curve analysis demonstrated that the AUC values for predicting NHB based on these indicators were all >0.600, with odds ratios (OR) >1, indicating good predictive value. Based on the above influencing factors, a nomogram prediction model was established. The C-index value of calibration curve was 0.953, indicating that the prediction model has good discrimination; the AUC value of the prediction model was 0.998(95% CI:0.996-1.000), indicating that the prediction model has good predictive performance. Conclusion The increase in intestinal microbiota (Bifidobacterium, Lactobacillus, Escherichia coli), the enhancement of intestinal barrier function (DAO, D-lactic acid and bacterial endotoxin), and the decrease of immune-related nutrients (vitamin A, arginine, zinc) are all independent risk factors for the occurrence of NHB. The nomogram prediction model constructed based on intestinal microflora, intestinal barrier function, and immune-related nutrients can intuitively and accurately predict the risk of NHB occurrence, providing reference for early clinical screening and intervention.
2026, Vol. 14 
