Development of a prediction model for neonatal hypoglycemia risk factors: a retrospective study

Background It’s challenging for healthcare workers to detect neonatal hypoglycemia due its rapid progression and lack of aura symptoms. This may lead brain function impairment the newborn, placing a significant care burden on family creating an economic society. Tools early diagnosis are lacking. study aimed identify newborns at high risk developing by prediction model. Methods Using retrospective design, pairs (470) women their in tertiary hospital from December 2021 September 2022 were included this study. Socio-demographic data clinical mothers collected. Univariate multivariate logistic regression used screen optimized factors. A nomogram was constructed using R software, calibration curve receiver operator characteristic (ROC) utilized evaluate model performance. Results Factors integrated into maternal age (odds ratio [OR] =1.10, 95% CI: 1.04, 1.17), fasting period (OR=1.07, 1.03, 1.12), ritodrine use (OR=2.00, 1.05, 3.88), gestational diabetes mellitus (OR=2.13, 1.30, 3.50), week (OR=0.80, 0.66, 0.96), fetal distress (OR=1.76, 1.11, 2.79) body mass index (OR=1.50, 1.24, 1.84). The area under (AUC) 0.79 (95% confidence interval [CI]: 0.75, 0.82), specificity 0.82, sensitivity 0.62. Conclusion demonstrated good predictive development identifies advancing age, extended before delivery, use, diagnosis, increase probability hypoglycemia, while reduces hypoglycemia.