Wang Shanshan, Wang Chan, Zheng Siqi, Dou Haiping, Qu Danyang, Wang Yuqian, Yang Liu
Department of Pediatrics, The Second Hospital of Dalian Medical University, Dalian, China.
Department of Otolaryngology, The Second Hospital of Dalian Medical University, Dalian, China.
PeerJ. 2025 Sep 3;13:e20017. doi: 10.7717/peerj.20017. eCollection 2025.
Neonatal hyperbilirubinemia is a common condition and a leading cause of hospitalization in newborns in their first week of life. Thus early identification of infants at risk is particularly important. In this study, we explored risk factors for its development of neonatal hyperbilirubinemia, and then constructed and validated an easy-to-use nomogram for the early prediction.
This study was conducted retrospectively and non-interventionally, involving 646 neonates born at the Second Hospital of Dalian Medical University between January 2021 and January 2024. The study population was systematically partitioned through cluster sampling into a training set comprising of 454 neonates and a validation set of 192 neonates, adhering to a 7:3 ratio, utilizing the R-4.4.0 program. Independent predictors of neonatal hyperbilirubinemia were identified using least absolute shrinkage and selection operator (LASSO) regression from the training set, and a nomogram was constructed based on these predictors. The performance of the nomogram was assessed using receiver operating characteristic (ROC) curves, calibration curves and decision curve analysis (DCA).
Among 646 newborns, there were 350 males and 296 females, with a mean gestational age (GA) of 38.4 ± 1.4 weeks and birth weight (BW) of 3,264.1 ± 490.7 g. Six independent factors associated with hyperbilirubinemia were identified: GA, BW, premature rupture of membranes (PROM) ≥ 18 hours or concurrent maternal fever, maternal-infant blood type incompatibility with positive direct Coombs test, supplementation with probiotics, and weight loss > 9% within 3 days. Calibration curves indicated that the nomogram closely matched the actual observed values in both the training and validation sets. The areas under the ROC curves for predicting hyperbilirubinemia were 0.825 (95% confidence interval (CI) [0.777-0.874]) in the training set and 0.829 (95% CI [0.757-0.901]) in the validation set. DCA showed that the nomogram has clinical applicability.
The nomogram constructed in this study has good differentiation, calibration and clinical applicability, and has the potential to be used for predicting neonatal hyperbilirubinemia.
新生儿高胆红素血症是一种常见病症，也是新生儿出生后第一周住院的主要原因。因此，早期识别有风险的婴儿尤为重要。在本研究中，我们探讨了新生儿高胆红素血症发生的危险因素，然后构建并验证了一种易于使用的列线图用于早期预测。
本研究采用回顾性非干预性研究，纳入了2021年1月至2024年1月在大连医科大学附属第二医院出生的646例新生儿。使用R-4.4.0程序，通过整群抽样将研究人群按7:3的比例系统地分为一个由454例新生儿组成的训练集和一个由192例新生儿组成的验证集。使用最小绝对收缩和选择算子（LASSO）回归从训练集中确定新生儿高胆红素血症的独立预测因素，并基于这些预测因素构建列线图。使用受试者操作特征（ROC）曲线、校准曲线和决策曲线分析（DCA）评估列线图的性能。
646例新生儿中，男性350例，女性296例，平均胎龄（GA）为38.4±1.4周，出生体重（BW）为3264.1±490.7g。确定了与高胆红素血症相关的6个独立因素：胎龄、出生体重、胎膜早破（PROM）≥18小时或并发母体发热、母婴血型不合且直接抗人球蛋白试验阳性、补充益生菌以及出生后3天内体重下降>9%。校准曲线表明，列线图在训练集和验证集中均与实际观察值密切匹配。训练集中预测高胆红素血症的ROC曲线下面积为0.825（95%置信区间（CI）[0.777-0.874]），验证集中为0.829（95%CI[0.757-0.901]）。DCA表明列线图具有临床适用性。
本研究构建的列线图具有良好的区分度、校准度和临床适用性，具有用于预测新生儿高胆红素血症的潜力。
