Construction and validation of neonatal hypoglycemia risk prediction model
10.3969/j.issn.1673-9701.2024.11.010
- VernacularTitle:新生儿低血糖风险预测模型的构建及验证
- Author:
Shaoyan ZHANG
1
;
Wei ZHANG
1
;
Tingting CAI
2
Author Information
1. Ward 24, Obstetric Nursing Unit, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou 315000, Zhejiang, China
2. School of Nursing, Fudan University, Shanghai 200032, China
- Publication Type:Journal Article
- Keywords:
Neonates;
Hypoglycemia;
Risk factors;
Predictive models
- From:
China Modern Doctor
2024;62(11):40-43
- CountryChina
- Language:Chinese
-
Abstract:
Objective To investigate the risk factors of neonatal hypoglycemia,establish the risk prediction model of neonatal hypoglycemia and test the effectiveness of the model.Methods Retrospective analysis was performed to collect clinical data of 727 newborns and pregnant mothers who were delivered in a Grade Ⅲ general hospital from October 2018 to August 2020.Univariate analysis and multivariate Logistic regression analysis were used to analyze related risk factors to construct prediction models.The clinical data of 150 newborns and pregnant women from September 2020 to February 2021 were selected to test the efficacy of the model.Results Multivariate Logistic regression analysis showed that feeding problems,neonatal hypothermia,neonatal complications,gestational diabetes and fetal distress were independent risk factors for neonatal hypoglycemia(P<0.05).The model verification results showed that the area under the curve(AUC)was 0.883,the sensitivity was 82.97%,the specificity was 88.35%,the positive predictive value was 76.47%,the negative predictive value was 91.92%,and the total accuracy of the model was 88.67%,which had a good prediction ability.Conclusion The prediction model established in this study has a good ability to predict the risk of neonatal hypoglycemia,which can be used to provide reference for early screening of high-risk groups of neonatal hypoglycemia and starting predictive nursing intervention measures.