中国实用神经疾病杂志2025，Vol.28Issue(10)：1278-1282,5.DOI:10.12083/SYSJ.240900
新生儿缺氧缺血性脑病预后Nomogram预测模型的建立及验证
Establishment and verification of Nomogram prognostic model for neonatal hypoxic-ischemic encephalopathy
摘要
Abstract
Objective To establish a Nomogram prognostic model for neonates with hypoxic-ischemic encephalopathy(HIE)by R software,and verify its efficacy.Methods Sixty-four HIE newborn were selected as the study subjects,all of whom were admitted to the Affiliated Minda Hospital of Hubei University for Nationalities from January 2020 to December 2023.According to the prognosis within 28 days after birth,the newborn were divided into survival group and death group.Clinical data,biochemical indexes and general maternal data of the two groups were collected.Univariate and multivariate Logistic regression analysis were used to screen the risk factors affecting the poor prognosis of HIE.The selected risk factors were incorporated into R software to construct a Nomogram prediction model for HIE prognostic risk,and the established model was verified.Results The 5 min Apgar score of the death group was lower than that of the survival group(P＜0.05),the severity of the disease(severe),and age of starting treatment,PCT and CRP levels were higher than those of the survival group(P＜0.05).Logistic regression analysis showed that 5 min Apgar score＜4 points,age at the beginning of treatment＞2 days,the severity of disease was severe,PCT＞24.35 ng/L and CRP＞22.45 mg/L were all risk factors for death in HIE(P＜0.05).ROC curve showed that area under the curve(AUC),95％CI,the sensitivity and specificity of the Nomogram risk model to predict the death of HIE was 0.854,0.641-0.986,94.70％and 78.60％,respectively(P＜0.001).Bootstrap method was used to conduct 1 000 internal repeated sampling verification on the constructed model,and the results showed that the C-index of the column-line prediction model was 0.821(95％CI:0.798-0.996).The calibration curve showed that both the predicted and the actual predicted values were near the ideal curve,and the Hosmer-Lemeshow goodness of fit curve test(x2=2.739,P=0.668).Conclusion Apgar score＜4 points,age of starting treatment＞2 days,the severity of disease is severe,PCT＞24.35 ng/L and CRP＞22.45 mg/L are risk factors for death in HIE.The Nomogram prediction model based on the above factors has good predictive value and calibration degree for HIE death.关键词
新生儿缺氧缺血性脑病/预后/危险因素/Nomogram模型/预测价值Key words
Hypoxic ischemic encephalopathy/Prognosis/Risk factor/Nomogram model/Predictive value分类
医药卫生引用本文复制引用
邢珩,唐琴,聂瑶,单丽..新生儿缺氧缺血性脑病预后Nomogram预测模型的建立及验证[J].中国实用神经疾病杂志,2025,28(10):1278-1282,5.基金项目
2017年湖北省教育厅科研计划项目(编号:D20171901) （编号:D20171901）
