新生儿缺氧缺血性脑病脑损伤的预测模型构建  

Predictive modeling for brain injuries in neonatal hypoxic-ischemic encephalopathy

作　　者：李德欢 李栋学 龙宗敏 王雪 沈达梅 何青 王荣品[3] LI Dehuan;LI Dongxue;LONG Zongmin;WANG Xue;SHEN Damei;HE Qing;WANG Rongpin(Urinary Surgery,Third Affiliated Hospital of Zunyi Medical University,First People’s Hospital of Zunyi,Zunyi 563000,China;Department of Radiology,Third Affiliated Hospital of Zunyi Medical University,First People’s Hospital of Zunyi,Zunyi 563000,China;Radiology Department of Guizhou Provincial People’s Hospital,International Exemplary Cooperation Base of Precision Imaging for Diagnosis and Treatment,Guiyang 550002,China)

机构地区：[1]遵义医科大学第三附属医院/遵义市第一人民医院泌尿外科,贵州遵义563000 [2]遵义医科大学第三附属医院/遵义市第一人民医院放射科,贵州遵义563000 [3]贵州省人民医院放射科/精准影像诊疗示范型国际科技合作基地,贵州贵阳550002

出　　处：《中国中西医结合影像学杂志》2025年第2期191-196,共6页Chinese Imaging Journal of Integrated Traditional and Western Medicine

基　　金：贵州省科技支撑计划项目(黔科合支撑[2019]2810号);遵义市科技计划项目(遵市科合HZ字[2021]267号)。

摘　　要：目的:构建缺氧缺血性脑病(HIE)新生儿发生多种脑损伤的预测模型。方法:回顾性纳入HIE患儿319例,根据MRI图像上脑损伤情况,分为多发脑损伤组87例和非多发脑损伤组232例。收集患儿围产期及产妇临床信息,使用单因素logistic回归分析筛选变量,采用多因素logistic回归分析构建预测模型并绘制列线图,评价模型区分度、校准度及决策曲线。结果:单因素logistic回归分析显示,宫内窘迫、Apgar评分、体质量、胎次及胎方位差异均有统计学意义(均P<0.01),其余变量差异均无统计学意义(均P>0.05)。多因素logistic回归分析显示,宫内窘迫、Apgar评分、体质量、胎次是HIE脑损伤的独立危险因素(均P<0.05),可用于建模。模型预测HIE患儿发生多种脑损伤的区分度良好,AUC为0.827(95%CI 0.775~0.879),截断值为0.24,敏感度、特异度分别为78.2%、75.0%;校准曲线显示模型预测风险与实际情况高度吻合,Hosmer-Lemeshow检验χ^(2)=4.64、P=0.79;决策曲线显示模型具有临床适用性。结论:基于产妇及胎儿围产期临床信息构建的预测模型对HIE患儿的脑损伤风险具有较好的预测能力,可为临床决策提供参考。Objective:To develop a predictive model for multiple brain injuries in neonates with hypoxic-ischemic encephalopathy(HIE).Methods:This retrospective study analyzed 319 HIE neonates,87 cases with multiple brain injuries and 232 cases without multiple injuries.Maternal and perinatal variables were assessed through univariate logistic regression screening,followed by multivariate logistic regression.A nomogram was constructed and evaluated for discrimination,calibration,and clinical utility.Results:Univariate logistic regression analysis showed that the intrauterine distress,Apgar score,birth weight,parity,and fetal position had statistical differences(all P<0.01).Multivariate logistic regression analysis confirmed intrauterine distress,Apgar score,birth weight,and parity as independent risk factors for brain injury(all P<0.05),which were used for modeling.The model predicted the differentiation of various brain injuries in HIE neonatus was good,with AUC of 0.827(95%CI 0.775—0.879),cut-off value of 0.24,sensitivity of 78.2%,specificity of 75.0%.The calibration curve showed that the risk predicted by the model was highly consistent with the actual situation(Hosmer-Lemeshow test,χ^(2)=4.64,P=0.79).The decision curve showed that the model had clinical applicability.Conclusions:This perinatal parameter-based prediction model effectively stratifies multiple brain injury risk in HIE neonates,offering clinical references for early intervention planning.

关 键 词：缺氧缺血 脑 婴儿 新生 脑损伤 预测模型 

分 类 号：R72[医药卫生—儿科]