利用健康社会决定因素和机器学习方法预测儿童创伤性脑损伤的结局
本研究纳入新英格兰最大安全网医院2006年1月至2013年12月收治的15岁以下钝性创伤患儿211例,分析健康社会决定因素对头部损伤结局的影响,并构建整合社会经济因素的机器学习算法预测头部CT创伤相关阳性或阴性结果。与儿科头部CT结局显著相关的因素包括损伤严重度评分(ISS)、年龄和保险类型(P<.05),有临床相关创伤相关头部CT表现的患儿年龄中位数1.8岁,无此类表现者年龄中位数9.1岁;包含ISS时精细高斯支持向量机测试AUC最高(0.923),准确率0.837、敏感度0.647、特异度0.962。
要点
- 有临床相关头部CT表现的患儿年龄中位数1.8岁,无此类表现者9.1岁,5岁以下儿童风险更高。
- 与儿科头部CT结局显著相关的因素包括ISS、年龄和保险类型(P<.05)。
- 含ISS时精细高斯SVM测试AUC 0.923、准确率0.837、敏感度0.647、特异度0.962。
核心结论
- 儿童TBI中临床相关头部CT表现的关键预测因素包括ISS、年龄和健康社会决定因素,5岁以下儿童风险更高;新型精细高斯SVM模型表现优于其他机器学习算法,预测准确率高,该工具有望改善临床决策同时减少儿童辐射暴露。
研究设计与样本
- 队列研究,纳入新英格兰最大安全网医院2006年1月至2013年12月就诊的15岁以下钝性创伤患者211例,收集种族、语言、家庭收入和保险类型等社会经济数据及ISS、年龄、性别和受伤机制等参数,多变量分析筛选预测头部CT阳性结局的显著因素;队列按80%训练集(168例)和20%测试集(43例)分层抽样拆分,训练22种多参数机器学习算法,采用5折交叉验证和GridSearchCV超参数调优,表现最佳的模型在测试集上评估。
诊断标准与关键数值
- 与儿科头部CT结局显著相关的因素为ISS、年龄和保险类型(P<.05);含ISS时精细高斯支持向量机测试AUC 0.923、准确率0.837、敏感度0.647、特异度0.962;粗略树准确率0.837、AUC 0.837、敏感度0.824、特异度0.846;不含ISS时窄神经网络表现最佳,准确率0.837、AUC 0.857、敏感度0.765、特异度0.885。
临床应用与阅片要点
- 作者认为该工具在改善临床决策同时减少儿童辐射暴露方面显示出前景。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND AND PURPOSE: Considerable socioeconomic disparities exist among pediatric patients with traumatic brain injury (TBI). This study aims to analyze the effects of social determinants of health on head injury outcomes and to create a novel machine-learning algorithm (MLA) that incorporates socioeconomic factors to predict the likelihood of a positive or negative trauma-related finding on head CT.
MATERIALS AND METHODS: A cohort of patients with blunt trauma younger than age 15 who presented to the largest safety net hospital in New England between January 2006 and December 2013 (n=211) was included in this study. Patient socioeconomic data such as race, language, household income, and insurance type were collected alongside other parameters like Injury Severity Score (ISS), age, sex, and mechanism of injury. Multivariable analysis was performed to identify significant factors in predicting a positive head CT outcome. The cohort was split into 80% training (168 samples) and 20% testing (43 samples) data sets by using stratified sampling. Twenty-two multiparametric MLAs were trained with 5-fold cross-validation and hyperparameter tuning via GridSearchCV, and top-performing models were evaluated on the test data set.
RESULTS: Significant factors associated with pediatric head CT outcome included ISS, age, and insurance type (P < .05). The age of the subjects with a clinically relevant trauma-related head CT finding (median = 1.8 years) was significantly different from the age of patients without such findings (median = 9.1 years). These predictors were utilized to train the machine learning models. With ISS, the fine Gaussian support vector machine (SVM) achieved the highest test AUC (0.923), with accuracy = 0.837, sensitivity = 0.647, and specificity = 0.962. The coarse tree yielded accuracy = 0.837, AUC = 0.837, sensitivity = 0.824, and specificity = 0.846. Without ISS, the narrow neural network performed best with accuracy = 0.837, AUC = 0.857, sensitivity = 0.765, and specificity = 0.885.
CONCLUSIONS: Key predictors of clinically relevant head CT findings in pediatric TBI include ISS, age, and social determinants of health, with children younger than 5 at higher risk. A novel fine Gaussian SVM model outperformed other MLAs, offering high accuracy in predicting outcomes. This tool shows promise for improving clinical decisions while minimizing radiation exposure in children.
引用
- Kaliaev A, Vejdani-Jahromi M, Gunawan A, et al. Outcome Prediction in Pediatric Traumatic Brain Injury Utilizing Social Determinants of Health and Machine Learning Methods. AJNR Am J Neuroradiol. 2026. PMID: 40789613. doi:10.3174/ajnr.A8961
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。