Machine learning for early prediction of sepsis-associated acute brain injury.
Machine learning for early prediction of sepsis-associated acute brain injury.
复制标题
用于早期预测败血症相关急性脑损伤的机器学习。
DOI：
10.3389/fmed.2022.962027
复制
发表时间：
2022
影响因子：
3.9
通讯作者：
中科院分区：
文献类型：
--
作者：
脓毒症相关性脑病(SAE)是指与脓毒症相关的弥漫性脑功能障碍，可导致较高的死亡率。我们的目标是开发和验证一个基于临床特征的最优机器学习模型，用于早期预测脓毒症相关的急性脑损伤。我们分析了重症监护医学信息集市(MIMIC III)临床数据库中的成年脓毒症患者。使用随机森林、支持向量机、决策树分类器、梯度增强机(GBM)、多层感知器(MLP)、极端梯度增强机(XGBoost)、光梯度增强机(LGBM)和传统的Logistic回归模型对候选模型进行训练。应用这些方法对基于精度和曲线下面积(AUC)的最优模型进行了开发和验证。总共有12,460名脓毒症患者符合纳入标准，6,284名患者(50.4%)遭受了脓毒症相关的急性脑损伤。与其他模型相比，LGBM模型取得了最好的性能。训练集和测试集的AUC均显示出极好的效度(训练集AUC 0.91，测试集AUC 0.87)。特征重要性分析显示，血糖、年龄、平均动脉压、心率、血红蛋白和ICU住院时间是预测脓毒症相关性急性脑损伤发生的前6个重要临床因素。几乎一半住进ICU的脓毒症患者都有脓毒症相关的急性脑损伤。LGBM模型比其他机器学习模型更好地识别脓毒症相关的急性脑损伤患者。血糖、年龄和平均动脉压是预测脓毒症相关性急性脑损伤发生的三个最重要的临床因素。
Sepsis-associated encephalopathy (SAE) is defined as diffuse brain dysfunction associated with sepsis and leads to a high mortality rate. We aimed to develop and validate an optimal machine-learning model based on clinical features for early predicting sepsis-associated acute brain injury. We analyzed adult patients with sepsis from the Medical Information Mart for Intensive Care (MIMIC III) clinical database. Candidate models were trained using random forest, support vector machine (SVM), decision tree classifier, gradients boosting machine (GBM), multiple layer perception (MLP), extreme gradient boosting (XGBoost), light gradients boosting machine (LGBM) and a conventional logistic regression model. These methods were applied to develop and validate the optimal model based on its accuracy and area under curve (AUC). In total, 12,460 patients with sepsis met inclusion criteria, and 6,284 (50.4%) patients suffered from sepsis-associated acute brain injury. Compared other models, the LGBM model achieved the best performance. The AUC for both train set and test set indicated excellent validity (Trainset AUC 0.91, Testset AUC 0.87). Feature importance analysis showed that glucose, age, mean arterial pressure, heart rate, hemoglobin, and length of ICU stay were the top 6 important clinical factors to predict occurrence of sepsis-associated acute brain injury. Almost half of patients admitted to ICU with sepsis had sepsis-associated acute brain injury. The LGBM model better identify patients with sepsis-associated acute brain injury than did other machine-learning models. Glucose, age, and mean arterial pressure were the three most important clinical factors to predict occurrence of sepsis-associated acute brain injury.
登录
查看更多内容
脓毒症相关脑病中钙结合蛋白 A8 和肿瘤坏死因子受体相关因子 6 的诊断和预测水平：一项前瞻性观察研究
影响因子：
6.1
作者：
Zhang LN;Wang XH;Wu L;Huang L;Zhao CG;Peng QY;Ai YH
通讯作者：
Ai YH
用于脓毒症早期检测的可解释的人工智能预测器
影响因子：
8.8
作者：
Yang, Meicheng;Liu, Chengyu;Li, Jianqing
通讯作者：
Li, Jianqing
影响因子：
3.1
作者：
Rosenblatt, Kathryn;Walker, Keenan A.;Nyquist, Paul
通讯作者：
Nyquist, Paul
影响因子：
9.8
作者：
Johnson AE;Pollard TJ;Shen L;Lehman LW;Feng M;Ghassemi M;Moody B;Szolovits P;Celi LA;Mark RG
通讯作者：
Mark RG
影响因子：
8.8
作者：
Angus, D C;Linde-Zwirble, W T;Pinsky, M R
通讯作者：
Pinsky, M R