Wang Kai, Gu Longyuan, Liu Wencai, Xu Chan, Yin Chengliang, Liu Haiyan, Rong Liangqun, Li Wenle, Wei Xiu'e
Department of Neurology, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China.
Key Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China.
Front Neurol. 2023 Feb 23;14:1092534. doi: 10.3389/fneur.2023.1092534. eCollection 2023.
To explore the predictors of death in acute ischemic stroke (AIS) patients within 1 year based on machine learning (ML) algorithms.
This study retrospectively analyzed the clinical data of patients hospitalized and diagnosed with AIS in the Second Affiliated Hospital of Xuzhou Medical University between August 2017 and July 2019. The patients were randomly divided into training and validation sets at a ratio of 7:3, and the clinical characteristic variables of the patients were screened using univariate and multivariate logistics regression. Six ML algorithms, including logistic regression (LR), gradient boosting machine (GBM), extreme gradient boosting (XGB), random forest (RF), decision tree (DT), and naive Bayes classifier (NBC), were applied to develop models to predict death in AIS patients within 1 year. During training, a 10-fold cross-validation approach was used to validate the training set internally, and the models were interpreted using important ranking and the SHapley Additive exPlanations (SHAP) principle. The validation set was used to externally validate the models. Ultimately, the highest-performing model was selected to build a web-based calculator.
Multivariate logistic regression analysis revealed that C-reactive protein (CRP), homocysteine (HCY) levels, stroke severity (SS), and the number of stroke lesions (NOS) were independent risk factors for death within 1 year in patients with AIS. The area under the curve value of the XGB model was 0.846, which was the highest among the six ML algorithms. Therefore, we built an ML network calculator (https://mlmedicine-de-stroke-de-stroke-m5pijk.streamlitapp.com/) based on XGB to predict death in AIS patients within 1 year.
The network calculator based on the XGB model developed in this study can help clinicians make more personalized and rational clinical decisions.
基于机器学习（ML）算法探索急性缺血性卒中（AIS）患者1年内死亡的预测因素。
本研究回顾性分析了2017年8月至2019年7月在徐州医科大学第二附属医院住院并诊断为AIS的患者的临床资料。患者按7:3的比例随机分为训练集和验证集，采用单因素和多因素逻辑回归筛选患者的临床特征变量。应用六种ML算法，包括逻辑回归（LR）、梯度提升机（GBM）、极端梯度提升（XGB）、随机森林（RF）、决策树（DT）和朴素贝叶斯分类器（NBC），建立模型以预测AIS患者1年内的死亡情况。在训练过程中，采用10折交叉验证方法在内部验证训练集，并使用重要性排名和SHapley加性解释（SHAP）原则对模型进行解释。验证集用于外部验证模型。最终，选择性能最佳的模型构建基于网络的计算器。
多因素逻辑回归分析显示，C反应蛋白（CRP）、同型半胱氨酸（HCY）水平、卒中严重程度（SS）和卒中病灶数量（NOS）是AIS患者1年内死亡的独立危险因素。XGB模型的曲线下面积值为0.846，在六种ML算法中最高。因此，我们基于XGB构建了一个ML网络计算器（https://mlmedicine-de-stroke-de-stroke-m5pijk.streamlitapp.com/）来预测AIS患者1年内的死亡情况。
本研究开发的基于XGB模型的网络计算器可帮助临床医生做出更个性化、合理的临床决策。
