机器学习预测急性轻型缺血性卒中患者转归不良

Machine learning predicts poor outcome in patients with acute minor ischemic stroke

目的建立急性轻型缺血性卒中(acute minor ischemic stroke,AMIS)发病后90 d转归不良的机器学习预测模型,并解释各项危险因素的重要性。方法回顾性纳入2022年6月至2023年12月期间合肥市第二人民医院收治的AMIS患者。AMIS定义为入院时美国国立卫生研究院卒中量表(National Institutes of Health Stroke Scale,NIHSS)评分≤5分。根据发病后90 d改良Rankin量表评分将患者分为转归良好组(<2分)和转归不良组(≥2分)。采用递归特征消除(recursive feature elimination,RFE)方法筛选转归不良的特征变量。基于logistic回归(logistic regression,LR)、支持向量机(supported vector machine,SVM)和极端梯度提升(eXtreme Gradient Boosting,XGBoost)3种机器学习算法构建AMIS转归不良预测模型,并通过受试者工作特征曲线下面积(area under curve,AUC)和校准曲线比较模型的预测性能。采用沙普利加和解释(SHapley Additive exPlanations,SHAP)算法解释最佳预测模型中特征变量的作用。结果共纳入225例AMIS患者,其中152例(67.56%)转归良好,73例(32.44%)转归不良。RFE分析显示,基线NIHSS评分、基线收缩压、高血压、糖尿病、低密度脂蛋白胆固醇、高半胱氨酸、体重指数、D-二聚体以及年龄是与AMIS患者转归不良相关的特征变量。受试者工作特征曲线分析显示,LR模型预测效果最佳[AUC=0.888,95%置信区间(confidence interval,CI)0.807~0.970],其次是XGBoost模型(AUC=0.888,95%CI 0.796~0.980),SVM模型性能最低(AUC=0.849,95%CI 0.754~0.944)。校准曲线显示,LR模型的校准度表现最好。SHAP显示,基线收缩压、基线NIHSS评分、糖尿病、高血压和体重指数是AMIS患者转归不良排名前五的危险因素。结论LR算法在预测AMIS患者转归不良方面具有稳定优越的性能,基线收缩压、基线NIHSS评分、糖尿病、高血压和体重指数是AMIS患者转归不良的重要危险因素。

Objectives To develop a machine learning prediction model for poor outcome of acute minor ischemic stroke(AMIS)at 90 days after onset and to explain the importance of various risk factors.Methods Patients with AMIS admitted to the Second People's Hospital of Hefei from June 2022 to December 2023 were included retrospectively.AMIS was defined as the National Institutes of Health Stroke Scale(NIHSS)score≤5 at admission.According to the modified Rankin Scale score at 90 days after onset,the patients were divided into a good outcome group(<2)and a poor outcome group(≥2).Recursive feature elimination(RFE)method was used to screen characteristic variables of poor outcome.Based on logistic regression(LR),supported vector machine(SVM),and extreme Gradient Boosting(XGBoost)machine learning algorithms,prediction models for poor outcome of AMIS were developed,and the predictive performance of the models was compared by the area under the curve(AUC)of receiver operating characteristic(ROC)curve and the calibration curve.Shapley Additive exPlanations(SHAP)algorithm was used to explain the role of characteristic variables in the optimal prediction model.Results A total of 225 patients with AMIS were included,of which 152(67.56%)had good outcome and 73(32.44%)had poor outcome.Multivariate analysis showed that baseline NIHSS score,baseline systolic blood pressure,hypertension,diabetes,low-density lipoprotein cholesterol,homocysteine,body mass index,D-dimer,and age were the characteristic variables associated with poor outcome in patients with AMIS.The ROC curve analysis shows that the LR model had the best predictive performance(AUC=0.888,95%confidence interval[CI]0.807-0.970),the next was the XGBoost model(AUC=0.888,95%CI 0.796-0.980),while the SVM model had the lowest performance(AUC=0.849,95%CI 0.754-0.944).The calibration curve showed that the LR model performed the best in terms of calibration accuracy.SHAP showed that baseline systolic blood pressure,baseline NIHSS score,diabetes,hypertension and body mass index were the top five risk factors for poor outcome of patients with AMIS.Conclusions The LR algorithm has stable and superior performance in predicting poor outcome of patients with AMIS.Baseline systolic blood pressure,baseline NIHSS score,diabetes,hypertension and body mass index are the important risk factors for poor outcome of patients with AMIS.