基于决策树的中青年脑卒中患者生存质量预测模型研究

Prediction model of quality of life in young and middle-aged patients with stroke based on decision tree

目的:构建基于决策树的中青年脑卒中患者生存质量预测模型,评价预测模型的准确性和合理性。方法:采用便利抽样法,选取2021年9月至2022年8月连云港市第一人民医院神经内科住院的384例中青年脑卒中患者为研究对象,以卡方自动交互检验(CHAID)算法构建中青年脑卒中患者生存质量决策树模型,并通过受试者工作特征(ROC)曲线下面积(AUC)评估决策树模型的预测效果。结果:384例患者生存质量差的比例为48.7%。决策树模型包含3层共11个节点,提取应对方式(积极或消极)、高血压(是或非)、早期康复锻炼、社会支持水平6条分类规则,筛选出3类高危人群。决策树模型AUC为0.919。结论:决策树模型对中青年脑卒中患者生存质量预测简便易行,预测效果较好,可用于筛选中青年脑卒中患者生存质量差的高危人群。

Objective:To evaluate the accuracy and rationality of decision tree in the prediction of young and middle-aged stroke patients,and to provide a basis for improving the quality of life of patients.Methods:The convenience sampling method was used to select 384 middle-aged and young stroke patients who were hospitalized in the department of neurology in the First People’s Hospital of Lianyungang from September 2021 to August 2022 as the research objects.The quality of life decision tree model of middle-aged and young stroke patients was built by using CHAID algorithm.And the area under receiver operating characteristics(ROC)curve(AUC)was used to evaluate the prediction effect of decision tree model.Results:The proportion of poor quality of life in 384 patients was 48.7%.The decision tree model contained 11 nodes in 3 layers,and 6 classification rules were extracted to screen out 3 high-risk groups,namely coping style(positive or negative),hypertension(yes or no),early rehabilitation exercise,and social support level.The AUC of decision tree model was 0.919.Conclusions:Decision tree model is simple and effective in predicting quality of life of young and middle-aged stroke patients,and can be used to screen high-risk groups with poor quality of life of young and middle-aged stroke patients.