基于改进的决策树算法分级诊疗模型研究

Research on the hierarchical diagnosis and treatment model improved based on decision tree algorithm

针对目前三甲医院看病挤、看病难、看病贵等问题,亟需对目前的诊疗体系进行改进,对大医院的患者进行分类和分流,文中设计了一种基于改进的决策树算法的分级诊疗机制,利用改进决策树算法的训练自学习特征,通过对孕妇的就医历史行为数据的分析,提取出影响就医医院的特征,并构建数据分类模型。根据已有的孕产妇就医选择数据,找到相应的不同特征孕妇的决策树模型,在模型基础上构建基于决策树算法的分级诊疗分类,从而可以有效地提高就医的效率,避免造成医院就医的不均衡。

In view of the current problems of crowded,difficult,and expensive medical visits in the top three hospitals,it is urgent to improve the current diagnosis and treatment system to classify and divert patients in large hospitals.A hierarchical diagnosis and treatment mechanism based on an improved decision tree algorithm is designed.Using the training self-learning features of the improved decision tree algorithm,through the analysis of the pregnant women’s medical history behavior data,the characteristics of the hospital are extracted and a data mining model is built.According to the current medical selection data of pregnant women,the corresponding decision tree models of pregnant women with different characteristics are found,and a hierarchical diagnosis and treatment classification is built based on the decision tree algorithm on the basis of the model,which can effectively improve the efficiency of medical treatment and avoid the imbalance of hospital medical treatment.