决策树模型在2型糖尿病患病风险预测中的应用

发布时间：2018-04-11 05:37

本文选题：型糖尿病 + 决策树　；参考：《中国卫生统计》2016年06期

【摘要】：目的探究决策树模型在2型糖尿病患病风险预测中的应用,为预防和控制2型糖尿病的发生和发展提供临床指导。方法收集数据并进行预处理,采用C5.0算法构建分类模型,之后对其预测结果进行评估。结果采用决策树构建的三个模型的训练集准确率分别为79.98%、98.26%、99.55%,测试集的准确率分别为81.27%、98.16%、98.16%,预测准确率都较高。结论采用C5.0算法构建决策树模型,对预测糖尿病的患病风险具有一定的应用价值。
[Abstract]:Objective to explore the application of decision tree model in predicting the risk of type 2 diabetes, and to provide clinical guidance for preventing and controlling the occurrence and development of type 2 diabetes.Methods the data were collected and preprocessed, the classification model was constructed by C5.0 algorithm, and the prediction results were evaluated.Results the training set accuracy of the three models constructed by decision tree was 79.98 and 98.260.55, and the accuracy of test set was 81.279.1698.160.The accuracy of prediction was higher.Conclusion using C5.0 algorithm to construct decision tree model has certain application value in predicting the risk of diabetes mellitus.
【作者单位】：河北省秦皇岛市燕山大学经济管理学院;河北省秦皇岛市中医医院;东华软件股份有限公司;
【基金】：2015年河北省研究生创新资助项目(00302-6370027) 秦皇岛市科技支撑计划项目(201601B044)
【分类号】：R587.1

【相似文献】