Influencing Factors of Heart Disease Based on Decision Tree-logistic Regression Model
In order to study the influencing factors of heart disease,a decision tree-logistic regression method is pro-posed to identify the influencing factors of heart disease by using the heart disease data set extracted from UCI database.In order to verify the effectiveness of the method,the accuracy,F1 score and specificity were used as evaluation indexes of the model.The experimental results showed that decision tree-logistic regression showed that the type of chest pain,the blood disease of thalassemia,the maximum heart rate achieved and the number of major blood chromosomes examined by fluorescence were influencing factors for heart disease.From the model evaluation,all indexes of the proposed decision tree-logistic regression model are higher than those of logistic regression and decision tree.Meanwhile,the AUC value of the area under ROC curve reached 0.858,indicating that the model was better for analyzing heart disease factors.
NETL
NSTL
万方数据
