Recognition Patterns Construction of Coronary Heart Disease Patients with Qi Stagnation Syndrome Based on Decision Tree

Abstract

Coronary heart disease (CHD), called Thoracic Obstruction in TCM, is one of the most important types of heart disease for its high incidence and high mortality. The methods of syndrome studies in TCM can not be completely in accordance with that of modern medicine because of the complexity itself. In this paper, we decide to investigate the ability of Decision Tree to predict CHD patients with or without qi stagnation syndrome. Predictions with CHAID Decision Tree (one type of the Decision Trees), we obtained recognition patterns made up of seven biological parameters. The accuracy of this diagnosis pattern was 80.7%, the sensitivity and specificity could reach 72.1% and 83.0%. The ADTree recognition pattern include six biological indicators. The accuracy of this diagnosis pattern was 94.6%, the sensitivity and specificity could reach 100% and 94.3%.