Classification and Regression Tree Analysis in Acute Coronary Syndrome Patients

Objectives: The objectives of this study are to use CART (Classification and regression tree) and step-wise regression to 1) define the predictors of quality of life in ACS (acute coronary syndrome) patients, using demographics, ACS symptoms, and anxiety as independent variables; and 2) discuss and compare the results of these two statistical approaches. Back- ground: In outcome studies of ACS, CART is a good alternative approach to linear regression; however, CART is rarely used. Methods: A descriptive survey design was used with 100 samples recruited. Result and Conclusions: Anxiety is the most significant predictor and also a stronger predictor than symptoms of ACS for the quality of life. The anxiety level patients experienced at the time heart attack occurred can be used to predict quality of life a month later. Furthermore, the majority of ACS patients experienced a moderate to high level of anxiety during a heart attack.