An approach for auxiliary diagnosing and screening coronary disease based on machine learning

How to accurately classify and predict whether an individual has Coronary Artery Disease (CAD) and the degree of coronary stenosis without using invasive examination? This problem has not been solved satisfactorily. To this end, the three kinds of machine learning (ML)algorithms, i.e., Boost Tree (BT), Decision Tree (DT), Logistic Regression (LR), are employed in this paper. First, 11 features including basic information of an individual, symptoms and results of routine physical examination are selected, and one label is specified, indicating whether an individual suffers from CAD or different severity of coronary artery stenosis. On the basis of it, a sample set is constructed. Second, each of these three ML algorithms learns from the sample set to obtain the corresponding optimal predictive results, respectively. The experimental results show that: BT predicts whether an individual has CAD with an accuracy of 94%, and this algorithm predicts the degree of an individuals coronary artery stenosis with an accuracy of 90%.