Significance of Visible Non-Invasive Risk Attributes for the Initial Prediction of Heart Disease Using Different Machine Learning Techniques

Table 2

Performance measures of developed heart disease models.

	Performance measures
Models	Sensitivity (%)	Specificity (%)	Accuracy (%)	Precision (%)	Error rate (%)	AUROC (%)
Decision tree	82	80	81	84	18	81
K nearest neighbor	73	66	70	69	30	70
Support vector machine	82	81	82	84	17	82
Random forest	85	83	84	85	15	85
Naive Bayes	72	66	69	70	30	70