Comparative Study on Heart Disease Prediction Using Feature Selection Techniques on Classification Algorithms

Table 7

Summary of performance.

Feature selection category	Techniques	Maximum accuracy (%)	Number of features	Classification technique
Initial dataset	—	63.92	13	KNN
Filter	ANOVA	83.60	8	RF
	ANOVA	83.60	8	LR
	Chi-square	81.96	9	DT
	Chi-square	81.96	10	DT
	Mutual information	83.60	7	LR
	Relief	83.60	7	LR
Wrapper	FFS	85.24	5	RF
	FFS	85.24	5	DT
	BFS	88.52	6	DT
	EFS	83.60	4	LR
	RFE	85.24	7	KNN
	RFE	85.24	8	RF
Embedded	Lasso	81.96	11	DT
	Ridge	83.60	5	RF