Research Article

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

Table 5

Reduced feature subsets using filter, wrapper, and embedded methods.

Feature selection methodFeaturesSize of feature subset
F1F2F3F4F5F6F7F8F9F10F11F12F13

ANOVA00100001110116
00100001111117
01100001111118
11100001111119
111000111111110

Chi-square00001001110116
10001001110117
10011001110118
10111001110119
101110111101110

Mutual information00100001110116
00100001111117
00101001111118
00101101111119
011011011111110

Relief00100000111116
00100001111117
01100001111118
11100001111119
111000111111110

Forward feature selection (FFS)10100000000114
11100000000115
11100001000116
10101001010117
10111011010119

Backward feature selection (BFS)01100010100116
10111011010108
11001111011019
10111010110119
10111011010119

Exhaustive feature selection (EFS)00000000100113
00100000100114
00101001100116
01101001010117
111110111001110

Recursive feature elimination (RFE)01100000101105
01100000101116
01100010101117
01100010111118
01100110111119

Lasso (L1)111110111101111

Ridge (L2)01100010100105