Heart Risk Failure Prediction Using a Novel Feature Selection Method for Feature Refinement and Neural Network for Classification

Table 2

Results of different subsets of features for the heart disease dataset.

					Sens. (%)	Spec. (%)
12	4	3	83.09	90.00	85.36	93.87	0.799
12	11	8	87.92	90.00	85.36	93.87	0.799
11	(5, 6)	4	82.60	91.11	85.36	95.91	0.822
11	(11, 12)	4	81.15	90.00	87.80	91.83	0.798
10	(4 to 6)	7	85.99	90.00	82.92	95.91	0.801
7	(3 to 8)	49	95.16	91.11	87.80	93.87	0.820
6	(6 to 12)	6	81.15	91.11	95.12	87.75	0.825
13	—	1	85.02	90.00	87.80	91.83	0.798