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

Table 4

Performance of various predictive models on the heart disease dataset.

Model	Hyperparameters			Spec.	Sens.	MCC
Adaboost		85.55	90.33	87.75	82.92	0.708
Adaboost		86.66	94.68	87.75	85.36	0.731
Adaboost		84.44	94.68	85.71	82.92	0.686
Adaboost		82.22	97.58	81.63	82.92	0.643
Random forest		81.11	98.06	87.75	73.17	0.619
Extra tree		68.88	100.0	65.30	73.17	0.383
SVM (linear)		90.00	84.05	93.87	85.36	0.799
SVM (RBF)	,	90.00	84.54	93.87	85.36	0.799
Proposed	(50, 2)	93.33	84.05	100	85.36	0.872