Neural Network-Based Coronary Heart Disease Risk Prediction Using Feature Correlation Analysis

Table 5

Nine features (age, BMI, To_chole, HDL, SBP, DBP, triglyceride, smoking, and diabetes) are selected and used for feature correlation analysis.

Input dataset	Learned NNk
	X(age+δ)	X(BMI+δ)	X(To_chole+δ)	X(HDL+δ)	X(SBP+δ)	X(DBP+δ)	X(triglyceride+δ)	X(smoking+δ)	X(diabetes+δ)
Age	0.080	0.009	0.016	0.004	0.011	0.008	0.009	0.022	0.019
BMI	0.031	0.038	0.019	0.013	0.025	0.026	0.037	0.010	0.036
To_chole	0.021	0.012	0.094	0.017	0.042	0.070	0.013	0.013	0.064
HDL	0.011	0.010	0.011	0.011	0.010	0.008	0.009	0.009	0.002
SBP	0.012	0.007	0.001	0.020	0.041	0.035	0.008	0.013	0.016
DBP	0.496	0.013	0.043	0.017	0.017	0.021	0.001	0.029	0.045
Triglyceride	0.009	0.005	0.008	0.008	0.003	0.005	0.009	0.005	0.006
Smoking	0.005	0.004	0.004	0.003	0.003	0.008	0.002	0.012	0.007
Diabetes	0.002	0.006	0.003	0.007	0.008	0.019	0.005	0.009	0.019
Average	0.074	0.012	0.022	0.011	0.017	0.022	0.010	0.014	0.024
Candidates of correlated feature	DBP	To_chole, DBP	DBP	BMI, To_chole, SBP, DBP	BMI, To_chole, DBP	BMI, To_chole, SBP	To_chole	Age, DBP	BMI, To_chole, DBP