Significance of Visible Non-Invasive Risk Attributes for the Initial Prediction of Heart Disease Using Different Machine Learning Techniques

Table 1

Feature selection techniques providing weight to each risk attribute.

Attributes	Feature selection techniques with their results and mean values
	ETC	GBC	RF	RFE	XGB	MEAN
Age	0.92	0.92	0.87	0.25	0.92	0.78
Sex	0.0	0.0	0.11	0.83	0.0	0.19
Alcohol consumption	0.09	0.09	0.09	0.75	0.09	0.22
Physical activity	0.25	0.25	0.08	0.67	0.25	0.30
Healthy diet	0.71	0.71	0.52	1.0	0.71	0.73
BMI	0.74	0.74	0.79	0.0	0.74	0.60
Hereditary	0.38	0.38	0.4	0.92	0.38	0.49
Smoking	0.17	0.17	0.09	0.5	0.17	0.22
Systolic BP	1.0	1.0	1.0	0.08	1.0	0.82
Diastolic BP	0.88	0.88	0.78	0.33	0.88	0.75
Socio-economic level	0.17	0.17	0.11	0.42	0.17	0.21