A diabetes prediction model based on Boruta feature selection and ensemble learning

BMC Bioinformatics

Table 2 Dataset statistics

NO	Attributes	Number of missing values	Average value	Maximum	Minimum	Standard deviation
1	Pregnancy	0	3.845	17	0	3.37
2	BMI	11	32.457	67.1	18.2	6.925
3	Insulin	374	155.548	846	14	118.776
4	Age	0	33.241	81	21	11.76
5	Blood pressure	35	72.405	122	24	12.382
6	Skin thickness	227	29.153	99	7	10.477
7	Glucose	5	121.687	199	44	30.536
8	Diabetes spectrum	0	0.472	2.42	0.078	0.331

ISSN: 1471-2105