From: Exploratory study on classification of diabetes mellitus through a combined Random Forest Classifier
Factors | Assignment |
---|---|
Gender (\({\mathrm{x}}_{1}\)) | Male = 1*; Female = 2 |
Age (\({\mathrm{x}}_{2}\)) |  < 40 = 1*;40 ~  = 2;60 ~  = 3; |
Region (\({\mathrm{x}}_{3}\)) | Village = 1*; City = 2 |
Ethnic (\({\mathrm{x}}_{4}\)) | Ethnic Han = 1*; National minority = 2 |
Culture level (\({\mathrm{x}}_{5}\)) | Elementary school and below = 1*; Junior and senior high school = 2; College degree and above = 3 |
Occupation (\({\mathrm{x}}_{6}\)) | Farmer = 1*; Retirees or unemployers = 2; Employers = 3; other = 4 |
Marital status (\({\mathrm{x}}_{7}\)) | Spinsterhood = 1*; Married or cohabiting = 2; Divorced, widowed or separated = 3 |
Smoking (\({\mathrm{x}}_{8}\)) | NO = 0; YES = 1 |
Drinking status (\({\mathrm{x}}_{9}\)) | Never drink = 1*; Drinking every day = 2; Frequently = 3; Occasionally = 4 |
Physical activity (\({\mathrm{x}}_{10}\)) | Insufficient = 1*; Normal = 2; Sufficient = 3 |
Fresh fruit (\({\mathrm{x}}_{11}\)) |  < 100 g/d = 1*;100 ~ 200 g/d = 2; > 200 g/d = 3 |
Vegetable intake level (\({\mathrm{x}}_{12}\)) |  < 400 g/d = 1*;400 ~ 500 g/d = 2; > 500 g/d = 3 |
Meat (\({\mathrm{x}}_{13}\)) |  < 50 g/d = 1*;50 ~ 100 g/d = 2; > 100 g/d = 3 |
Heart rate(\({\mathrm{x}}_{14}\)) | Bradycardia = 1; Normal = 2*; Tachycardia = 3 |
BMI(\({\mathrm{x}}_{15}\)) |  < 18.5 = 1*;18.5 ~  = 2, 24.0 ~  = 3;28.0 ~  = 4 |
Central obesity (\({\mathrm{x}}_{16}\)) | NO = 0*; YES = 1 |
Hypertension (\({\mathrm{x}}_{17}\)) | NO = 0*; YES = 1 |
Hyperlipidemia(\({\mathrm{x}}_{18}\)) | NO = 0*; YES = 1 |
Diabetes mellitus (y) | NO = 0*; YES = 1 |