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 |