Table 1 Dataset description
From: A diabetes prediction model based on Boruta feature selection and ensemble learning
NO | Property name | Property description | Type of data | Data range | Missing value |
|---|---|---|---|---|---|
1 | Pregnancy | Number of female pregnancies | Integer | 0–17 | No |
2 | BMI | BMI (kg/m2) | Float | 0–67.1 | Yes |
3 | Insulin | 2-h serum insulin | Integer | 0–846 | Yes |
4 | Age | Year | Integer | 21–81 | No |
5 | Blood pressure | Diastolic blood pressure (mmHg) | Integer | 0–122 | Yes |
6 | Skin thickness | Triceps skinfold thickness (mm) | Integer | 0–99 | Yes |
7 | Glucose | 2-h blood glucose (mg/dl) | Integer | 0–199 | Yes |
8 | Diabetes spectrum function | Diabetes spectrum function | Float | 0.078–2.42 | No |
9 | Outcome | Diabetic population marker | Integer | 0.1 | No |