768 labeled records across 8 medical predictor variables and one binary outcome class. These entries document physiological measurements from Pima Indian women to identify risk factors for diabetes onset.
Use Cases
- Train a binary classifier to predict the 'Outcome' column using 'Glucose' and 'BMI' as input features
- Analyze the 'Age' and 'Pregnancies' columns to identify demographic patterns in diabetes prevalence
- Utilize the 'DiabetesPedigreeFunction' to assess the influence of genetic history on the 'Outcome'
Strengths
- 768 individual patient records from the Pima Indian population
- 8 numeric features including 'Glucose', 'BloodPressure', 'SkinThickness', and 'Insulin'
- Binary target variable 'Outcome' indicating diabetes diagnosis