Problem: Train a model to predict the rate of progression of a person’s diabetes based on 10 measurements (features). The measurements included the person’s age, sex, body mass index (BMI), blood pressure (BP), and six serum measurements.
Context: Machine learning is increasingly being employed to diagnose patients, fuel drug discoveries, and predict health outcomes.
Model type: Linear regression
What we did: We used the dataset from a 2003 Stanford University study that collected measurements from 442 patients and then, one year later, collected data on the progression of each patient’s diabetes. You can learn more about the training data here. We used all this data to train a linear regression model. (More on how we built this demo.)
In the demo below, fill in the measurement fields with data of your choosing and then click “Predict.” The model will give a diabetes progression prediction based on your inputs.
The prediction will be shown here.