Problem Scenario

Machine Learning is showing promising results in various technology domains. Healthcare is one of them. Machine Learning can help doctors diagnose patients accurately.

In this use case, we use machine learning algorithms to predict the progression of diabetes in patients.

Description

The baseline measurements: Age, Sex, BMI, BP, and 6 Serum Measurements (S1, S2,...S6) of 422 patients is available in this paper. Our goal here is to teach the machine to predict the diabetes progression based on these 10 measurements. The live demo is available at our Machine Learning Showcase.

The following screenshot is the preview of this dataset. There are 10 measurements and diabetes progression represented as $Y which is the rightmost field.

...

1. The File Reader Snap reads the dataset which is in CSV format.
2. The CSV Parser Snap converts binary data into documents.
3. The Type Converter Snap automatically derives the types of data, since the types of documents from CSV Parser Snap are text represented by String data type.
   In this case, the data is converted into either BigInteger or BigDecimal representing numeric values.
4. The Cross Validator (Regression) Snap performs 10-fold cross validation using the linear regression algorithm.
   Image Removed

   View file
   name image.webp height 150

   
   
5. Finally, we use JSON Formatter Snap and File Writer Snap to save the result.

...