Diabetes patients need to scored at the point of sale based on factors like average blood sugar level, cholesterol, blood pressure, whether they take their meds regularly, etc. Depending on the patient’s score, their co-pay may vary as they refill medications.


The team built a classification model to predict the risk of patient medication compliance using the Spark notebook on Z. This identifies which patients are more likely to take their medication in a timely manner.


  • Healthcare

Tools Used

  • Spark Notebook on z/OS

Data Science Techniques

  • Classification


Healthcare company was able to positively affect the health of its patients, while doing so at a lower cost and providing a better member experience.

Need help with a similar case?

Contact us to find out how we can help!