The Christelijke Mutualiteit Vlaanderen (CM) is the biggest health insurance fund of Belgium with the biggest IT department.

It plays a triple role:

  1. CM reimburses a part of your health care costs;
  2. CM provides you with a replacement income when an illness or accident makes it impossible for you to work;
  3. CM offers a broad range of additional services and advantages.

Challenge

The current scanner solution processes 5 million handwritten documents per month. Yet the current scanner does not achieve the requirements as it not always recognizes the handwritings correctly. Consequently, employees still invest a huge amount of their time in deciphering and typing the text of the paper documents into their application.

Solution

Leveraging the power of Google’s AI Platform, we could quickly train and evaluate various Tensorflow models. After each iteration, improved versions of the models and APIs were shared with interested stakeholders using Container Registry so they could try it for themselves.

Our people process 5 million handwritten documents per month. Thanks to the add on of AI to this process, our scanner recognizes a lot more!

Peter Van Maele – Head of Architecture ICT CM

The result is an automated process by adding AI to the scanner, which deciphers the handwriting on the documents and pre-fills it in the application. We made the existing processes more efficient with some great results:

  • Faster reimbursement of health care costs
  • Speeding up the intake process of health insurance documents
  • Higher percentage of attests recognized thanks to the AI compontent

Tensr

Tensr is a brand of Vectr Consulting that focuses on engineering AI and ML solutions using Google Cloud Platform. Their expertise lies within big data engineering as we pre design data to make magic possible. Machine learning, to craft intelligent solutions generating business value with data models and cloud analytics to leverage the power of the cloud through analytical insights.