ST IT CLOUD case study: Assertive Machine Learning
In this article, we are going to talk about the case study of the healthcare segment, its main challenge being the processing of a large volume of clients, which causes highly complex bottlenecks, with regard to medical auditing in authorizations for exams and procedures. The work of ST IT Cloud, was through Data Lake and Machine Learning, to develop a system that worked in an orchestrated and economic way.
THE ST IT CHALLENGE
As previously mentioned, the processing of information within Unimed – BH was becoming extremely complex, when it came to approving medical exams and authorizing Guides. With that, the superintendent of IT, Ezequiel Ribeiro da Silva, explains that currently more than 180,000 requests for procedures are generated per month. “About 145,000 of these requests are already handled by Unimed-BH systems through fixed rules. However, there are 35,000 monthly requests that are forwarded to medical auditors, whose role is to evaluate these requests on a case-by-case basis”, he says.
With this, three main points were seen as necessary to automate the process, check it out:
- Decrease expenses with medical auditing in requests for exams and procedures
- Make assessments for approval and audit more effective
- Streamline the exam approval process
GET TO KNOW ST IT SOLUTIONS
Elaboration of the Architecture and development of a system that was able to load data and files, structured and semi-structured, transactional and historical in a Data Lake in an Orchestrated and Economical way.
In addition, the development of a Machine Learning model assertive enough to automatically authorize medical exams and procedures, validation, display of information and alerts in Near Real Time was also carried out.
“The current solution is the result of several experiments and designs of different architectures in different pilots. The flexibility of using different services available on AWS, with the allocation billing system, allowed Unimed-BH to experiment with several scenarios before arriving at the most appropriate one”, reveals Silva for AWS.
Currently, the project is having good results, with more agility in the processes with a faster 40% and we intend to improve to 60% as the model matures, further improving the experience and results!
If your company has a data challenge, innovation or migration to the Cloud, contact our experts.
▶ stitcloud.com/contact
Follow us on social networks:
#bigdata #stit #bigdatasolutions #data solutions #data processing #kubernetes #aws #eks
Sources: AWS Case, to check it out in full visit: https://aws.amazon.com/pt/solutions/case-studies/unimedbh/
English 
Portuguese 
Spanish