Use of AI and Machine Learning to accelerate analysis of reimbursement processes to SUS
In the Health area, there are many opportunities and insights that can be recognized by applying artificial intelligence techniques. Our project with Finep and the Ministry of Science, Technology and Innovation, with resources from FNDCT, seeks to innovate the sector of process analysis to make it even more assertive and agile through the use of Machine Learning.
The main challenge is to automate the administrative challenges analysis processes for SUS reimbursement, making it automated, agile, and simplified, maintaining a large base of data intelligence to also have performance in learning and the responses to be provided.
These challenges are received every month and ANS needs to evaluate and approve or not. Today, all of this is done manually by ANS technicians, making the activity slow due to the large number of processes.
HOW WE HELP
First, by creating a platform for legal process analysis with a Machine Learning algorithm, developed with the help of NLT libraries using Python as a programming language, seeking to bring agility and simplify the analysis of legal processes.
With the platform implementation, the goal is to have an initial 60% reduction in manual work of technicians. As the Artificial Intelligence algorithm learns from specific cases, performance will grow quickly and assertively.
This platform will be able to: analyze, interpret, present a preliminary response to technicians and, depending on the level of complexity, respond to these challenges automatically.
Thus, the stored data will be processed in large volumes (big data) hosted on cloud servers allowing scaling, when necessary, resources of: storage, memory, and processor on the server. In addition, redundancies and clustering will be generated for greater performance.