What is it about?
Fraud and waste costs medical insurance providers (including public health programs) billions annually. Big data makes human checking of claims difficult; machine learning and data mining allow unusual claims to be flagged prior to being followed up by experts. This paper explores requirements for real-world use of these processes.
Featured Image
Photo by Alina Grubnyak on Unsplash
Why is it important?
Improving understanding of how output of machine learning and data mining will be used by experts will result in more suitable algorithms being developed.
Perspectives
This paper summarized many of the lessons about this topic which I learned over the course of my research; while other papers of mine have explained the methods used, this explores the approach, and I hope it proves useful to other researchers in the field.
James Kemp
Read the Original
This page is a summary of: Developing an anomaly detection framework for Medicare claims, January 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3579375.3579410.
You can read the full text:
Contributors
The following have contributed to this page
