Many firms with self-funded medical insurance administered by outside parties fail to review the administrators' performance effectively. Often the firms do not know the extent of overpayments because they lack the expert knowledge to evaluate the paid claims. We examine the use of a simple expert system in conjunction with optimization methods for identifying claims payment errors. The knowledge base in constructed using expertise from the areas of claims processing, auditing, medical diagnosis, and procedure coding practices. Once potential errors are identified, a mathematical program is used to select claims for audit based on maximizing expected benefits subject to various firm-specific processing limitations. We use an efficient Lagrangian relaxation to solve instances of this pure binary programming problem with as many as 150,000 variables. We report on our experience in the use of this system on behalf of a Fortune 100 firm's claims data base.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Management Science and Operations Research