METHOD OF PERSONALIZING, INDIVIDUALIZING, AND AUTOMATING THE MANAGEMENT OF HEALTHCARE FRAUD-WASTE-ABUSE TO UNIQUE INDIVIDUAL HEALTHCARE PROVIDERS

摘要

A method of preventing healthcare fraud-waste-abuse uses artificial intelligence machines to limit financial losses. Healthcare payment request claims are analyzed by predictive models and their behavioral details are compared to running profiles unique to each healthcare provider submitting the claims. A decision results that the instant healthcare payment request claim is or is not fraudulent-wasteful-abusive. If it is, a second analysis of a group behavioral in which the healthcare provider is clustered using unsupervised learning algorithms and compared to a running profile unique to each group of healthcare providers submitting the claims. An overriding decision results if the instant healthcare payment request claim is or is not fraudulent-wasteful-abusive according to group behavior.

主权项

1. A method of personalizing, individualizing, and automating the management of healthcare fraud-waste-abuse to unique individual healthcare providers, comprising:
collecting and aggregating with a processor and an algorithm executed by the processor that combines incoming streams of electronic data records of healthcare payment request claim data originated by a variety of healthcare providers with a correlated non-claim based utilization data, actual clinical data, and pharmacy claim or transaction data, and that stores such a data correlation and combination as cleaned and enriched data records in a computer memory storage device; initializing a continual and individual tracking of distinct behaviors of the variety of healthcare providers with the processor and an algorithm executed by the processor that creates and adapts a unique and independent smart agent profile assigned to and maintained in the computer memory storage device for each and every one of the variety of healthcare providers; continually comparing with the processor and an algorithm executed by the processor that retrieves a corresponding unique and independent smart agent profile, and that matches such to an instant incoming electronic data record of healthcare payment request claim data, and that computes therefrom any new deviation of behavior; simultaneously classifying said instant incoming electronic data record of healthcare payment request claim data with the processor and an algorithm executed by the processor that applies a fraud-waste-abuse criteria and a predictive model trained by supervised and unsupervised learning technologies; classifying each said new deviation of behavior with the processor and an algorithm that applies a unique individual behavior criteria based on a comparison of an individual past behaviors extracted and recorded in their unique healthcare provider profile and an instant behavior evident in the instant incoming healthcare payment request claim stored in the computer memory storage device; issuing a decision with the processor and an algorithm that estimates an instant healthcare payment request claim as fraudulent-wasteful-abusive based on a combination of the classifying each said new deviation of behavior and any predictions from the simultaneously classifying said instant incoming electronic data record of healthcare payment request claim data; and directing the above to any subsequently received incoming healthcare payment request claims, and repeating the above if an instant payment request claim was estimated as not being non-fraudulent-wasteful-abusive.