Predictive Modeling Analysis of Medicare Claims

As of June 30, 2011, CMS is streaming all Medicare FFS claims through its predictive modeling technology. As each claim streams through the predictive modeling system, the system builds profiles of providers, networks, billing patterns, and beneficiary utilization. These profiles enable CMS to create risk scores to estimate the likelihood of fraud and flag potentially fraudulent claims and billing patterns. Risk scores enable CMS to quickly identify unusual billing activity and flag claims for more thorough review prior to releasing payment. The system automatically prioritizes claims, providers, beneficiaries, and networks that are generating the most alerts and highest risk scores. Risk scores alone do not initiate administrative action and serve only to alert CMS to the necessity of more careful review of claims activity. Currently, CMS is not denying claims solely based on the alerts generated by predictive models. CMS is focused on developing and refining models that identify unusual behavior without disrupting its claims processing for Medicare providers. Working closely with clinical experts across the country and of every provider specialty, CMS is developing and refining algorithms that reflect the complexities of medical treatment and billing. The new technology will ultimately benefit the program’s many honest providers and suppliers by enabling the agency to prioritize the highest-risk cases for investigation and review.