Implementing a New Technology: FPS Successes, Challenges, and Best Practices Centers for Medicare & Medicaid Services Raymond Wedgeworth Director, Data Analytics and Control Group Center for Program Integrity
The FPS Technology The FPS is the state-of-art predictive analytic technology required under the SBJA of 2010. Since June 30 th, 2011, the FPS has run predictive algorithms and other analytics nationwide. Information is presented to end-users on a daily basis on a more real-time basis than ever before. For the first time in history of the program, CMS is systematically applying advanced analytics against Medicare FFS pre-paid claims on a streaming, nationwide basis for PI purposes. 2
First Year of the Fraud Prevention System Built the FPS foundation and infrastructure Established governance structure to prioritize models and enhancements Provided access and training Created an Analytics Lab and built data analysis expertise through internal and external partners Established collaboration and partnership as a standard business practice Solicited and incorporated user feedback Leveraged the Command Center for FPS modeling and investigations activities
Measuring Outcome 4
SBJA Reporting Requirements The SBJA requires the Secretary of HHS to submit reports for each of the first three years of FPS implementation. The SBJA also requires the OIG to certify certain components of the report. We recently completed our third Report to Congress and received OIG certification. 5
FPS Report to Congress: Key Savings CMS calculated savings based on the key administrative actions that it can take: Revocations the estimated amount of payments that CMS avoided making by revoking providers. Payment suspensions the amount being held in suspense due to payment suspensions. Overpayments the amount that CMS identified and referred as overpayments. Auto-denial edits the estimated paid amount denied due to edits. Prepayment review the estimated paid amount denied due to prepayment reviews. Law enforcement referrals the amount identified and sent to law enforcement for potentially fraudulent providers. 6
Millions FPS Report to Congress: Key Savings $300 $250 $200 $820 Million Total Savings Over 3 Years Certified by the OIG $150 $100 $50 $115.4 M Savings due to investigations Expedited, Augmented, or Corroborated by the FPS Savings due to FPS $- First Year 7
Millions FPS Report to Congress: Results $500 $450 $400 $350 $300 $250 $200 $250.1 M $820 Million Total Savings Over 3 Years Certified by the OIG Savings due to investigations Expedited, Augmented, or Corroborated by the FPS $150 $100 $50 $115.4 M Savings due to FPS $- First Year Second Year 8
Millions FPS Report to Congress: Results $500 $450 $400 $350 $300 $250 $200 $150 $100 $50 $- $115.4 M First Year $250.1 M Second Year $454.0 M Third Year $820 Million Total Savings Over 3 Years Certified by the OIG Savings due to investigations Expedited, Augmented, or Corroborated by the FPS Savings due to FPS Reporting Year 9
Overview of the Process for Fraud Prevention Model Prioritization and Development Fraud Prevention System Lead Medicare Savings Action Investigation 10
The Old Way Lead Investigation Action Savings Contractor Staff Enrollment Specialists Policy Experts Doctors Nurses Data Analysts Agents federal contract leads State Experts 11
The New Way FPS Lead Investigation Action Savings Fraud Prevention System Contractor Staff Doctors Nurses Enrollment Specialists Command Center Agents Policy Experts Data Analysts federal contract leads State Experts 12
New Analytics Approach Rule Anomaly Predictive Model Social Network FPS National Health Care Claims (Credit Card Charges). And Other Information Providers (Cardholders) Book of Business 13
Future Enhancements and Expansion of FPS Compliance Unintentional (new rule, moved locations) Non Compliance Limited (errors, specific issues) Significant (pattern of abuse, multiple issues) Intentional (potential fraud) Claims that do not meet Medicare policy Denying Claims through FPS Expanding Claims Denials Providers Identified by the FPS Providers with the Lower Risk Implementing Prepayment Review for RACs Piloting Accelerated Intervention Approach with MACs Providers with the Highest Risk Automatically added to ZPIC Workload Action Taken on 938 providers in FY 2013 14
Implementing Predictive Technology (Best Practices) 15
Implementing Predictive Technology Develop a robust process for incorporating field intelligence, policy knowledge, and clinical expertise (or other expertise relevant to the industry) into the development of predictive or other sophisticated algorithms to ensure that the results of the technology are actionable. Develop a method for tracking, measuring, and evaluating the actions taken based on the information produced by the technology. The technology is a tool to provide more accurate leads more quickly; in order to achieve savings the information must be then used appropriately to take action. 16
Implementing Predictive Technology Incorporate cost savings into the return on investment methodology to ensure that the expenditures that are prevented are part of the savings. Because there is not an audit trail for prevented payments, as there is for recoveries, engage actuarial expertise in the methodology development. Develop an analytic environment for data exploration that includes historic information necessary for predictive modeling and an operational environment that quickly displays results and visualization (graphics, maps) that assists the end user in taking action. 17
Implementing Predictive Technology Develop in-house analytic and business knowledge in order to implement predictive analytics that meet the needs of endusers. Develop and implement a governance process to prioritize program integrity vulnerabilities. 18
Questions? 19