CMS's FPS identifies or prevents $654.8 million in 2015

AI system

System: Fraud Prevention System (FPS)
Model: Not assessed
Release: Not assessed
Application developer: Contractors engaged by CMS (the report lists 'Developing Contractor Costs' and 'Modeling Contractor Costs' without naming firms)
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: Claims data run through FPS edits and models that generate leads for Zone Program Integrity Contractors. Administrative levers listed in Table 1 (pre-payment edits, payment suspensions, revocation of billing privileges, overpayment referrals, law-enforcement referrals).
Human oversight: Not assessed
Relation to AI: The report counts savings from actions taken due to the FPS and from investigations the FPS expedited, augmented or corroborated. So the system's own contribution cannot be separated from investigators' work. The technique is not described. CMS deployed the system and paid unnamed developing and modeling contractors, so developer and deployer are not the same body.
AI contribution: Not assessed

Outcome identifiers: Not assessed
Benefit: $654.8 million in inappropriate Medicare payments identified or prevented in 2015
Category: Reduced Risk
Status: Not assessed
Beneficiary groups: Organizations. Society.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: $654.8 million in inappropriate Medicare payments identified or prevented in 2015
Comparison: the FPS's identified savings in the previous year, 2014
Results: Reference: identified savings from the previous year ($454.0 million in Table 1). Result: $654.8 million.
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Kind of value: inappropriate Medicare payments identified or prevented in calendar year 2015
Amount: $654.8 million
Currency and prices: Not assessed
Period and unit: Not assessed
Realization: Not assessed
Recipients and payers: Medicare program (CMS)
Gross or net: Not assessed
Included costs: Not assessed
Comparison: Not assessed
Method: Not assessed
Return and payback: Not assessed

Participants: Developer: Contractors engaged by CMS (the report lists 'Developing Contractor Costs' and 'Modeling Contractor Costs' without naming firms). Operator: Centers for Medicare and Medicaid Services (CMS).
Jurisdictions: Operator: United States.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: Statutory basis and funding (the Small Business Jobs Act of 2010 defines the implementation years). Contractor capacity to investigate leads (investigation costs of $28.9 million in 2015). A savings methodology certified by HHS-OIG.
Replication attempts: 3 follow-up entries. Benefit recurred: 3.
Later findings: Not assessed
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: Organizations. Society.
Depth: Not assessed
Reasons: Organizations: The report gives aggregate identified savings for CMS with no single attributable case. Society: Savings to the Medicare program are stated only as yearly aggregates mixing actual denials with projected avoidance.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: The deployer's account

Kind: Not assessed
Related entries: Not assessed
Field: Health insurance fraud and improper payments. Medicare program integrity.
Purpose: Identify or prevent inappropriate Medicare payments by generating leads that program-integrity contractors investigate and act on.
Dates: Date basis unassessed: 2015 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: dbb137d510c0…