HHS Launches AI Initiative to Detect Fraud and Waste in Federal Health Programs
May 21, 2026 – 5:29 pm
The Department of Health and Human Services (HHS) is transitioning from a "pay and chase" approach to a real-time AI screening system across Medicare, Medicaid, CHIP, and the Marketplace.
The US Department of Health and Human Services has unveiled an artificial intelligence initiative aimed at identifying fraud and waste within its federal health programs, building upon a strategy outlined in February. This shift promises to replace the traditional "pay and chase" model with real-time AI analysis of claims before they are processed. According to a joint HHS announcement, the program encompasses Medicare, Medicaid, CHIP, and the Health Insurance Marketplace.
In February, HHS Secretary Robert F. Kennedy Jr., Vice President JD Vance, and CMS Administrator Mehmet Oz emphasized this transition from investigating after the fact to a "detect and deploy" model using AI tools to identify suspicious claims at the time of adjudication.
The initiative is driven by significant financial losses: Medicare’s fee-for-service program alone incurred an estimated $28.83 billion in improper payments during fiscal 2025, as per a CMS fact sheet. Medicare Part C contributed an additional $23.67 billion. A Government Accountability Office report from April revealed that federal-wide improper payments totaled roughly $186 billion for the year, concentrated in five key programs, including Medicare and Medicaid.
This effort is supported by a Request for Information (RFI) opened in late February, seeking industry insights on analytics methodologies, AI tooling, and data-sharing practices. The RFI closed on March 30 and will inform a proposed rule known as "CRUSH," meaning "Comprehensive Regulations to Uncover Suspicious Healthcare."
While pilots are ongoing, the May initiative represents an operational step forward. The HHS Office of Inspector General has tested a machine learning model that assesses providers for billing practices indicative of fraud or abuse, and CMS reported a 59% increase in total Medicare program integrity savings during fiscal 2025, rising from $26.3 billion to $41.9 billion.
A potential challenge lies in balancing effective pre-payment screening with the impact of false positives on providers. Delayed payments can significantly affect legitimate practices, especially smaller ones. Industry groups have already requested clear appeal rights and human review thresholds during the RFI process, but these safeguards remain to be finalized in the rulemaking.
Unclear at this stage are the details surrounding model vendors, data types (de-identified or fully identifiable), and the system’s operational framework.