Making Medicaid fraud patterns visible through data journalism and interactive visualization
Healthcare fraud costs American taxpayers an estimated $30-100 billion annually. Most of it goes undetected—not because the data doesn't exist, but because no one is looking at it the right way.
We analyze publicly available Medicaid billing data to uncover statistical anomalies that may indicate fraud. Our goal is to make these patterns accessible to journalists, investigators, and concerned citizens.
This is independent data journalism—not affiliated with any government agency. We present findings transparently, allowing you to explore the data yourself.
Data from CMS Medicare Provider Spending (2018-2023)
We use advanced statistical methods to identify billing anomalies:
Providers with > 200% year-over-year billing increases are automatically flagged. Legitimate practices rarely grow this fast without fraud or billing errors.
We identify providers billing > 3x their state and specialty average. These outliers often indicate upcoding, unbundling, or phantom billing.
We analyze unusual concentrations in specific HCPCS codes, particularly autism therapy services (97151-97158), where fraud has been extensively documented.
Important: Statistical anomalies are not proof of fraud. They indicate patterns worthy of further investigation by authorities. Some legitimate providers may show unusual patterns due to specialization or practice changes.
Source: U.S. Department of Health & Human Services (HHS-Official/medicaid-provider-spending)
Time Range: 2018-2023 (6 years of billing data)
Total Volume: Loading... across ... providers
Update Frequency: Dataset is updated annually by HHS
All data used in this analysis is publicly available. We do not access protected health information (PHI) or patient records. Provider names and billing totals are published by HHS as part of Medicare/Medicaid transparency initiatives.
This project was developed using OpenClaw, an AI agent framework that accelerates data journalism and web development. From data analysis to interactive visualizations, AI helped transform raw Medicaid billing data into actionable insights.