Today the HHS DOGE team open sourced the largest Medicaid dataset in department history.
This dataset contains aggregated, provider-level claims data for a specific billing code over time.
For example, using this dataset, it would have been possible to easily detect the large-scale autism diagnosis fraud seen in Minnesota.
Download the data yourself:
Today the HHS DOGE team open sourced the largest Medicaid dataset in department history.
This dataset contains aggregated, provider-level claims data for a specific billing code over time.
For example, using this dataset, it would have been possible to easily detect the…
— DOGE HHS (@DOGE_HHS) February 13, 2026
so far I've found about $90 billion of likely fraudulent payments
just from 0.16% of the providers in the data set released. NY state appears to be the absolute worst https://t.co/0WsvRsx2qx pic.twitter.com/TZQu1XwKot
— Beaver 🦁 (@beaverd) February 13, 2026
Per Grok:
To search the Medicaid Provider Spending dataset:
1. Download it (10.32 GB) from the HHS Open Data platform at http://healthdata.gov (search for “Medicaid Provider Spending”).
2. It’s aggregated tabular data (likely CSV) by provider, procedure code, month (2018-2024).
3. Use Python for analysis: import pandas as pd; df = http://pd.read_csv(‘file.csv’); # Filter e.g., df[df[‘procedure_code’] == ‘code’] or df[df[‘provider_id’] == ‘id’]. For large files, use Dask.
4. To detect anomalies like fraud, group by code/location and plot trends with matplotlib.