PHI Scrubbed Data Metrics
This page provides an overview of the PHI (Protected Health Information) scrubbed data metrics available in the dataset. The metrics are designed to give insights into the contents of the de-identified dataset while protecting patient privacy.
Release Overview
This project will have multiple data releases over time. Each release will include updated and new PHI scrubbed metrics. Below is the list of available releases:
February 2025
The February 2025 release is the first PHI scrubbed release of the dataset. It includes comprehensive demographic metrics and other key data points with all PHI removed. You can find detailed information about this release by following the link below:
May 2025
The May 2025 PHI scrubbed release includes additional data sources such as OMOP image occurrence, Philips ISPM, and Stanford cancer registry with all PHI removed. You can find detailed information about this release by following the link below:
August 2025
The August 2025 PHI scrubbed release includes additional data sources such as OMOP image occurrence, Philips ISPM, Stanford cancer registry, and STAMP Add-On data with all PHI removed. You can find detailed information about this release by following the link below:
November 2025
The November 2025 PHI scrubbed release includes updated data sources such as OMOP 5.4, image occurrence, Philips ISPM, and Stanford cancer registry with all PHI removed. You can find detailed information about this release by following the link below:
February 2026
The February 2026 PHI scrubbed release includes updated data sources such as OMOP 5.4, image occurrence, Stanford cancer registry, whole slide imaging, and genetic variants with all PHI removed. You can find detailed information about this release by following the link below:
May 2026
The May 2026 PHI scrubbed release includes updated data sources such as OMOP 5.4, image occurrence, Stanford cancer registry, whole slide imaging, genetic variants, episode table, and additional metrics with all PHI removed. You can find detailed information about this release by following the link below:
August 2026
The August 2026 release is the seventh release of the dataset. It refreshes existing data sources — OMOP 5.4, image occurrence, Stanford Cancer Registry, whole slide imaging, genetic variants, and the episode table — and adds several new sources:
_external_death_recordswhich includes external death records from the California Department of Public Health (CDPH), Care Everywhere, and Social Security (LADMF)Neural Frame event data with structured treatment and timeline details, including radiation therapy records, chemotherapy courses, event categories, and event dates
Additional genetic variants expanded coverage beyond Solid tumor STAMP, including Heme-STAMP NGS/MRD, POLE, Guardant360, and the Stanford Pharmacogenomics Panel
Future Releases
Future releases will include additional PHI scrubbed metrics and updates to the existing ones.