Synthetic Healthcare Claims Database for 2016

SyH-DR contains synthetic claim-level data from Medicare, Medicaid, and commercial insurance plans for the 2016 calendar year. The Agency for Healthcare Research and Quality (AHRQ) created it from a nationally representative sample of insured individuals, with person-level elements aggregated or masked.

Use Cases

• Analyze claim-level cost and utilization patterns across Medicare, Medicaid, and commercial insurance plan types.
• Study the marginal distribution of synthetic claim elements to model healthcare spending for insured populations.
• Research healthcare access and service use within a nationally representative sample of insured individuals for 2016.

Strengths

• Data is nationally representative for insured individuals in the 2016 calendar year.
• Synthetic claim elements are designed to resemble the marginal distribution of original data for privacy-preserving research.
• Compiles data from three major insurance sources: Medicare, Medicaid, and commercial plans.

Limitations

• Contains synthetic data at the claim level, which may not capture all real-world correlations or individual-level patterns.
• Person-level data elements are aggregated or masked, limiting detailed demographic or longitudinal patient analysis.
• The dataset is static for 2016 and may not reflect current healthcare trends or policy changes.

Provenance

Source

U.S. Department of Health & Human Services, Agency for Healthcare Research and Quality (AHRQ).

Collection Method

Created from eligibility and claims files for Medicare, Medicaid, and commercial insurance plans, with synthetic data elements generated at the claim level.

Time Range

Calendar year 2016.

Freshness

Last updated in September 2023, but data covers the 2016 calendar year.

Geography

Nationally representative sample of insured individuals in the United States.