Synthea-MIMIC: Synthetic Multi-Table Clinical EHRs

Synthetic electronic health records designed for clinical prediction tasks. The dataset is multi-table, suggesting a relational structure typical of real-world EHR systems. Its origin and specific scale are not detailed in the provided metadata.

Use Cases

• Train clinical risk prediction models based on synthetic patient records.
• Benchmark temporal forecasting algorithms based on multi-table EHR structure.
• Develop and test data anonymization techniques on realistic synthetic healthcare data.

Strengths

• Data is synthetic, which may facilitate sharing and use without the privacy restrictions of real patient data.
• Multi-table structure likely mirrors the relational complexity of production electronic health record systems.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Collection Method

Synthetic generation, likely based on real data patterns.