SYNUR: Synthetic Nursing Observation Extraction Dataset

SYNUR is a synthetic dataset created by Microsoft to support research in structuring nurse dictation transcripts. It is intended to extract clinical observations for flowsheet-style EHR entries, aiming to reduce documentation burden. The dataset was last updated on 2026-03-02.

Use Cases

• Train models for extracting structured observations from nurse dictation transcripts.
• Develop automated systems to convert spoken nurse assessments into flowsheet-style EHR entries.
• Research methods to reduce clinical documentation burden through NLP.

Strengths

• Created by a major research organization (Microsoft).
• Specifically designed for a clear use case: reducing nursing documentation burden.
• Last updated on 2026-03-02.

Limitations

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

Provenance

Source

Microsoft

Collection Method

Synthetic data generation, likely for research purposes.

Time Range

Synthetic data; no real temporal coverage.

Freshness

Last updated 2026-03-02 21:26:58.

Geography

Synthetic data; no real geographic coverage.