← Back to catalog

MIMIC-IV not scored

Large de-identified EHR dataset from 364,627 patients across 546,028 hospital admissions and 94,458 ICU stays at Beth Israel Deaconess Medical Center (BIDMC), Boston. Organised into two modules: hosp (hospital-wide EHR: admissions, diagnoses, procedures, labs, prescriptions, microbiology) and icu (ICU clinical information system: charted events, inputs/outputs, procedures, datetimes). Time period 2008–2022, de-identified to 2100–2200 range. v3.1 (October 2024). Linked datasets include MIMIC-IV-Note (clinical notes), MIMIC-IV-ED (emergency department), and MIMIC-CXR (chest X-rays). PhysioNet Credentialed Health Data License 1.5.0 — requires free PhysioNet credentialing, CITI training completion, and DUA signature. The most widely used open clinical EHR dataset for ICU prediction, clinical NLP, and foundation model development.

Not auto-scored

This entry has no harvestable repository signal (e.g. a dataset, standard, or hosted service), so the deterministic scorer does not assign a ring.

Signals & lineage

Every value records the source it was harvested from.

FieldValueSource
HuggingFace downloads (monthly)not_foundhuggingface
PyPI downloads (monthly)not_foundpypi

Change history

Recorded deviations — when a harvested value changed between runs.

WhenFieldWasNowSource
2026-11-20T21:45:53.810881hf_downloads——huggingface
2026-11-20T21:45:53.732411pypi_downloads——pypi