MIMIC-III: Critical Care Patient Data from a Tertiary Hospital

A single-center database from a large tertiary care hospital containing information for patients admitted to critical care units. Data includes vital signs, medications, laboratory measurements, clinical notes, procedure codes, diagnostic codes, and survival data. The dataset is maintained by the MIT Laboratory for Computational Physiology and supports academic and industrial research.

Use Cases

• Predict patient outcomes based on vital signs and laboratory measurements mentioned in the description
• Develop natural language processing models for clinical notes charted by care providers
• Analyze treatment patterns and hospital length of stay using medication and procedure data
• Conduct quality improvement initiatives using diagnostic codes and survival data

Strengths

• Data includes a wide variety of clinical information such as vital signs, medications, lab measurements, and notes
• Dataset is freely available and supported by a formal access process through PhysioNet and AWS

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• Last update date is unknown; freshness unverified

Provenance

Source

MIT Laboratory for Computational Physiology

Collection Method

Comprises information from patients admitted to critical care units at a large tertiary care hospital.

Time Range

null

Freshness

null

Geography

United States (inferred from platform tags)