The MIMIC database

In a nutshell

The MIMIC (Medical Information Mart for Intensive Care) database is one of the most widely used intensive care databases in the world. Publicly accessible upon completion of an ethics training and with a justified research purpose, it contains data from over 50,000 patients admitted to intensive care. It is an excellent learning ground for working with data from clinical data warehouses.

What is MIMIC?

The MIMIC database is a North American database containing data from over 50,000 patients admitted to intensive care at the Beth Israel Deaconess Medical Center (Boston, USA). It is developed and maintained by the MIT Lab for Computational Physiology.

It is one of the most widely used intensive care databases in the scientific literature, thanks to its public access and the richness of its data: demographics, diagnoses, lab results, medication prescriptions, clinical notes, physiological signals, and more.

A learning tool

Despite imperfect data quality (missing data, entry errors, selection bias), MIMIC is an excellent foundation for learning to work with data from clinical data warehouses (CDWs). Many online courses and tutorials use it as their primary dataset.

Available versions

MIMIC comes in several versions:

MIMIC-III (2016): data from 2001 to 2012, approximately 46,000 patients, MIMIC-specific data schema.
MIMIC-IV (2023): most recent version. Data from 2008 to 2019, approximately 65,000 patients, modernized schema.

Both versions can be converted to the OMOP CDM format using open source ETLs: MIT-LCP/mimic-omop for MIMIC-III, OHDSI/MIMIC for MIMIC-IV. A demo database of MIMIC-IV OMOP with 100 patients is freely available (see below).

Which version to choose?

If you’re just starting out, go with MIMIC-IV OMOP Demo: you’ll learn both clinical data manipulation and the OMOP standard, which is increasingly used in research. We offer interactive tutorials to query this database directly in your browser: beginner and intermediate. To work with the full dataset in OMOP format, you’ll need to run the ETL yourself.

Demo databases (open access)

Demo databases are publicly available. They contain anonymized data from 100 patients and require no registration.

You can download them directly:

MIMIC-III Demo — MIMIC data schema
MIMIC-IV OMOP Demo — OMOP CDM v5.4 data schema

These demo databases are ideal for discovering the data structure and practicing SQL queries before accessing the full data.

Accessing the full data

To access the full databases, you need to complete a few steps. The process typically takes a few days to a week.

Create a PhysioNet account

Submit a credentialing request

Fill out the credentialing form on PhysioNet. You will need to provide your information and the contact details of a supervisor or colleague, who will receive a verification email.

Complete the CITI Course

This is a mandatory online training on research ethics and data protection. The steps are detailed on the PhysioNet website. Allow approximately 2 to 3 hours.

Submit your certificate

Once the training is complete, download your CITI certificate and submit it on PhysioNet for validation by the team.

Sign the Data Use Agreement

Final step: sign the Data Use Agreement (DUA) for the MIMIC project. You will then have access to download the data.

Useful links:

Database structure

Native MIMIC schema

The native MIMIC-IV schema is organized around several modules:

hosp: hospital data (admissions, diagnoses, prescriptions, lab results)
icu: intensive care-specific data (physiological measurements, severity scores, inputs/outputs)
ed: emergency department data
note: free-text clinical notes

Key tables include patients, admissions, diagnoses_icd, labevents, prescriptions, chartevents, and more.

Full documentation

The official MIMIC-IV schema documentation is available online. Each table is described in detail with its columns and relationships.

OMOP schema

The OMOP version of MIMIC-IV follows the OMOP CDM v5.4 standard. The data is reorganized into standardized tables: person, visit_occurrence, condition_occurrence, measurement, drug_exposure, etc. You can explore the full schema on our interactive explorer.

The advantage of the OMOP format is that you can use the same SQL queries on any database converted to OMOP, whether it’s MIMIC, a French hospital warehouse, or any other compliant database.

MIMIC is a publicly accessible database of over 50,000 ICU patients, ideal for learning.
Demo databases with 100 patients are immediately accessible, no registration needed.
Access to the full data requires registration, CITI training, and signing a DUA.
The MIMIC-IV OMOP Demo lets you learn both clinical data manipulation and the OMOP standard simultaneously.