tmux new -s mimic_iv
cp .pgpass ~/.pgpass
sudo apt install postgresql-client -y
make up
./scripts/load_mimiciv_data.sh
# under the path
# mimic_automatic/mimic-iii/buildmimic/postgres
make create-user mimic datadir="/home/ec2-user/workspace/mimic_iii/" DBNAME="mimic" DBPASS="p13240!" DBHOST="127.0.0.1"
make create-user mimic-gz datadir="/home/ec2-user/workspace/mimic_iii/" DBNAME="mimic" DBPASS="p13240!" DBHOST="127.0.0.1"
Control+b d
tmux a -t mimic_iv
pg_dump -U postgres -h localhost -p 5432 -d mimic -F d -j 15 -f mimic_iii.dump
This repository contains code for five databases on PhysioNet:
- MIMIC-III - critical care data for patients admitted to ICUs at the BIDMC between 2001 - 2012
- MIMIC-IV - hospital and critical care data for patients admitted to the ED or ICU between 2008 - 2019
- MIMIC-IV-ED - emergency department data for individuals attending the ED between 2011 - 2019
- MIMIC-IV Waveforms (TBD) - this dataset has yet to be published.
- MIMIC-CXR - chest x-ray imaging and deidentified free-text radiology reports for patients admitted to the ED from 2012 - 2016
The repository contains one top-level folder containing community developed code for each datasets:
- mimic-iii - build scripts for MIMIC-III, derived concepts which are available on the
physionet-data.mimiciii_derived
dataset on BigQuery, and tutorials. - mimic-iv - build scripts for MIMIC-IV, derived concepts which are available on the
physionet-data.mimic_derived
dataset on BigQuery, and tutorials. - mimic-iv-cxr - code for loading and analyzing both dicom (mimic-iv-cxr/dcm) and text (mimic-iv-cxr/txt) data. In order to clearly indicate that MIMIC-CXR can be linked with MIMIC-IV, we have named this folder mimic-iv-cxr, and any references to MIMIC-CXR / MIMIC-IV-CXR are interchangeable.
- mimic-iv-ed - build scripts for MIMIC-IV-ED.
- mimic-iv-waveforms - TBD
Each subfolder has a README with further detail regarding its content.
-
Bloatectomy (paper) - A python based package for removing duplicate text in clinical notes
-
Medication categories - Python script for extracting medications from free-text notes
-
MIMIC Extract (paper) - A python based package for transforming MIMIC-III data into a machine learning friendly format
-
FIDDLE (paper) - A python based package for a FlexIble Data-Driven pipeLinE (FIDDLE), transforming structured EHR data into a machine learning friendly format
If you use code or concepts available in this repository, we would be grateful if you would:
- cite the dataset(s) you use as described in the PhysioNet project page: MIMIC-III, MIMIC-IV, MIMIC-IV-ED , and/or MIMIC-CXR
- include a DOI for the code rather than a direct link to the GitHub repo, i.e. https://doi.org/10.5281/zenodo.821872
- cite the MIMIC code repository paper: The MIMIC Code Repository: enabling reproducibility in critical care research
@article{johnson2018mimic,
title={The MIMIC Code Repository: enabling reproducibility in critical care research},
author={Johnson, Alistair E W and Stone, David J and Celi, Leo A and Pollard, Tom J},
journal={Journal of the American Medical Informatics Association},
volume={25},
number={1},
pages={32--39},
year={2018},
publisher={Oxford University Press}
}
By committing your code to the MIMIC Code Repository you agree to release the code under the MIT License attached to the repository.