MIMIC-IV-ED Demo

Abstract

MIMIC-IV-ED is a publicly accessible database of over 400,000 emergency department (ED) admissions to the Beth Israel Deaconess Medical Center between 2011 and 2019. Access to MIMIC-IV-ED requires registration on PhysioNet, identity verification, completion of human participant training, and signing of a data use agreement. Here, we have provided an openly available demo of MIMIC-IV-ED containing a subset of 100 patients. Being a derivative dataset, the MIMIC-IV-ED demo is deidentified according to the same standard as MIMIC-IV-ED. The demo is intended to support workshops, educational material, exploration of MIMIC-IV-ED, and other aims enabled by an openly available dataset.

Background

The emergency department (ED) is a high demand environment requiring rapid triaging of patients for further care. The MIMIC-IV-ED database [1] was released to support data analysis in emergency care by providing a large database of admissions to an ED at a tertiary academic medical center in Boston, MA. MIMIC-IV-ED is a module of MIMIC-IV, meaning the information contained within MIMIC-IV-ED is linkable to information in MIMIC-IV [2]. Both MIMIC-IV and MIMIC-IV-ED allow credentialed researchers around the world unprecedented access to real world clinical data, helping to reduce the barriers to conducting important medical research. Although the public availability of the data allows studies to be reproduced and collaboratively improved in ways that would not otherwise be possible, the access restriction imposed limits insight into database content for new investigators. The MIMIC-III Clinical Database Demo, an openly available subset of 100 patients, was immensely useful in the past for demonstration, educational, and research purposes. Here we recapitulate the approach by releasing a small subset of MIMIC-IV-ED openly.

Methods

The creation of the MIMIC-IV Clinical Database Demo [3] involved the selection of 100 subject_id chosen to ensure overlap with MIMIC-CXR v2.0.0. The same set of subject_id are used in the selection of patients for inclusion in the MIMIC-IV-ED demo. As all tables in MIMIC-IV-ED contain subject_id, all tables were filtered using the list of selected subject_id. Protected health information (PHI) as listed in the HIPAA Safe Harbor provision was removed from MIMIC-IV-ED and consequently also removed from the demo dataset described herein. More detail on the deidentification process is described on the MIMIC-IV-ED project page [1].

Data Description

The MIMIC-IV-ED demo is a relational database containing a single patient tracking table, edstays, and five data tables: diagnosis, medrecon, pyxis, triage, and vitalsign. All tables from MIMIC-IV-ED were included in the demo dataset. Detailed descriptions of these tables are provided on the MIMIC-IV-ED project page [1]. Data files are distributed in comma separated value (CSV) format following the RFC 4180 memorandum [4].

Usage Notes

CSV files can be opened natively using any text editor or spreadsheet program. However, as some tables are large it may be preferable to navigate the data via a relational database. For convenience, the database has been loaded into the physionet-demo project on Google BigQuery within the mimiciv_ed dataset. Alternatively, code for loading the files into a variety of database systems is available from the MIMIC Code repository [5]. Similar to the source datasets, the MIMIC-IV-ED demo is linkable to the MIMIC-IV Clinical Database demo [3] via subject_id.

Release Notes

Release notes for the MIMIC-IV-ED demo follow the release notes for the MIMIC-IV-ED database.

Ethics

This project was approved by the Institutional Review Boards of Beth Israel Deaconess Medical Center (Boston, MA) and the Massachusetts Institute of Technology (Cambridge, MA). Requirement for individual patient consent was waived because the project did not impact clinical care and all protected health information was deidentified.

Acknowledgements

This research and development was supported by the National Institutes of Health grant NIH-R01-EB017205. We would like to thank the Beth Israel Deaconess Medical Center for their continued collaboration and support of MIMIC. In particular we thank Carolyn Conti, Alvin Gayles, Ayad Shammout, and Lu Shen for their help with data extraction.

Conflicts of Interest

The authors declare no competing financial interests.

References

1. Johnson, A., Bulgarelli, L., Pollard, T., Celi, L. A., Mark, R., & Horng, S. (2023). MIMIC-IV-ED (version 2.2). PhysioNet. https://doi.org/10.13026/5ntk-km72.
2. Johnson, A., Bulgarelli, L., Pollard, T., Horng, S., Celi, L. A., & Mark, R. (2023). MIMIC-IV (version 2.2). PhysioNet. https://doi.org/10.13026/6mm1-ek67.
3. Johnson, A., Bulgarelli, L., Pollard, T., Horng, S., Celi, L. A., & Mark, R. (2022). MIMIC-IV Clinical Database Demo (latest version). PhysioNet. https://doi.org/10.13026/ng9m-3n32.
4. Shafranovich Y. Common format and MIME type for comma-separated values (CSV) files. https://www.hjp.at/doc/rfc/rfc4180.html
5. Johnson AE, Stone DJ, Celi LA, Pollard TJ. The MIMIC Code Repository: enabling reproducibility in critical care research. Journal of the American Medical Informatics Association. 2018 Jan;25(1):32-9. https://github.com/MIT-LCP/mimic-code