Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

The MIMIC Code Repository: enabling reproducibility in critical care research.

Alistair Ew Johnson1, David J Stone2, Leo A Celi1,3

  • 1Massachusetts Institute of Technology, Cambridge, MA, USA.

Journal of the American Medical Informatics Association : JAMIA
|October 17, 2017
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

NIH Funding for Artificial Intelligence in Surgical Specialties: Allocation and Alignment with US Disease Burden.

Journal of the American College of Surgeons·2026
Same author

Large Language Models Provide Accurate but Potentially Unsafe Answers to Multimodal Critical Care Medicine Board Review Questions.

Critical care medicine·2026
Same author

Moving beyond the benchmarks: Five foundational principles for meaningful AI evaluation in healthcare.

PLOS digital health·2026
Same author

Can AI Say "I Don't Know"?

The New England journal of medicine·2026
Same author

Evidence, transparency, and scope: concerns about Doctronic.

BMJ (Clinical research ed.)·2026
Same author

Who is leading medical AI? A systematic review and scientometric analysis of chest x-ray research.

medRxiv : the preprint server for health sciences·2026

This study introduces the MIMIC Code Repository, a centralized resource for reproducible critical care research. It provides open-source code to analyze electronic health records, enhancing study comparability and advancing medical knowledge.

Area of Science:

  • Critical Care Medicine
  • Health Informatics
  • Data Science

Background:

  • Reproducibility is crucial for reliable medical research and clinical decision-making.
  • Existing critical care datasets lack standardized, accessible code for analysis.

Purpose of the Study:

  • To introduce the Medical Information Mart for Intensive Care (MIMIC) Code Repository.
  • To provide a centralized, open-source code base for reproducible research on the MIMIC dataset.

Main Methods:

  • Developed a centralized code repository for data loading, extraction, and analysis.
  • Utilized executable documents for tutorials and end-to-end study replication.
  • Implemented an issue tracker for community collaboration and resource improvement.
Keywords:
critical caredata miningelectronic health recordintensive caremimic-iiireproducibility

Related Experiment Videos

Main Results:

  • Extracted key clinical concepts including severity scores, comorbidities, and sepsis definitions.
  • Enabled reproduction of published studies, serving as a template for future research.
  • Facilitated direct interaction between data users and generators for improved data understanding.

Conclusions:

  • The MIMIC Code Repository enables end-to-end reproducible analysis of electronic health records.
  • Open-source code alongside the MIMIC-III database promotes comparable and reproducible research.
  • Community collaboration within the repository enhances the resource for future medical studies.