MIMIC-IV Benchmark Tasks
Standardized ICU benchmarks on MIMIC-IV — mortality, LOS, sepsis, AKI, drug dosing.
Composite score: 89.4
Rubric (1–5 per criterion)
rigor
5/5
coverage
4/5
maintenance
5/5
adoption
5/5
quality
5/5
accessibility
3/5
industry_relevance
4/5
Metadata
Stages
Phase IIIClinical DevelopmentPost-market / RWE
Modalities
cross-modality
Task types
clinical-outcome
License
PhysioNet Credentialed
First release
2020
Last updated
2025-02
Flags
none
Size & scope
- patients: 299712
- tasks: 14
Primary paper
Title
MIMIC-IV, a freely accessible electronic health record dataset
Authors
Johnson AEW, Bulgarelli L, Shen L, et al.
Year
2023
DOI / arXiv
Citations
620
Links
- Official site: https://physionet.org/content/mimiciv/
- GitHub: https://github.com/MIT-LCP/mimic-code
- Leaderboard: N/A
Hosted by (initiatives)
Experts (primary authors / maintainers)
Groups (host labs / companies / consortia)
Related benchmarks
Notes (honest caveats)
Canonical clinical ML benchmark. Credentialed access limits casual use.