MIMIC-III IHM is a dataset derived from the MIMIC-III critical care database. It is hosted on the Kaggle platform. The specific content and structure require verification after download due to minimal metadata.
Use Cases
- Train a binary classifier to predict in-hospital mortality from clinical variables (inferred from domain, verify after download)
- Benchmark risk stratification models for ICU patients (inferred from domain, verify after download)
- Analyze temporal trends in critical care outcomes (inferred from domain, verify after download)
Strengths
- Published on Kaggle, a major platform for data science resources.
Limitations
- Metadata is minimal; actual content requires verification after download.
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count, file formats, and license are unknown, which may limit suitability assessment.