Benchmark dataset for early prediction of sepsis from hourly ICU clinical measurements, from the PhysioNet/Computing in Cardiology Challenge 2019. Contains data from 40,336 ICU patients across three hospital systems (two publicly available). Each patient record includes 8 vital signs, 26 laboratory values, and 6 demographic fields sampled hourly, with Sepsis-3 onset labels. Freely downloadable (CC-BY 4.0) without a data use agreement. Reference implementations provided in Python, MATLAB, Julia, and R. The canonical open benchmark for sepsis early warning algorithm development and comparison.
This entry has no harvestable repository signal (e.g. a dataset, standard, or hosted service), so the deterministic scorer does not assign a ring.
Every value records the source it was harvested from.
| Field | Value | Source |
|---|---|---|
| HuggingFace downloads (monthly) | not_found | huggingface |
| PyPI downloads (monthly) | rate_limited | pypi |
Recorded deviations — when a harvested value changed between runs.
| When | Field | Was | Now | Source |
|---|---|---|---|---|
| 2026-11-20T21:46:02.508980 | hf_downloads | — | — | huggingface |
| 2026-11-20T21:46:02.457363 | pypi_downloads | — | — | pypi |