Trauma Hemorrhage & Coagulopathy Cohort
Year: 2026
Type: article
Abstract: This upload contains a free evaluation sample only (100 patients × 3 arms, 216,000 profile rows) — not the full dataset. The complete dataset — 10,000 patients × 3 counterfactual resuscitation arms, 30,000 regimens, 21,600,000 profile rows — is available at: https://sentineldata.com.ua/dataset/trauma-hemorrhage-coagulopathy-cohort Sample contents: sample_patients.parquet 100 rows sample_regimens.parquet 300 rows sample_profiles.parquet 216,000 rows sample_outcomes.parquet 300 rows The sample is a true subset — rows sliced from the release tables, not regenerated — and its equality with the release files is verified programmatically before packaging. Dataset Architecture & Specifications The Trauma Hemorrhage & Coagulopathy Cohort (DS2) is a fully synthetic, mechanistically generated dataset of severe traumatic hemorrhage and trauma-induced coagulopathy (TIC), built for the development and validation of resuscitation-policy, coagulopathy-prediction, tipping-point-detection, and counterfactual-evaluation algorithms. All 88 governing parameters are traced to literature with DOI/PMID verification or calibrated against published cohort aggregates (PROPPR, CRASH-2, Gonzalez 2016) with the anchoring literature documented — zero parameters are unsourced. The dataset contains no real patient data and is not intended for clinical use. Synthetic Patients 10,000 (severe hemorrhage, ATLS ... Full description with all tables is on the Wiki page of this project. Full dataset and purchase: https://sentineldata.com.ua/dataset/trauma-hemorrhage-coagulopathy-cohort . Zenodo copy: https://doi.org/10.5281/zenodo.22903092
Source: Open Science Framework
Author: Maksym Chekerskyi
Language: English
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W7225464138