HCTO — Hemorrhage Control and Tourniquet Outcomes

This upload contains the full technical documentation and a free evaluation sample (500 casualties stratified by shock class, with 6,760 vitals rows) — not the full dataset. Full dataset (25,000 casualties, 81 fields + 323,704 vitals rows): https://sentineldata.com.ua/dataset/hcto-hemorrhage-control-tourniquet-outcomes Sample contents (SAMPLE.7z, verified by unpacking and counting): File Rows × Cols Content HCTO_sample_main.parquet 500 × 81 500 casualties drawn from the main table, stratified by ATLS shock class (I: 225, II: 148, III: 86, IV: 41); same 81-field schema as the full dataset HCTO_sample_vitals.parquet 6,760 × 6 Matching 5-minute HR / SBP / RR / SpO2 rows for the 500 casualties (3–49 measurements per casualty, mean 13.5) HCTO_sample_passport_EN.pdf — Sample data passport HCTO_sample_readme.txt — Short readme VALIDATION/ — benchmark_script.py, doctrine_validation.py, HCTO_benchmark_results.parquet and the validation report (PDF) The sample is a true subset of the full dataset, not regenerated: its columns match the 81-field schema exactly, neither table contains null values, and every vitals row belongs to a sample casualty. It is meant for evaluating the schema, join logic and tooling, not for model training or statistical inference; rare subgroups are represented by few records. The sample is released under CC BY-NC 4.0. Files in this record: the full Dataset ... Full description with all tables is on the Wiki page of this project. Full dataset and purchase: https://sentineldata.com.ua/dataset/hcto-hemorrhage-control-tourniquet-outcomes . Zenodo copy: https://doi.org/10.5281/zenodo.23402152