Heat Stroke Patient Data with SOFA 2.0 Scores for Mortality Risk, 2013-2023

A multicenter retrospective cohort study of 292 patients with a first diagnosis of heat stroke admitted to two tertiary hospitals in China between 2013 and 2023. The dataset, authored by Haoming Luo and shared on figshare, includes calculated severity scores and in-hospital mortality outcomes. It was used to assess the predictive performance of the recalibrated SOFA 2.0 score.

Use Cases

• Benchmarking severity scores like SOFA 2.0, original SOFA, MEWS, NEWS, and HSSS for mortality prediction based on early clinical data.
• Training competing risk models for in-hospital mortality using cumulative incidence functions and Fine–Gray models.
• Identifying clinical subphenotypes of heat stroke patients via unsupervised clustering on early clinical and laboratory features.

Strengths

• Includes data for 292 patients with a mean age of 29.8 years and 24 in-hospital deaths (8.2% mortality).
• Compares five established clinical severity scores using data from the first 24 hours of admission.
• Covers a 10-year time range (2013-2023) from two tertiary hospitals, providing longitudinal clinical context.

Limitations

• Row count and column-level documentation are unknown, limiting suitability assessment and requiring field inference after download.
• The dataset is small (130.2 KB), indicating limited scope and sample size for robust model training.
• Subtype-specific findings are noted as requiring cautious interpretation, and external validation is recommended.

Provenance

Source

Haoming Luo via figshare.

Collection Method

Multicenter retrospective cohort study.

Time Range

2013 to 2023

Freshness

Last updated 2026-04 13 05:47:37; freshness should be verified.

Geography

Two tertiary hospitals in China.