Data Sheet 1_Predictive performance of the SOFA 2.0 score for in-hospital mortality in pat

A 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 data-driven study, authored by Haoming Luo, compares the predictive performance of the recalibrated SOFA 2.0 score against other severity scores for in-hospital mortality. It includes early clinical and laboratory features used for unsupervised clustering to identify clinical subtypes.

Use Cases

• Benchmarking severity scores like SOFA 2.0, original SOFA, and MEWS for mortality prediction based on early admission data.
• Training or validating models for in-hospital mortality risk in heat stroke patients based on clinical and laboratory features.
• Conducting competing risk analysis for mortality using Fine–Gray models based on the study's outcome structure.
• Identifying clinical subphenotypes of heat stroke via unsupervised clustering based on the described early features.

Strengths

• Dataset includes 292 patient records with a mean age of 29.8 ± 14.9 years.
• Study spans a 10-year time range (2013-2023) from two tertiary hospitals.
• Compares multiple established clinical severity scores (SOFA2, SOFA, MEWS, NEWS, HSSS).
• Primary outcome (in-hospital death) is analyzed with a competing risk approach.

Limitations

• Row count and column-level documentation are unknown, limiting suitability assessment.
• Data may reflect geographic and institutional bias inherent to the two Chinese hospitals.
• The authors note that subtype-specific findings should be interpreted cautiously and external validation is required.

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

China (two tertiary hospitals)