Sepsis-Induced ARDS Patient Data with Glucose-Lymphocyte Ratio Biomarker

2,485 patient records from the MIMIC-IV database form a derivation cohort for a study linking glucose-lymphocyte ratio to mortality. An external validation cohort of 298 patients from a Chinese hospital confirms the findings. Shucun Liu published this retrospective analysis on figshare in March 2026.

Use Cases

• Predicting 28-day mortality risk in sepsis-induced ARDS patients based on glucose-lymphocyte ratio
• Evaluating biomarker performance against established severity scores like APS III and SAPS II
• Conducting subgroup analyses to identify patient cohorts where the biomarker is most effective
• Training machine learning models for early risk stratification in intensive care units

Strengths

• Multicenter study with a primary cohort of 2,485 patients and an external validation cohort of 298 patients
• Analysis demonstrates improved predictive accuracy when adding glucose-lymphocyte ratio to APS III and SAPS II models
• Dataset is openly available under a CC-BY-4.0 license

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• Data may reflect geographic bias inherent to the specific hospital sources

Provenance

Source

MIMIC-IV database and Affiliated Hospital of Xuzhou Medical University

Collection Method

Multicenter retrospective cohort analysis

Freshness

Last updated 2026-03-19 06:34:39; freshness should be verified