eICU critical care database: Patient clinical parameters and outcomes for ICU risk prediction model development

Despite advances in intensive care, sepsis remains a leading cause of mortality in intensive care unit (ICU) patients, especially middle-aged and elderly individuals. Given the limitations of conventional scoring systems and the interpretability challenges of machine learning models, this study aims to develop and temporally validate a nomogram for predicting 28-day ICU mortality in middle-aged and elderly sepsis patients via the eICU database (2014-2015), providing a clinically practical prediction tool. This retrospective study included 13,717 sepsis patients aged ≥ 45 years. The cohort was temporally divided into training (n = 6,397; 2014) and validation (n = 7,320; 2015) sets. Variable selection was performed via random forest importance ranking and LASSO regression. A nomogram was developed on the basis of multivariable logistic regression analysis. The 28-day ICU mortality rates were 9.08% and 9.49% in the training and validation cohorts, respectively. The final nomogram inco..., , ## Description of the data and file structure

This dataset was extracted from the eICU Collaborative Research Database, a multi-center intensive care unit (ICU) database containing de-identified clinical data from critically ill patients. The eICU database includes detailed information from adult ICU patients across multiple hospitals in the United States, capturing demographic information, vital signs, laboratory measurements, treatment interventions, and outcomes. For this research, relevant clinical data was extracted according to our study objectives. The data collection process followed the eICU database usage guidelines and data protection protocols, utilizing only de-identified data. No on-site experiments were conducted; the data collection relied solely on organizing and filtering information from the existing electronic health record database.

For additional context: The eICU Collaborative Research Database v2.0 contains anonymized clinical data from over 200,000 ICU stays a..., Ethics approval and consent to participate
Owing to the retrospective nature of the study and the established security framework, the requirement for informed consent was waived. No additional institutional review board approval was required for the use of this database, as detailed at https://eicu-crd.mit.edu/about/acknowledgments/.

Consent for publication
Not applicable.