Why the study?
Sex-specific predictors of in-hospital mortality in ICU patients with heart failure were not previously explored using machine learning approaches.
Cohort (n=30,411)
Yes
Answers are grounded in this paper and cite their sources.
Machine learning analysis reveals distinct sex-specific predictors for in-hospital mortality among ICU heart failure patients, with systolic blood pressure being more critical in women and BUN, creatinine, and temperature in men.
This retrospective cohort study analyzed congestive heart failure (HF) patients from MIMIC-IV and eICU-CRD. Statistical tests described patient characteristics, while machine learning models (CART, RF, XGBoost, LightGBM) ranked sex-specific predictors, with SHAP used for interpretation. Among 30,411 patients, 3,840 died (men: 12.7%, mean age 69.50; women: 12.6%, mean age 73.02). Systolic blood pressure (SBP) was more critical for mortality in women, while body temperature, blood urea nitrogen (BUN), and creatinine was more significant in men. This is the first machine learning study to explore sex-specific in-hospital mortality predictors in ICU HF patients, identifying both known and potentially important risk factors.
No takes yet. Share an insight, caveat, or question.
Xinhui Tian (2025) conducted a cohort in Congestive heart failure (n=30,411). Female sex vs. Male sex was evaluated on in-hospital mortality.
Synapse has enriched 10 related papers. Consider them for comparative context: