Prognostic value of iron-metabolism biomarkers in critically ill patients with atrial fibrillation: a machine learning-based retrospective cohort study.

Journal: International journal of surgery (London, England)
Published Date: Jun 12, 2025

Abstract

Iron homeostasis may significantly impact outcomes in critically ill patients with atrial fibrillation (AF), yet its prognostic value remains unclear. Analyzing 2,145 AF patients from MIMIC-IV database, we found 43% mortality (n = 928) at 1-year follow-up. Elevated ferritin (Q4 HR 1.59, 95%CI 1.30-1.95, p<0.001) and serum iron (Q4 HR 1.33, 95%CI 1.11-1.60, p = 0.002) predicted higher mortality, while higher transferrin (Q4: HR 0.65, 95%CI: 0.53-0.79, p<0.001) and TIBC (Q4: HR 0.64, 95%CI: 0.53-0.79, p<0.001) were protective. The gradient boosting decision trees model achieved excellent prediction (AUC 0.85 training/validation, 0.71 testing), with TIBC as the top predictor. These iron-metabolism indicators provide strong prognostic value for risk stratification in critically ill patients with AF.

Authors

  • Chaoqun Huang
    Department of Cardiovascular Medicine, The First Bethune Hospital of Jilin University, Changchun, Jilin Province, China.
  • Shangzhi Shu
    Department of Cardiovascular Medicine, The First Bethune Hospital of Jilin University, Changchun, Jilin Province, China.
  • Xuejun Hui
    Department of Nephrology, the Second Hospital of Jilin University, Changchun, China.
  • Megumi Narisawa
    Department of Cardiology, Nagoya University Graduate School of Medicine, Nagoya, Japan.
  • Xiongjie Jin
    Department of Cardiology and Hypertension, Jilin Provincial Key Laboratory of Stress and Cardiovascular Disease, Yanbian University Hospital, Yanji, China.
  • Shuyan Li
  • Xian Wu Cheng
    Department of Cardiology, Nagoya University Graduate School of Medicine, Nagoya, Japan.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals