An explainable machine learning model predicts 30-day readmission after vertebral augmentation.

Journal: iScience
Published Date: Nov 19, 2025

Abstract

Osteoporotic vertebral compression fracture (OVCF) patients face high 30-day readmission risks after vertebral augmentation procedures (VAPs). Using electronic health records (EHRs) of 3,947 OVCF patients who underwent VAPs (2019-2024), we developed an interpretable machine learning model to identify readmission predictors. Eight algorithms were evaluated via 10-fold cross-validation, and XGBoost showed the best performance (area under the curve [AUC], sensitivity, specificity, F1 score, and decision curve analysis). SHapley Additive exPlanations (SHAPs) analysis revealed key predictors including frailty, fall history, prolonged hospitalization, comorbidities (pulmonary/kidney disease), advanced age, and hypoalbuminemia. A clinical web application was created for real-time risk stratification, visualizing individualized risk contributions via SHAP to enable proactive interventions and targeted prevention, thereby improving outcomes and reducing healthcare burden.

Authors

  • Chen Liu
    Department of Radiology, Southwest Hospital, Third Military Medical University (Army Military Medical University), Chongqing, China.
  • Qingyang Fu
    Department of Orthopedics, Qilu Hospital, Shandong University, Jinan, Shandong 250000, China.
  • Wang Qifei
    The School of Physics and Electronics, Shandong Normal University, Jinan 250358, China.
  • Weixiao Sun
    Operating Room, Qilu Hospital of Shandong University, Jinan, China.
  • Shimin Tang
    The School of Physics and Electronics, Shandong Normal University, Jinan 250358, China.
  • Zhe Wang
    Department of Pathology, The Eighth Affiliated Hospital, Sun Yat-sen University, Shenzhen 518033, China.
  • Lianying Ma
    The School of Physics and Electronics, Shandong Normal University, Jinan 250358, China.
  • Yunze Feng
    Department of Orthopedics, Qilu Hospital, Shandong University, Jinan, Shandong 250000, China.
  • Xu Zhai
    Wangjing Hospital of China Academy of Traditional Chinese Medicine, Beijing, China.
  • Chunlin Li
    School of Biomedical Engineering, Capital Medical University, Beijing, China. [email protected].
  • Wanlong Xu
    Department of Orthopedics, Qilu Hospital, Shandong University, Jinan, Shandong 250000, China.
  • Wencan Zhang
    Department of Orthopedics, Qilu Hospital of Shandong University, Jinan, Shandong 250012, China.
  • Le Li
    Department of Rehabilitation Medicine, First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, 510080, China.
  • Haipeng Si
    Department of Orthopedics, Qilu Hospital of Shandong University, Jinan, Shandong 250012, China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals