Mode
Text Size
Log in / Sign up

XGB model predicts mortality in elderly patients with vertebral compression fractures

XGB model predicts mortality in elderly patients with vertebral compression fractures
Photo by Faustina Okeke / Unsplash
Key Takeaway
Consider this XGB mortality model for risk stratification in elderly vertebral fracture patients, but note it lacks external validation.

This single-center retrospective cohort study developed and validated a predictive model for long-term mortality in 440 patients aged 65 years and older diagnosed with vertebral compression fractures between 2017 and 2020. The study compared five survival analysis models using a training set (n=296) and a validation set (n=144).

The XGB model demonstrated superior predictive performance compared to other models, with a C-index of 0.753 in the validation set. SHAP analysis identified age, sex, previous fracture, history of cancer, and co-morbidity as significant predictors of mortality. Kaplan-Meier survival analysis showed significant stratification of high- and low-risk groups (p < 0.05).

Safety and tolerability were not reported, as no interventions were tested. Key limitations include the single-center retrospective design, lack of external validation, unreported follow-up duration, and no information on mortality rates or absolute risk reductions.

The model may help identify high-risk elderly patients for targeted interventions, but it is not ready for clinical implementation without external validation. This is a predictive modeling study, not an interventional trial, and does not establish causation.

Study Details

Study typeCohort
EvidenceLevel 3
PublishedApr 2026
View Original Abstract ↓
Vertebral compression fractures (VCFs) are prevalent among the elderly, often leading to significant complications and mortality. We aimed to develop and validate a predictive model for long-term mortality in patients with VCFs, utilizing a comprehensive dataset from a single-center retrospective study. A total of 440 patients aged 65 years and older, diagnosed with VCFs between 2017 and 2020, were included. The participants were divided into a training set (n = 296) and a validation set (n = 144). We employed five survival analysis models: Cox Proportional Hazards, LASSO, Random Survival Forests, Gradient Boosting Machine, and Extreme Gradient Boosting (XGB). The XGB model demonstrated superior predictive performance, achieving a C-index of 0.753 with the top five predictive variables, outperforming other models in the validation set. SHAP analysis revealed age, sex, previous fracture, history of cancer, and co-morbidity as significant predictors of mortality. The model’s robustness was confirmed through Kaplan–Meier survival analysis, which showed significant stratification of high- and low-risk groups (p 
Free Newsletter

Clinical research that matters. Delivered to your inbox.

Join thousands of clinicians and researchers. No spam, unsubscribe anytime.