Development and validation of a clinical risk stratification model for lumbar vertebral compression fractures in patients with lumbar disc herniation.

Study design: Retrospective study. Background: Patients with lumbar disc herniation (LDH) are at increased risk for lumbar vertebral compression fractures (LVCFs). Early identification of high-risk individuals is clinically significant but remains challenging due to the lack of targeted risk stratification tools. Methods: This retrospective study analyzed data from 2120 LDH patients treated at the First Affiliated Hospital of Anhui University of Chinese Medicine between July 2020 and July 2025. After exclusions, 544 patients were included and randomly divided into training (70%) and internal validation (30%) cohorts. Least absolute shrinkage and selection operator (LASSO) regression was used to identify risk factors, and a nomogram was constructed based on logistic regression. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA). Results: Seven independent risk factors were identified: age, lower limb sensory impairment, D-dimer, alkaline phosphatase, triglycerides, subcutaneous fasciitis, and lumbar lordosis angle. The model demonstrated good discrimination, with an area under the curve (AUC) of 0.867 (95% CI: 0.8299-0.9036) in the training set and 0.894 (95% CI: 0.8427-0.9415) in the internal validation set. Calibration curves showed good agreement between assessed and observed risks. ROC and DCA analyses confirmed the discriminative performance of this model. Conclusion: We developed and validated a novel risk stratification model that estimates LVCFs risk in LDH patients using readily available clinical and imaging parameters. This tool may facilitate early risk stratification, personalized intervention, and improved fracture prevention in this high-risk population.