Predicting Progression from Osteoporotic Vertebral Compression Fracture to Kümmell Disease: A Two-Centre Machine-Learning Study with External Evaluation
In brief
Model scored 0.993 AUC predicting fracture progression in an external cohort
Among 555 patients with osteoporotic vertebral fractures, 175 developed Kummell disease. In a separate cohort of 126 patients, a machine-learning model showed very high discrimination, with an area under the curve of 0.993; bone mineral density, spinal curvature and age were influential predictors. The retrospective findings need prospective validation before the model can guide care.
- Journal
- Spine (Q1)
- Published
- 20 November 2026
- Study design
- Prospective / inception cohort
- Evidence level
- Level 2, Moderate (CEBM 2b)
- Authors
- Yitong Wang, Haifu Sun, Wenxiang Tang, Xingyu You, Xuran Guo, Xiao Sun, et al.
- PMID
- 43063155
- DOI
- 10.1097/BRS.0000000000005938
Why clinicians should know about it
- Picked for Spine Surgery (top studies of the week, 22 November 2026): Predicts osteoporotic fracture progression and potential surgical deterioration
Abstract
STUDY DESIGN: A two-center retrospective cohort study with independent external validation. OBJECTIVE: To identify factors associated with progression from conservatively treated osteoporotic vertebral compression fracture (OVCF) to Kümmell disease (KD) and to evaluate machine-learning models for predicting this progression. SUMMARY OF BACKGROUND DATA: A subset of patients with OVCF treated conservatively subsequently develop KD, which may result in persistent pain, progressive vertebral collapse, and neurological impairment. However, factors associated with this progression remain incompletely understood, and externally validated prediction models are lacking. METHODS: The development and external validation cohorts included 555 and 126 patients, respectively. Clinical characteristics and quantitative DXA, CT, MRI, and paraspinal muscle parameters were analyzed. Independent factors associated with KD were identified using multivariable logistic regression. Twelve machine-learning classifiers were developed and internally evaluated using nested stratified cross-validation and subsequently assessed in the independent external cohort. Shapley additive explanations (SHAP) were used to interpret model predictions. RESULTS: Among 555 patients in the development cohort, 175 developed KD and 380 achieved vertebral union. Older age, diabetes, fracture during the hot season, higher vertebral bone quality score, greater paraspinal muscle fat infiltration, and larger Cobb angle were independently associated with KD, whereas higher bone mineral density (BMD) and osteoporosis treatment were associated with lower odds of KD. Under nested internal validation, CatBoost achieved the highest AUC of 0.983. In the external cohort, LightGBM achieved an AUC of 0.993 and the highest accuracy and F1 score. SHAP analysis identified BMD as the most influential predictor, followed by Cobb angle and age. CONCLUSIONS: Progression from OVCF to KD was associated with skeletal fragility, vertebral deformity, paraspinal muscle quality, age, diabetes, fracture season, and osteoporosis treatment. Machine-learning models demonstrated high discriminative performance in external validation. Prospective validation of a prespecified model is warranted before clinical implementation.
Abstract as published, via PubMed.
For healthcare professionals. The summary is generated by AI from the published abstract, and the evidence level is assigned automatically from the study design on the Oxford CEBM hierarchy. Neither is medical advice. Read the full paper before changing practice.