What type of study is this?

This is a Validation Study study.

What question did this study set out to answer?

To identify risk factors for proximal junctional kyphosis after long-segment fusion in adult degenerative scoliosis and develop a machine learning prediction model.

December 11, 2025Global Spine JournalOpen Access

Machine Learning–Based Prediction of Proximal Junctional Kyphosis in Adult Degenerative Scoliosis After Long-Segment Fusion: A Multicenter Training–Validation Study

View Full Paper

Ask AI

Bookmark

Authors

XMXianglong MengCapital Medical University SXShude XuCapital Medical University ZZZhiheng ZhaoBeijing Anzhen Hospital

Discussion

Member takes

Implication

Retrospective study identifies risk factors for proximal junctional kyphosis in adult degenerative scoliosis, suggesting predictive models aid surgical planning.

Key Points

To identify risk factors for proximal junctional kyphosis after long-segment fusion in adult degenerative scoliosis and develop a machine learning prediction model.
Retrospective analysis of 142 adult degenerative scoliosis patients from two centers.
Patients assessed for risk factors using demographic, radiographic, and surgical parameters.
Independent predictors identified using multivariate logistic regression.
Key variables determined via LASSO regression and tested with six machine learning algorithms.
Model interpretability analyzed with Local Interpretable Model-agnostic Explanations.
Proximal junctional kyphosis occurred in 24 patients (16.9%).
Logistic regression identified lower T-score, higher T1–pelvic angle, and female sex as risk factors.
LASSO retained five key predictor features.
The back-propagation neural network with LASSO achieved the best performance (external validation AUC = 0.882).
Predictors T-score, T1PA, and pelvic incidence were confirmed as influential.

Cite This Study

Meng et al. (2025) studied this question.

synapsesocial.com/papers/69401b1e2d562116f28f75f2 https://doi.org/10.1177/21925682251407962

View Full Paper

Ask AI

Bookmark

Implication

Retrospective study identifies risk factors for proximal junctional kyphosis in adult degenerative scoliosis, suggesting predictive models aid surgical planning.

Machine Learning–Based Prediction of Proximal Junctional Kyphosis in Adult Degenerative Scoliosis After Long-Segment Fusion: A Multicenter Training–Validation Study

Discussion

Member takes

Implication

Key Points

Cite This Study

Machine Learning–Based Prediction of Proximal Junctional Kyphosis in Adult Degenerative Scoliosis After Long-Segment Fusion: A Multicenter Training–Validation Study

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider