Spine - 2026-08-03 - Journal Article
Explainable Machine Learning for Perioperative Risk Stratification of Radiographic Adjacent Segment Degeneration After Short-Segment Lumbar Fusion.
Yao R, Wang D, Cui P, Fan Z, Wang Q, Chen X, Lu J, Lu S
Topics
Key Takeaway
A random forest model using five perioperative variables achieved AUROC 0.782 (internal) and 0.749 (external validation) for predicting radiographic adjacent segment degeneration after short-segment lumbar fusion, with preoperative intervertebral space height as the dominant predictor.
Summary Depth
Choose how much analysis to show on this article page.
Summary
This study developed and externally validated a machine-learning framework to predict radiographic adjacent segment degeneration (ASDeg) after short-segment lumbar fusion. Five algorithms were trained on 570 patients using LASSO, RF-RFE, and Boruta feature selection, retaining preoperative ISH, postoperative PI-LL mismatch, frailty, Coflex implantation, and WOMAC-defined lower-extremity dysfunction. The random forest model outperformed logistic regression, XGBoost, LightGBM, and MLP with AUROC 0.782 internally and 0.749 on the independent 150-patient cohort; ASDeg occurred in 212 of 570 internal patients (37.2%).
Key Limitation
The primary endpoint is radiographic ASDeg rather than symptomatic adjacent segment disease or reoperation, so the model's clinical utility depends on an unestablished and likely variable conversion rate from radiographic to symptomatic disease.
Original Abstract
STUDY DESIGN
Retrospective Cohort Study.
OBJECTIVES
To develop and externally validate an explainable machine-learning framework for perioperative risk stratification of radiographic adjacent segment degeneration (ASDeg) after short-segment lumbar fusion.
SUMMARY OF BACKGROUND DATA
Radiographic ASDeg is frequently observed after lumbar fusion and may represent an early structural phenotype preceding symptomatic adjacent segment disease (ASDis) in some patients. However, existing risk assessment approaches are limited by heterogeneous risk factors, insufficient model interpretability, and limited external validation. Machine-learning methods may improve perioperative risk stratification by integrating clinical, radiographic, surgical, and functional variables.
METHODS
Clinical data were retrospectively collected from two hospitals. The internal cohort included 570 patients who underwent posterior short-segment lumbar fusion for lumbar degenerative disease, and an independent cohort of 150 patients from another institution was used for external validation. The internal cohort was randomly divided into training and internal test sets at a 7:3 ratio using stratified sampling according to ASDeg status. Feature selection was performed exclusively in the training set using least absolute shrinkage and selection operator regression (LASSO), random forest-recursive feature elimination (RE-RFE), and Boruta. Five algorithms were developed and compared: logistic regression, random forest (RF), extreme gradient boosting (XGBoost), Light Gradient Boosting Machine(LightGBM), and multilayer perceptron (MLP). Model performance was evaluated using discrimination, calibration, precision-recall (P-R) analysis, and decision-curve analysis(DCA). Shapley Additive Explanations (SHAP) were used for model interpretation.
RESULTS
Radiographic ASDeg occurred in 212 of 570 patients in the internal cohort. Five perioperative variables were retained for model construction: preoperative intervertebral space height (ISH), postoperative pelvic incidence-lumbar lordosis (PI-LL) mismatch, frailty, Coflex implantation, and preoperative Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC)-defined lower-extremity dysfunction. Among the candidate algorithms, the RF model showed the highest discriminative performance, with an AUROC of 0.782 in the internal test set and 0.749 in the external validation cohort. SHAP analysis identified preoperative ISH as the strongest contributor to model output.
CONCLUSIONS
This externally validated RF-based model provides a structured and interpretable framework for postoperative radiographic ASDeg risk stratification after short-segment lumbar fusion. By integrating clinically accessible perioperative variables, the model may support individualized imaging follow-up and provide a preliminary basis for future studies using symptomatic adjacent segment disease or revision surgery as clinically oriented endpoints.