Explainable Supervised Learning Classification Model Using Diffusion Tensor Imaging Predicts Postoperative Outcomes in Cervical Spondylotic Myelopathy: A Preliminary Study
JOR SPINE · 2026-06 · 9 (2)
DOI: 10.1002/jsp2.70197 ↗Kurz gefasst
Fachartikel in der Zeitschrift JOR SPINE, online erschienen am 10.06.2026. Verfasst von Yifei Peng und 6 weiteren Autor:innen. Beteiligte Einrichtung: Hebei Medical University Shijiazhuang China. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Background
Cervical spondylotic myelopathy (CSM) is common in older adults. Some patients may experience incomplete neurological recovery after surgery, or even deterioration. Accurate prognosis is essential for patients, yet current tools use subjective scores and fail to detect early spinal cord microstructural changes.
Methods
CSM patients undergoing preoperative cervical MRI and diffusion tensor imaging (DTI) scans between 2024 and 2025 at a single center were included in this retrospective study. Data were retrieved from medical records, and the determination of whether patients achieved minimal clinically important difference (MCID) was based on the change in modified Japanese Orthopaedic Association (mJOA) scores. Three supervised learning classification models, namely extreme gradient boosting (XGB), logistic regression (LR), and support vector machine (SVM), were constructed based on DTI and clinical risk factors. The performance of these models was evaluated using the area under the receiver operating characteristic curve (AUC) and precision‐recall curve (AP), and decision curve analysis (DCA). The contribution of each feature to model prediction was visualized by SHapley Additive exPlanations (SHAP).
Results
The training set included 163 patients (mean age: 54.43 ± 10.27 years; 57 males), whereas the testing set included 71 patients (mean age: 54.86 ± 12.25 years; 23 males). The AUCs for XGB, LR, and SVM models in the training set were 0.940, 0.791, and 0.908 respectively ( p < 0.05). The XGB model showed the best performance in the training set (AUC = 0.940, AP = 0.948), and the results in the testing set demonstrated moderate discriminative ability with good precision (AUC = 0.754; 95% CI, 0.643–0.857, AP = 0.851; 95% CI, 0.742–0.937). DCA showed that the clinical utility of the XGB model was relatively high.
Conclusion
An explainable XGB model based on DTI and clinical risk factors provides a foundation for preoperative risk stratification of MCID achievement in postoperative CSM.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Hebei Medical University Shijiazhuang China.
- Department of Radiology and Nuclear Medicine The First Hospital of Hebei Medical University Shijiazhuang China.
ORCID-Profile: Yifei Peng, Ruoyu Wang
Zitieren
APA
Peng, Y., Zhang, Z., Zhang, Z., Shi, K., Wang, R., Liu, Y., & Zhang, L. (2026). Explainable Supervised Learning Classification Model Using Diffusion Tensor Imaging Predicts Postoperative Outcomes in Cervical Spondylotic Myelopathy: A Preliminary Study. JOR SPINE, 9(2). https://doi.org/10.1002/jsp2.70197
Vancouver
Peng Y, Zhang Z, Zhang Z, Shi K, Wang R, Liu Y, et al. Explainable Supervised Learning Classification Model Using Diffusion Tensor Imaging Predicts Postoperative Outcomes in Cervical Spondylotic Myelopathy: A Preliminary Study. JOR SPINE. 2026;9(2). doi:10.1002/jsp2.70197
BibTeX
@article{Peng2026,
author = {Peng, Yifei and Zhang, Zixuan and Zhang, Zhikun and Shi, Kaiyi and Wang, Ruoyu and Liu, Yue and Zhang, Li},
title = {Explainable Supervised Learning Classification Model Using Diffusion Tensor Imaging Predicts Postoperative Outcomes in Cervical Spondylotic Myelopathy: A Preliminary Study},
journal = {JOR SPINE},
year = {2026},
volume = {9},
number = {2},
doi = {10.1002/jsp2.70197}
}
EUVIMED