EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A severity classification model of cervical spondylotic radiculopathy symptoms based on MRI radiomics: A retrospective study

Xi Wang iD, Qiaoli Tao, Huanwen Liu, Huangbo Lin, Honglai Zhang

PLOS One · 2025

DOI: 10.1371/journal.pone.0327756 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Xi Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Guangzhou University of Chinese Medicine, School of Medical Information Engineering, Guangzhou, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Radiculopathy, Spondylosis, Cervical Vertebrae. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop a severity classification model for symptoms of cervical spondylotic radiculopathy (CSR) based on magnetic resonance imaging (MRI) radiomics and to evaluate the predictive value of MRI radiomics features in the classification of symptoms severity, providing an objective basis for personalized therapeutic interventions.

Methods

This retrospective study included 99 patients diagnosed with CSR, admitted between August 2022 and April 2023. Symptom severity was assessed using the neck disability index (NDI) scale, which facilitated the categorization of participants into mild and severe symptoms groups. A comprehensive set of 3,404 quantitative radiomics features was extracted from four predefined regions of interest (ROIs) using the 3D Slicer software. The least absolute shrinkage and selection operator (LASSO) regression analysis was used to identify the optimal subsets of radiomics features, which were subsequently used to develop a support vector machine (SVM) classification model. Model performance was evaluated using receiver operating characteristic (ROC) curve analysis with area under the curve (AUC) calculations, complemented by accuracy, precision, sensitivity and F1 score evaluations.

Results

Analysis of cervical T2-weighted MRI resulted in the extraction of 3,404 radiomics features from four ROIs. Using the LASSO regression for feature selection, 96 radiomics features were retained for model construction. The most discriminatory characteristics were in the intervertebral discs at levels C4/5, C5/6, and C6/7 in the mid-sagittal plane. The model demonstrated an AUC of 0.91. The accuracy of the model is 0.917, the precision is 0.979, the sensitivity is 0.833, and the F1 score is 0.890.

Conclusion

The severity classification model of CSR symptoms based on MRI radiomics demonstrates robust predictive performance in assessing the severity of CSR symptoms, serving as an effective decision-support tool for guiding personalized therapeutic strategies in clinical practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingRadiculopathySpondylosisCervical VertebraeHumansFemaleRetrospective StudiesMaleMiddle AgedAdultSeverity of Illness IndexROC CurveSupport Vector MachineAgedRadiomics

Autor:innen und Institutionen

  • Guangzhou University of Chinese Medicine, School of Medical Information Engineering, Guangzhou, China.
  • Guangzhou University of Chinese Medicine, Intelligent Chinese Medicine Research Institute, Guangzhou, China.

ORCID-Profile: Xi Wang

Zitieren

APA

Wang, X., Tao, Q., Liu, H., Lin, H., & Zhang, H. (2025). A severity classification model of cervical spondylotic radiculopathy symptoms based on MRI radiomics: A retrospective study. PLOS One. https://doi.org/10.1371/journal.pone.0327756

Vancouver

Wang X, Tao Q, Liu H, Lin H, Zhang H. A severity classification model of cervical spondylotic radiculopathy symptoms based on MRI radiomics: A retrospective study. PLOS One. 2025. doi:10.1371/journal.pone.0327756

BibTeX
@article{Wang2025,
  author = {Wang, Xi and Tao, Qiaoli and Liu, Huanwen and Lin, Huangbo and Zhang, Honglai},
  title = {A severity classification model of cervical spondylotic radiculopathy symptoms based on MRI radiomics: A retrospective study},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0327756}
}
Kostenlos starten →