Prediction of lumbar disc degeneration based on interpretable machine learning models: retrospective cohort study
In this study, an LDD prediction model was developed using paravertebral muscle quantitative data and ML algorithms, with SHAP analysis incorporated to enhance model interpretability. The XGBoost model demonstrated the best predictive performance and holds potential to guide early clinical prevention and treatment.
Authors
- Xinggang Mao (ORCID: https://orcid.org/0000-0001-8505-1904)
- Weihui Qi (ORCID: https://orcid.org/0000-0003-2893-8589)
- Hao Pan (ORCID: https://orcid.org/0000-0001-7136-5822)
- Gao-Yong Jia
- Xiaofeng Li (ORCID: https://orcid.org/0000-0001-7038-5119)
- Dong Wang (ORCID: https://orcid.org/0000-0002-4235-8719)
- Weidong Zhang (ORCID: https://orcid.org/0000-0002-4700-1276)
- Tenghui Li (ORCID: https://orcid.org/0000-0002-8810-962X)
Institutions
- Zhejiang Chinese Medical University (CN)
- Shanghai University of Traditional Chinese Medicine (CN)
- Shanghai Traditional Chinese Medicine Hospital (CN)
- Hangzhou Hospital of Traditional Chinese Medicine (CN)
Publication Details
- Journal
- The Spine Journal
- Published
- 2025-04-09
- DOI
- https://doi.org/10.1016/j.spinee.2025.04.004
- Citations
- 7
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 4.72
Funders
- National Natural Science Foundation of China
- Hangzhou Science and Technology Bureau