Development and Validation of Interpretable Machine Learning Models Incorporating Paraspinal Muscle Quality to Predict Cage Subsidence Risk Following Posterior Lumbar Interbody Fusion
Key risk factors for PLIF cage subsidence were identified, and a validated machine learning model was developed. The high-performance LightGBM model, deployed in a user-friendly web application, enables spine surgeons to optimize surgical planning and reduce subsidence risk.
Authors
- Zhonglai Qian (ORCID: https://orcid.org/0000-0002-0737-9696)
- Lei Deng (ORCID: https://orcid.org/0000-0002-2818-0432)
- Xiaolan You (ORCID: https://orcid.org/0000-0002-5982-0316)
- Jun Zou (ORCID: https://orcid.org/0000-0001-9563-2702)
- Fanguo Lin (ORCID: https://orcid.org/0009-0004-5062-4556)
- Huilin Yang (ORCID: https://orcid.org/0000-0001-9679-2759)
- Zhanlong Shen (ORCID: https://orcid.org/0000-0002-6897-5125)
- Xiao Sun (ORCID: https://orcid.org/0000-0001-9750-7032)
- Hao Liu (ORCID: https://orcid.org/0000-0002-1318-5783)
- Haifu Sun
- Wenxiang Tang (ORCID: https://orcid.org/0009-0004-3964-9357)
Institutions
- Soochow University (CN)
- Arcadia (US)
- Zhongda Hospital Southeast University (CN)
- Second Affiliated Hospital of Soochow University (CN)
- First Affiliated Hospital of Soochow University (CN)
- Arcadia University (US)
Publication Details
- Journal
- Spine
- Published
- 2025-05-07
- DOI
- https://doi.org/10.1097/brs.0000000000005388
- Citations
- 3
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 2.02