SHAP-based interpretable machine learning for Parkinson's disease severity prediction: integrated analysis of clinical and environmental features
This proof-of-concept study developed an interpretable framework with methodological safeguards against data leakage, demonstrating promising screening potential with realistic performance expectations. However, the cross-sectional, single-center design limits generalizability, requiring external validation and longitudinal studies before clinical deployment.
Authors
- Yang Qiu (ORCID: https://orcid.org/0000-0002-7600-3684)
- Xiang Li (ORCID: https://orcid.org/0000-0001-9595-8526)
- Han Miao (ORCID: https://orcid.org/0000-0003-1933-4206)
- Jianke Xu
- Xinsheng Han (ORCID: https://orcid.org/0000-0001-7972-2820)
- Yuting Jin (ORCID: https://orcid.org/0000-0003-0192-5833)
- Hongyang Zhang (ORCID: https://orcid.org/0000-0002-5817-7154)
Institutions
- Kaifeng University (CN)
- Kaifeng City Children's Hospital (CN)
- Yellow River Conservancy Technical Institute (CN)
Publication Details
- Journal
- Frontiers in Neurology
- Published
- 2025-09-29
- DOI
- https://doi.org/10.3389/fneur.2025.1678463
- Citations
- 3
- Primary Topic
- Parkinson's Disease Mechanisms and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 4.17