Predicting cognitive impairment in Parkinson’s disease: a machine learning approach based on clinical and neuropsychological data
Machine learning models integrating multimodal clinical and neuropsychological data demonstrate high accuracy in predicting cognitive impairment in Parkinson's disease, with Random Forest emerging as the most reliable approach. This framework provides a practical tool for early risk stratification, potentially enabling timely interventions and individualized management to reduce the burden of cognitive decline in Parkinson's disease.
Authors
- Ya‐Fang Chen (ORCID: https://orcid.org/0000-0003-2995-9189)
- Meili Yang (ORCID: https://orcid.org/0000-0002-9912-2774)
- Jiayin Wang (ORCID: https://orcid.org/0000-0002-3862-6557)
- Chuxin Wang (ORCID: https://orcid.org/0009-0008-0257-184X)
- Yao Xiao (ORCID: https://orcid.org/0009-0005-2580-2290)
- Jinying Zhang (ORCID: https://orcid.org/0000-0002-2634-6275)
- Zeming Guo
- Jinzhong Huang
Institutions
- Fujian Medical University (CN)
- Second Affiliated Hospital of Fujian Medical University (CN)
- Union Hospital (CN)
Publication Details
- Journal
- Frontiers in Neurology
- Published
- 2025-12-19
- DOI
- https://doi.org/10.3389/fneur.2025.1709386
- Primary Topic
- Parkinson's Disease Mechanisms and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Natural Science Foundation of Fujian Province
- Fujian Medical University