Diagnostic classification of mild cognitive impairment in Parkinson's disease using subject-level stratified machine-learning analysis
This study developed and validated robust machine learning models for PD-MCI classification using standard clinical assessments alone. Through subject-level or site-level stratified cross-validation combined with Bayesian optimization, we achieved rigorous model evaluation while minimizing overfitting risk. These findings demonstrate the potential for implementing data-driven, interpretable diagnostic tools to enhance early cognitive impairment screening in routine PD care.
Authors
- Haoquan Hu (ORCID: https://orcid.org/0000-0002-5288-2186)
- Jing Wang (ORCID: https://orcid.org/0000-0001-7199-4784)
- Li Zhang (ORCID: https://orcid.org/0000-0003-1092-7531)
- Xie Xiao
- Pengwei Wang (ORCID: https://orcid.org/0000-0002-5667-3488)
- Han Hong-fang
- Yanfang Chen (ORCID: https://orcid.org/0000-0002-6182-5036)
- Lihan Wang (ORCID: https://orcid.org/0000-0002-9130-0505)
Institutions
- Xinyang Normal University (CN)
- Nanjing Xiaozhuang University (CN)
- Shandong Eye Hospital (CN)
- Shanghai Institute of Technology (CN)
Publication Details
- Journal
- Frontiers in Aging Neuroscience
- Published
- 2025-10-22
- DOI
- https://doi.org/10.3389/fnagi.2025.1687925
- Primary Topic
- Parkinson's Disease Mechanisms and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Bristol-Myers Squibb
- Eli Lilly and Company
- Pfizer
- Sanofi
- Biogen
- Teva Pharmaceutical Industries
- Celgene
- Jazz Pharmaceuticals
- Neurocrine Biosciences
- Verily Life Sciences
- Voyager Therapeutics
- National Natural Science Foundation of China
- Servier
- Xinyang Normal University
- H. Lundbeck A/S
- Sun Pharma
- Genentech
- Allergan
- Avid Radiopharmaceuticals
- Nanhu Scholars Program for Young Scholars of Xinyang Normal University