A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment
Data harmonization significantly improved the consistency and performance of feature selection and ML classification, with <i>z</i>-score harmonization yielding the best results. This study also highlights the importance of nested cross-validation (CV) to control overfitting and the potential of a semi-automatic pipeline for early AD detection using MRI, with future applications integrating other neuroimaging data to enhance prediction.
Authors
- José M. Sánchez‐Bornot (ORCID: https://orcid.org/0000-0003-4014-4255)
- Ibrahima Faye (ORCID: https://orcid.org/0000-0001-7777-1119)
- Alwani Liyana Ahmad (ORCID: https://orcid.org/0009-0008-4256-6412)
- Damien Coyle (ORCID: https://orcid.org/0000-0002-4739-1040)
- Roberto C. Sotero (ORCID: https://orcid.org/0000-0001-9640-2722)
- Zamzuri Idris
Institutions
- University of Ulster (GB)
- Universiti Sains Malaysia (MY)
- University of Calgary (CA)
- Universiti Teknologi Petronas (MY)
- Hospital Universiti Sains Malaysia (MY)
- Hotchkiss Brain Institute (CA)
- University of Bath (GB)
Publication Details
- Journal
- PeerJ
- Published
- 2024-12-13
- DOI
- https://doi.org/10.7717/peerj.18490
- Citations
- 5
- Primary Topic
- Dementia and Cognitive Impairment Research
- Type
- article
- Field-Weighted Citation Impact
- 1.93
Funders
- Alzheimer's Association
- Bristol-Myers Squibb
- Eli Lilly and Company
- Pfizer
- Biogen
- University of Southern California
- Meso Scale Diagnostics
- Alzheimer's Disease Neuroimaging Initiative
- BioClinica
- Novartis Pharmaceuticals Corporation
- Northern California Institute for Research and Education
- Eisai
- Universiti Sains Malaysia
- Universiti Teknologi Petronas
- Alberta Innovates
- Servier
- H. Lundbeck A/S
- IXICO
- National Institutes of Health
- Genentech
- Canadian Institutes of Health Research
- Engineering and Physical Sciences Research Council
- DoD Alzheimer's Disease Neuroimaging Initiative