Towards improving Alzheimer's intervention: a machine learning approach for biomarker detection through combining MEG and MRI pipelines.
Authors
Affiliations (5)
Affiliations (5)
- Universiti Teknologi PETRONAS, Department of Applied Sciences, Seri Iskandar, 32610, Malaysia.
- Ulster University School of Computing Engineering and Intelligent Systems, Ulster University, Derry, Londonderry, BT48 7JL, United Kingdom of Great Britain and Northern Ireland.
- University of Calgary, Department of Radiology and Hotchkiss Brain Institute, Calgary, Alberta, T2N 1N4, Canada.
- Department of Computer Science, University of Bath, Bath Institute for the Augmented Human, Bath, Bath, BA2 7AY, United Kingdom of Great Britain and Northern Ireland.
- Hospital Pakar Universiti Sains Malaysia, Department of Neurosciences, Kota Bharu, Kelantan, 11800, Malaysia.
Abstract
To identify robust biomarkers for early cognitive decline, classification performance was evaluated for healthy controls (HC) versus mild cognitive impairment (MCI) using MEG-derived spectral features at the sensor and source levels, and by testing whether adding MRI anatomical features improves discrimination in the BioFIND cohort. Data from 324 participants (166 HC and 158 MCI) were analyzed using automated artifact rejection and source reconstruction. Spectral biomarkers, including sensor-space and sourcespace representations, were extracted from the magnetometer and gradiometer signals. Five inverse-solution methods were assessed (including linearly constrained minimum variance [LCMV] and exact low-resolution electromagnetic tomography analysis [eLORETA]) to increase the robustness of source-based biomarker selection. Multiple classifiers, including a support vector machine (SVM) and L1-regularized logistic regression (GLMNET), were compared using nested K-fold cross-validation embedded in Monte Carlo replications to limit overfitting. The best performance was obtained by combining MRI features with source-based MEG features using GLMNET, achieving 76.31 ± 1.47% accuracy and 82.44 ± 1.44% AUC. MEG-only models showed strong discrimination and outperformed MRI-only analyses, particularly those based on the LCMV and eLORETA features. Across settings, the SVM and GLMNET were the most consistently effective classifiers. These findings support MEG/EEG spectral biomarkers, particularly source-based representations, as sensitive markers of early AD-related functional changes. Integrating MEG with MRI can further improve HC-versus-MCI classification. The study also demonstrated that rigorous validation (nested cross-validation with Monte Carlo replication) is essential for reliable biomarker assessment and for comparing preprocessing, inverse-solution, and classifier choices in translational neuroimaging pipelines.