Background: The study of genetic variant carriers provides an opportunity to identify neurophysiological changes in preclinical stages. Electroencephalography (EEG) is a low-cost and minimally invasive technique which, together with machine learning, provide the possibility to construct systems that classify subjects that might develop Alzheimer's disease (AD).
Objective: The aim of this paper is to evaluate the capacity of the machine learning techniques to classify healthy Non-Carriers (NonCr) from Asymptomatic Carriers (ACr) of PSEN1-E280A variant for autosomal dominant Alzheimer's disease (ADAD), using spectral features from EEG channels and brain-related independent components (ICs) obtained using independent component analysis (ICA).
Methods: EEG was recorded in 27 ACr and 33 NonCr. Statistical significance analysis was applied to spectral information from channels and group ICA (gICA), standardized low-resolution tomography (sLORETA) analysis was applied over the IC as well. Strategies for feature selection and classification like Chi-square, mutual informationm and support vector machines (SVM) were evaluated over the dataset.
Results: A test accuracy up to 83% was obtained by implementing a SVM with spectral features derived from gICA. The main findings are related to theta and beta rhythms, generated in the parietal and occipital regions, like the precuneus and superior parietal lobule.
Conclusion: Promising models for classification of preclinical AD due to PSEN-1-E280A variant can be trained using spectral features, and the importance of the beta band and precuneus region is highlighted in asymptomatic stages, opening up the possibility of its use as a screening methodology.
Keywords: Alzheimer’s disease; PSEN1-E280A; electroencephalography; independent component analysis; machine learning; spectral analysis.