Fig 1.
EEG signal pre-processing and feature extraction pipeline.
Schematic representation of the standardized EEG pre-processing workflow applied in this study, including detrending, referencing, artifact removal using ICA and wavelet-ICA, normalization, feature extraction, and harmonization. The pipeline generates spectral, connectivity, and entropy-based features across multiple frequency bands and independent components.
Table 1.
Demographic and clinical characteristics of the EEG datasets.
Fig 2.
Propensity score matching across multicenter EEG datasets.
Age- and sex-matched records from healthy non-carrier subjects (HC) and E280A mutation Alzheimer’s disease carriers without clinically detectable cognitive impairment (ACr) were combined across four cohorts and matched using propensity score matching at 2:1, 5:1, and 10:1 ratios.
Fig 3.
Feature selection and model evaluation workflow.
Diagram illustrating the iterative feature selection process applied to harmonized EEG data, including correlation-based feature reduction, decision tree-based importance ranking, model training, and performance evaluation using confusion matrices.
Fig 4.
Relative power in the Alpha 2 band across cohorts.
Boxplots showing the distribution of relative power values for independent components in the Alpha 2 frequency band across four cohorts, separated by healthy non-carrier subjects (HC) and asymptomatic E280A mutation carriers (ACr).
Fig 5.
Area of common support after propensity score matching.
Distribution of propensity scores for healthy non-carrier subjects (HC) and E280A mutation Alzheimer’s disease carriers without clinically detectable cognitive impairment (ACr), illustrating the region of common support used for matching.
Fig 6.
Distribution of EEG feature effect sizes.
Kernel density plots illustrating the distributions of Cohen’s d for selected EEG features, including spectral power, functional connectivity, synchronization likelihood, entropy, and cross-frequency coupling measures. Positive or negative values indicate the direction of differences between healthy non-carrier subjects (HC) and asymptomatic E280A mutation carriers (ACr). Statistical significance was assessed using the Mann–Whitney U test.
Table 2.
Key EEG features differentiating ACr and HC subjects across sample ratios (Cohen’s d and Bonferroni p-values).
Table 3.
Classification performance metrics across matching ratios.
Fig 7.
Learning curves for different class distribution ratios.
Training and validation accuracy curves for decision tree models trained using 2:1, 5:1, and 10:1 ratios of healthy non-carrier subjects (HC) to asymptomatic E280A mutation carriers (ACr).
Fig 8.
Confusion matrices for classification performance.
Confusion matrices obtained from the test datasets for decision tree models trained using 2:1, 5:1, and 10:1 HC-to-ACr ratios. Performance was evaluated on 20% of the total data.