Risk Factors Predicting Amyloid PET Positivity in Patients with Mild Cognitive Impairment and Apolipoprotein E ɛ3/ɛ3 Genotypes

Predicting amyloid-PET and clinical conversion in apolipoprotein E ε3/ε3 non-demented individuals with multidimensional factors

The apolipoprotein E (APOE) ε4 is a well-established risk factor of amyloid-β (Aβ) in Alzheimer's disease (AD). However, because of the high prevalence of APOE ε3, there may be a large number of people with APOE ε3/ε3 who are non-demented and have Aβ pathology. There are limited studies on assessing Aβ status and clinical conversion in the APOE ε3/ε3 non-demented population. Two hundred and ninety-three non-demented individuals with APOE ε3/ε3 from ADNI database were divided into Aβ-positron emission tomography (Aβ-PET) positivity (+) and Aβ-PET negativity (-) groups using cut-off value of >1.11. Stepwise regression searched for a single or multidimensional clinical variables for predicting Aβ-PET (+), and the receiver operating characteristic curve (ROC) assessed the accuracy of the predictive models. The Cox regression model explored the risk factors associated with clinical conversion to mild cognitive impairment (MCI) or AD. The results showed that the combination of sex, education, ventricle and white matter hyperintensity (WMH) volume can accurately predict Aβ-PET status in cognitively normal (CN), and the combination of everyday cognition study partner total (EcogSPTotal) score, age, plasma p-tau 181 and WMH can accurately predict Aβ-PET status in MCI individuals. EcogSPTotal score were independent predictors of clinical conversion to MCI or AD. The findings may provide a non-invasive and effective tool to improve the efficiency of screening Aβ-PET (+), accelerate and reduce costs of AD trial recruitment in future secondary prevention trials or help to select patients at high risk of disease progression in clinical trials.

PET-validated EEG-machine learning algorithm predicts brain amyloid pathology in pre-dementia Alzheimer's disease

Developing reliable biomarkers is important for screening Alzheimer's disease (AD) and monitoring its progression. Although EEG is non-invasive direct measurement of brain neural activity and has potentials for various neurologic disorders, vulnerability to noise, difficulty in clinical interpretation and quantification of signal information have limited its clinical application. There have been many research about machine learning (ML) adoption with EEG, but the accuracy of detecting AD is not so high or not validated with Aβ PET scan. We developed EEG-ML algorithm to detect brain Aβ pathology among subjective cognitive decline (SCD) or mild cognitive impairment (MCI) population, and validated it with Aβ PET. 19-channel resting-state EEG and Aβ PET were collected from 311 subjects: 196 SCD(36 Aβ +, 160 Aβ -), 115 MCI(54 Aβ +, 61Aβ -). 235 EEG data were used for training ML, and 76 for validation. EEG features were standardized for age and sex. Multiple important features sets were selected by 6 statistics analysis. Then, we trained 8 multiple machine learning for each important features set. Meanwhile, we conducted paired t-test to find statistically different features between amyloid positive and negative group. The best model showed 90.9% sensitivity, 76.7% specificity and 82.9% accuracy in MCI + SCD (33 Aβ +, 43 Aβ -). Limited to SCD, 92.3% sensitivity, 75.0% specificity, 81.1% accuracy (13 Aβ +, 24 Aβ -). 90% sensitivity, 78.9% specificity and 84.6% accuracy for MCI (20 Aβ +, 19 Aβ -). Similar trends of EEG power have been observed from the group comparison between Aβ + and Aβ -, and between MCI and SCD: enhancement of frontal/ frontotemporal theta; attenuation of mid-beta in centroparietal areas. The present findings suggest that accurate classification for beta-amyloid accumulation in the brain based on QEEG alone could be possible, which implies that QEEG is a promising biomarker for beta-amyloid. Since QEEG is more accessible, cost-effective, and safer than amyloid PET, QEEG-based biomarkers may play an important role in the diagnosis and treatment of AD. We expect specific patterns in QEEG could play an important role to predict future progression of cognitive impairment in the preclinical stage of AD. Further feature engineering and validation with larger dataset is recommended.

Novel quantitative electroencephalogram feature image adapted for deep learning: Verification through classification of Alzheimer’s disease dementia

Quantitative electroencephalography (QEEG) analysis is commonly adopted for the investigation of various neurological disorders, revealing electroencephalogram (EEG) features associated with specific dysfunctions. Conventionally, topographies are widely utilized for spatial representation of EEG characteristics at specific frequencies or frequency bands. However, multiple topographies at various frequency bands are required for a complete description of brain activity. In consequence, use of topographies for the training of deep learning algorithms is often challenging. The present study describes the development and application of a novel QEEG feature image that integrates all required spatial and spectral information within a single image, overcoming conventional obstacles. EEG powers recorded at 19 channels defined by the international 10–20 system were pre-processed using the EEG auto-analysis system iSyncBrain^®, removing the artifact components selected through independent component analysis (ICA) and rejecting bad epochs. Hereafter, spectral powers computed through fast Fourier transform (FFT) were standardized into Z-scores through iMediSync, Inc.’s age- and sex-specific normative database. The standardized spectral powers for each channel were subsequently rearranged and concatenated into a rectangular feature matrix, in accordance with their spatial location on the scalp surface. Application of various feature engineering techniques on the established feature matrix yielded multiple types of feature images. Such feature images were utilized in the deep learning classification of Alzheimer’s disease dementia (ADD) and non-Alzheimer’s disease dementia (NADD) data, in order to validate the use of our novel feature images. The resulting classification accuracy was 97.4%. The Classification criteria were further inferred through an explainable artificial intelligence (XAI) algorithm, which complied with the conventionally known EEG characteristics of AD. Such outstanding classification performance bolsters the potential of our novel QEEG feature images in broadening QEEG utility.

Novel quantitative electroencephalogram feature image adapted for deep learning: Verification through classification of Alzheimer's disease dementia

Quantitative electroencephalography (QEEG) analysis is commonly adopted for the investigation of various neurological disorders, revealing electroencephalogram (EEG) features associated with specific dysfunctions. Conventionally, topographies are widely utilized for spatial representation of EEG characteristics at specific frequencies or frequency bands. However, multiple topographies at various frequency bands are required for a complete description of brain activity. In consequence, use of topographies for the training of deep learning algorithms is often challenging. The present study describes the development and application of a novel QEEG feature image that integrates all required spatial and spectral information within a single image, overcoming conventional obstacles. EEG powers recorded at 19 channels defined by the international 10-20 system were pre-processed using the EEG auto-analysis system iSyncBrain^®, removing the artifact components selected through independent component analysis (ICA) and rejecting bad epochs. Hereafter, spectral powers computed through fast Fourier transform (FFT) were standardized into Z-scores through iMediSync, Inc.'s age- and sex-specific normative database. The standardized spectral powers for each channel were subsequently rearranged and concatenated into a rectangular feature matrix, in accordance with their spatial location on the scalp surface. Application of various feature engineering techniques on the established feature matrix yielded multiple types of feature images. Such feature images were utilized in the deep learning classification of Alzheimer's disease dementia (ADD) and non-Alzheimer's disease dementia (NADD) data, in order to validate the use of our novel feature images. The resulting classification accuracy was 97.4%. The Classification criteria were further inferred through an explainable artificial intelligence (XAI) algorithm, which complied with the conventionally known EEG characteristics of AD. Such outstanding classification performance bolsters the potential of our novel QEEG feature images in broadening QEEG utility.

Machine Learning to Predict Brain Amyloid Pathology in Pre-dementia Alzheimer’s Disease Using QEEG Features and Genetic Algorithm Heuristic

The use of positron emission tomography (PET) as the initial or sole biomarker of β-amyloid (Aβ) brain pathology may inhibit Alzheimer’s disease (AD) drug development and clinical use due to cost, access, and tolerability. We developed a qEEG-ML algorithm to predict Aβ pathology among subjective cognitive decline (SCD) and mild cognitive impairment (MCI) patients, and validated it using Aβ PET. We compared QEEG data between patients with MCI and those with SCD with and without PET-confirmed beta-amyloid plaque. We compared resting-state eyes-closed electroencephalograms (EEG) patterns between the amyloid positive and negative groups using relative power measures from 19 channels (Fp1, Fp2, F7, F3, Fz, F4, F8, T3, C3, Cz, C4, T4, T5, P3, Pz, P4, T6, O1, O2), divided into eight frequency bands, delta (1–4 Hz), theta (4–8 Hz), alpha 1 (8–10 Hz), alpha 2 (10–12 Hz), beta 1 (12–15 Hz), beta 2 (15–20 Hz), beta 3 (20–30 Hz), and gamma (30–45 Hz) calculated by FFT and denoised by iSyncBrain^®. The resulting 152 features were analyzed using a genetic algorithm strategy to identify optimal feature combinations and maximize classification accuracy. Guided by gene modeling methods, we treated each channel and frequency band of EEG power as a gene and modeled it with every possible combination within a given dimension. We then collected the models that showed the best performance and identified the genes that appeared most frequently in the superior models. By repeating this process, we converged on a model that approximates the optimum. We found that the average performance increased as this iterative development of the genetic algorithm progressed. We ultimately achieved 85.7% sensitivity, 89.3% specificity, and 88.6% accuracy in SCD amyloid positive/negative classification, and 83.3% sensitivity, 85.7% specificity, and 84.6% accuracy in MCI amyloid positive/negative classification.