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.

Background aMCI is the most progressive prodromal stage of dementia. For early screening of dementia, it is very important to discriminate aMCI from age‐related physiologic cognitive decline. In addition, community‐based screening tool requires appropriate, less expensive technology. We developed QEEG biomarker algorithm using mixed machine‐learning methods, and validated it Method Nineteen channels of EEGs were measured from 382 community‐based normal subjects and 182 aMCI who showed standardized delayed verbal memory score under 16 percentiles. Various linear and non‐linear quantitative features were generated from single EEG such as frequency band power, power ratio, peak alpha frequency, cortical source current density, functional connectivity based on imaginary coherence and non‐linear complexity. Independent t‐test and least absolute shrinkage and selection operator (LASSO) were used to select the best combination of features. Probability index score for aMCI was developed by combination with logistic regression and penalized linear regression methods with 73 aMCI and 75 community‐based normal subjects. Probability index score could be ranged from 0 to 100, and higher score was referred to as more severe memory impairment due to underlying pathologic progression. Five fold validation was done to fit the best model for largest area under curve (AUC). Result The probability index score for aMCI was validated with blinded independent EEG dataset from 3 hospitals in Korea. The test set consisted of 307 community‐based normal and 109 aMCI subjects. When index score of 60 was applied at cut‐off value to discriminated aMCI from age‐related normal memory declined, the sensitivity was 93% and specificity was 90%. AUC was 0.93 (95% CI: 0.89–0.96) Conclusion QEEG findings of aMCI were different from those of age‐related normal memory declined. Above aMCI probability index score showed promising result. Individual EEGs are much various, and just single specific EEG feature or single machine‐learning method couldn’t be enough to show the significant discriminating power. Careful selection of EEG features and curation of different machine‐learning and statistical models is recommended. This EEG biomarker should be tested for larger aMCI and normal subject populations, and continuously revised and upgraded.

Depression is the mental disorder that prevalent in modern society, causing many people to suffer or even commit suicide. Psychiatrists and psychologists typically diagnose depression using representative tests such as the Beck’s Depression Inventory (BDI) and the Hamilton Depression Rating Scale (HDRS) in conjunction with patient consultations. Traditional tests, however, are time consuming, can be trained on patients, and entail a lot of clinician subjectivity. In the present study, we trained the machine learning models using sex and age-reflected z-score values of QEEG indicators based on data from Data Center for Korean EEG with 116 potential depression subjects and 80 healthy controls. The classification model distinguished potential depression groups and normal groups with a test accuracy of up to 92.31% and a 10-fold cross validation loss of 0.13. This performance proposes a model with z-score QEEG metrics considering sex and age as an objective and a reliable method for detecting potential depression.