AUTHOR=Kim Nam Heon , Yang Dong Won , Choi Seong Hye , Kang Seung Wan 

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

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 15 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2021.755499

DOI=10.3389/fncom.2021.755499

ISSN=1662-5188

ABSTRACT=We compared QEEG data between patients with mild cognitive impairment (MCI) and those with subjective cognitive decline (SCD) with and without PET-confirmed beta-amyloid plaque. We compared resting-state eyes-closed 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 modelling 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. We hypothesized that the more frequently a gene appears in good models, the more likely it is to contribute to the utility of that model. Based on a set standard, we extracted only those genes that exceeded the standard to create a higher-dimensional model. 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.