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 cog...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nam Heon Kim, Dong Won Yang, Seong Hye Choi, Seung Wan Kang
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	EEG Alzheimer’s disease (AD) beta-amyloid machine learning diagnosis genetic algorithm Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/434d140441cf4c15a15ea6ef0ba9e065
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:434d140441cf4c15a15ea6ef0ba9e065
record_format	dspace
spelling	oai:doaj.org-article:434d140441cf4c15a15ea6ef0ba9e0652021-11-11T13:54:54ZMachine Learning to Predict Brain Amyloid Pathology in Pre-dementia Alzheimer’s Disease Using QEEG Features and Genetic Algorithm Heuristic1662-518810.3389/fncom.2021.755499https://doaj.org/article/434d140441cf4c15a15ea6ef0ba9e0652021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fncom.2021.755499/fullhttps://doaj.org/toc/1662-5188The 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.Nam Heon KimDong Won YangSeong Hye ChoiSeung Wan KangSeung Wan KangFrontiers Media S.A.articleEEGAlzheimer’s disease (AD)beta-amyloidmachine learningdiagnosisgenetic algorithmNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Computational Neuroscience, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	EEG Alzheimer’s disease (AD) beta-amyloid machine learning diagnosis genetic algorithm Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	EEG Alzheimer’s disease (AD) beta-amyloid machine learning diagnosis genetic algorithm Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Nam Heon Kim Dong Won Yang Seong Hye Choi Seung Wan Kang Seung Wan Kang Machine Learning to Predict Brain Amyloid Pathology in Pre-dementia Alzheimer’s Disease Using QEEG Features and Genetic Algorithm Heuristic
description	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.
format	article
author	Nam Heon Kim Dong Won Yang Seong Hye Choi Seung Wan Kang Seung Wan Kang
author_facet	Nam Heon Kim Dong Won Yang Seong Hye Choi Seung Wan Kang Seung Wan Kang
author_sort	Nam Heon Kim
title	Machine Learning to Predict Brain Amyloid Pathology in Pre-dementia Alzheimer’s Disease Using QEEG Features and Genetic Algorithm Heuristic
title_short	Machine Learning to Predict Brain Amyloid Pathology in Pre-dementia Alzheimer’s Disease Using QEEG Features and Genetic Algorithm Heuristic
title_full	Machine Learning to Predict Brain Amyloid Pathology in Pre-dementia Alzheimer’s Disease Using QEEG Features and Genetic Algorithm Heuristic
title_fullStr	Machine Learning to Predict Brain Amyloid Pathology in Pre-dementia Alzheimer’s Disease Using QEEG Features and Genetic Algorithm Heuristic
title_full_unstemmed	Machine Learning to Predict Brain Amyloid Pathology in Pre-dementia Alzheimer’s Disease Using QEEG Features and Genetic Algorithm Heuristic
title_sort	machine learning to predict brain amyloid pathology in pre-dementia alzheimer’s disease using qeeg features and genetic algorithm heuristic
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/434d140441cf4c15a15ea6ef0ba9e065
work_keys_str_mv	AT namheonkim machinelearningtopredictbrainamyloidpathologyinpredementiaalzheimersdiseaseusingqeegfeaturesandgeneticalgorithmheuristic AT dongwonyang machinelearningtopredictbrainamyloidpathologyinpredementiaalzheimersdiseaseusingqeegfeaturesandgeneticalgorithmheuristic AT seonghyechoi machinelearningtopredictbrainamyloidpathologyinpredementiaalzheimersdiseaseusingqeegfeaturesandgeneticalgorithmheuristic AT seungwankang machinelearningtopredictbrainamyloidpathologyinpredementiaalzheimersdiseaseusingqeegfeaturesandgeneticalgorithmheuristic AT seungwankang machinelearningtopredictbrainamyloidpathologyinpredementiaalzheimersdiseaseusingqeegfeaturesandgeneticalgorithmheuristic
_version_	1718439028677672960

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

Ejemplares similares