IEEE transactions on bio-medical engineering · 2018
Biomarkers for Alzheimer's Disease Defined by a Novel Brain Functional Network Measure.
СтатьяПоддержка исследования: вне правительства СШАНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Song Zhenxi, Deng Bin, Wang Jiang, Wang Ruofan
Аннотация
OBJECTIVE: This paper aims to explore affordable biomarkers of Alzheimer's disease (AD) based on noninvasive, low cost, and portability electroencephalography (EEG) signals.
METHODS: By combining multiscale analysis and embedding space theory, a novel strategy was developed for constructing brain functional network inferred from generalized composite multiscale entropy vector (GCMSEV). Functional network analysis and seed analysis were used for comparing AD pattern versus control pattern. Machine learning methods were employed for proving the effectiveness of our method.
RESULTS: Patients with AD exhibited hypoconnectivity over the whole scalp, especially for long-range connections. Significant decreased connections between frontal and other regions reveals that the transmission of signals related to frontal hub is indeed damaged due to AD. The predictors consist of interfrontal and left frontal-right occipital connections that led to a good performance for distinguishing AD patients and normal subjects with over 96% classification accuracy and 0.98 parametric area under curve.
CONCLUSION: Above findings demonstrated the superior power of the EEG markers quantified by our GCMSEV network, as the indicator of abnormal functional connectivity in the brain of AD patients.
SIGNIFICANCE: This paper develops a novel EEG-based strategy for functional connectivity quantification and enriches the topographical biomarkers used for neurophysiological assessment.
METHODS: By combining multiscale analysis and embedding space theory, a novel strategy was developed for constructing brain functional network inferred from generalized composite multiscale entropy vector (GCMSEV). Functional network analysis and seed analysis were used for comparing AD pattern versus control pattern. Machine learning methods were employed for proving the effectiveness of our method.
RESULTS: Patients with AD exhibited hypoconnectivity over the whole scalp, especially for long-range connections. Significant decreased connections between frontal and other regions reveals that the transmission of signals related to frontal hub is indeed damaged due to AD. The predictors consist of interfrontal and left frontal-right occipital connections that led to a good performance for distinguishing AD patients and normal subjects with over 96% classification accuracy and 0.98 parametric area under curve.
CONCLUSION: Above findings demonstrated the superior power of the EEG markers quantified by our GCMSEV network, as the indicator of abnormal functional connectivity in the brain of AD patients.
SIGNIFICANCE: This paper develops a novel EEG-based strategy for functional connectivity quantification and enriches the topographical biomarkers used for neurophysiological assessment.