Computational analysis of electroencephalographic (EEG) signals have shown promising results in detecting brain disorders, such as Alzheimer’s disease (AD). AD is a progressive neurological illness that causes neuron cells degeneration, resulting in cognitive impairment. While there is no cure for AD, early diagnosis is critical to improving the quality of life of affected individuals. Here, we apply six computational time-series analysis methods (wavelet coherence, fractal dimension, quadratic entropy, wavelet energy, quantile graphs and visibility graphs) to EEG records from 160 AD patients and 24 healthy controls. Results from raw and wavelet-filtered (alpha, beta, theta and delta bands) EEG signals show that some of the time-series analysis methods tested here, such as wavelet coherence and quantile graphs, can robustly discriminate between AD patients from elderly healthy subjects. They represent a promising non-invasive and low-cost approach to the AD detection in elderly patients.

Alzheimer's disease (AD) is a progressive neurological illness that causes neuron cells degeneration, resulting in cognitive impairment, which includes loss of memory and space-time perception. While there is no cure for AD, early diagnosis is critical to improving the management and helping in the selection of new therapies, which leads to a better quality of life for the affected individuals, their relatives and caregivers. EEG is a non-invasive technique that can be employed in the investigation of AD, and computational analysis of EEG signals has revealed promising results in detecting AD. In this sense, the main goal of this article is to apply different computational methods to detect AD in order to compare them in terms of distinguishing AD patients from healthy elderly subjects and in terms of computational cost.

Aplicação de redes complexas na detecção automática da epilepsia Application of complex networks in automatic detection of epilepsy Resumo A epilepsia é uma doença cerebral que afeta a comunicação entre as células neuronais. O eletroencefalograma (EEG) desempenha um papel importante no diagnóstico da doença, uma vez que a mesma possui alta resolução temporal e fornece informações relevantes sobre a dinâmica cerebral. Recentemente, foi proposto um mapeamento de séries temporais em redes complexas, mostrando que a dinâmica de uma série temporal afeta nas topologias das redes geradas. Neste sentido, o principal objetivo deste trabalho é demonstrar que sinais de EEG de pacientes em diferentes condições de saúde geram redes complexas com topologias distintas, tornando possível a diferenciação entre pacientes com e sem epilepsia. As redes geradas por pacientes em diferentes condições de saúde apresentaram topologias distintas, o que atesta a eficiência do mapeamento em estudo na identificação dos pacientes com epilepsia. Palavras-chave: Computação científica. Mapeamento. Reconhecimeto de padrões. Séries temporais. Sinais de EEG.