Electroencephalogram hybrid method for Alzheimer early detection

• Type: Article in International Conference Proceedings Book
• Date: 2018

Authors

Rodrigues, PM (Author) Other; Freitas, D (Author) Other; Teixeira, JP (Author) Other; Bispo, B (Author) Other; Alves, D (Author) Other; Garrett, C (Author) Other

Conference proceedings International

Title: Procedia Computer Science

Pages: 209-214

9th International Conference on Ambient Systems, Networks and Technologies, ANT 2018

8 May 2018 through 11 May 2018

Indexing

Scopus - 2 Citations

Other information

Authenticus ID: P-00Q-9E3

DOI: 10.1016/j.procs.2018.10.030

Abstract (EN): Alzheimer's disease (AD) is a neurocognitive illness that leads to dementia and mainly affects the elderly. As the percentage of old people is strongly increasing worldwide, it is urgent to develop contributions to solve this complex problem. The early diagnosis at AD first stage known as Mild Cognitive Impairment (MCI) needs a better accuracy and there is not a biomarker able to detect AD without invasive tests. In this study, Electroencephalogram (EEG) signals have been used to serve as a way of finding parameters to improve AD diagnosis in first stages. For that, a hybrid method based on a Cepstral analysis of EEG Discrete Wavelet Transform (DWT) multiband decomposition was developed. Several Cepstral Distances (CD) were extracted to verify the lag between cepstra of conventional bands signals. The results showed that this hybrid method is a good tool for describing and distinguishing the AD EEG activity along its different stages because several statistically significant parameters variations were found between controls, MCI, moderate AD and advanced AD (the lowest p-value=0.003<0.05). © 2018 The Authors.

Language: English

Type (Professor's evaluation): Scientific