Automated Detection of Alzheimer’s Disease using raw EEG time series via. DWT-CNN model

Authors : Mesut ŞEKER, Mehmet Siraç ÖZERDEM

Pages : 673-684

Doi:10.24012/dumf.1197722

View : 18 | Download : 11

Publication Date : 2023-01-03

Article Type : Research Paper

Abstract :Dementia is an age-related neurological disease and gives rise to profound cognitive decline in patients’ life. Alzheimer’s Disease insert ignore into journalissuearticles values(AD); is the progression of dementia and AD patients generally have memory loss and behavioral disorders. It is possible to determine the stage of dementia by developing automated systems via. signals obtained from patients. EEG is a popular brain monitoring system due to its cost effective, non-invasive implementation, and higher time resolution. In current study, we include participants of 24 HC insert ignore into journalissuearticles values(12 eyes open insert ignore into journalissuearticles values(EO);, 12 eyes closed insert ignore into journalissuearticles values(EC););, and 24 AD insert ignore into journalissuearticles values(HC insert ignore into journalissuearticles values(12 eyes open insert ignore into journalissuearticles values(EO);, 12 eyes closed insert ignore into journalissuearticles values(EC););. The aim of current study is to design a practical AD detection tool for AD/HC participants with a model called DWT-CNN. We performed Discrete Wavelet Transform insert ignore into journalissuearticles values(DWT); to extract EEG sub-bands. A Conv2D architecture is applied to raw samples of related EEG sub-bands. According to obtained performance metrics calculated from confusion matrices, all AD and HC time series are correctly classified for alpha band and full band range under both EO and EC. Classification rate of AD vs. HC increases under EO state in all cases even if EC is commonly preferred in other studies. We will add MCI patients with equal size and similar demographics and repeat the experimental steps to develop early alert system in future studies. Adding more participants will also increase generalization ability of method. It is also promising study to combine EEG with different modalities insert ignore into journalissuearticles values(2D TF image conversion, or MRI); in a multimodal approach.
Keywords : Deep Learning, Alzheimer\`s Disease, CNN, EEG, Disease Detection