Cognitive deterioration is an important symptom of various neurological disorders. It is characterized by an impairment in memory and/or other cognitive functions compared to previous performance, leading to difficulties in daily activities and placing a burden on both families and communities. Electroencephalography (EEG), a non-invasive method, is used to monitor electrical activity in the brain. The power spectrum of EEG signals includes periodic and aperiodic components. While many studies had previously emphasized the periodic component, recent researches have concentrated on aperiodic information. In this study, we examined the value of both the periodic and aperiodic components for detecting cognitive deterioration in neurological diseases. To explore the value of these markers, EEG data from two different diseases – Alzheimer{\textquoteright}s disease (AD) and multiple sclerosis (MS) – were analyzed. The classification results varied for each disease (87\% accuracy for AD and 66.7\% for MS), indicating an intrinsic difference in classification tasks. Additionally, the aperiodic information showed a better performance in our classification tasks when we calculated it across a wider frequency band. Furthermore, topographic EEG feature maps showed that cognitive deterioration was associated with a steeper 1/f slope in multiple brain regions.
Kien, ND, Akbarian, F, Laton, J, Engelborghs, S, Van Schependom, J, Trung, NL & Nagels, G 2024, Value of periodic and aperiodic EEG components to detect cognitive deterioration. in 32nd European Signal Processing Conference, EUSIPCO 2024 - Proceedings. European Signal Processing Conference, European Signal Processing Conference, EUSIPCO, pp. 1446-1450, 32nd European Signal Processing Conference, EUSIPCO 2024, Lyon, France, 26/08/24. https://doi.org/10.23919/eusipco63174.2024.10715238
Kien, N. D., Akbarian, F., Laton, J., Engelborghs, S., Van Schependom, J., Trung, N. L., & Nagels, G. (2024). Value of periodic and aperiodic EEG components to detect cognitive deterioration. In 32nd European Signal Processing Conference, EUSIPCO 2024 - Proceedings (pp. 1446-1450). (European Signal Processing Conference). European Signal Processing Conference, EUSIPCO. https://doi.org/10.23919/eusipco63174.2024.10715238
@inproceedings{621bbfabec7a4ea3bbeb5c5d38a4db8e,
title = "Value of periodic and aperiodic EEG components to detect cognitive deterioration",
abstract = "Cognitive deterioration is an important symptom of various neurological disorders. It is characterized by an impairment in memory and/or other cognitive functions compared to previous performance, leading to difficulties in daily activities and placing a burden on both families and communities. Electroencephalography (EEG), a non-invasive method, is used to monitor electrical activity in the brain. The power spectrum of EEG signals includes periodic and aperiodic components. While many studies had previously emphasized the periodic component, recent researches have concentrated on aperiodic information. In this study, we examined the value of both the periodic and aperiodic components for detecting cognitive deterioration in neurological diseases. To explore the value of these markers, EEG data from two different diseases – Alzheimer{\textquoteright}s disease (AD) and multiple sclerosis (MS) – were analyzed. The classification results varied for each disease (87\% accuracy for AD and 66.7\% for MS), indicating an intrinsic difference in classification tasks. Additionally, the aperiodic information showed a better performance in our classification tasks when we calculated it across a wider frequency band. Furthermore, topographic EEG feature maps showed that cognitive deterioration was associated with a steeper 1/f slope in multiple brain regions.",
keywords = "Aperiodic, classification, cognitive deterioration, EEG, FOOOF-tool, periodic",
author = "Kien, \{Nguyen Duc\} and Fahimeh Akbarian and Jorne Laton and Sebastiaan Engelborghs and \{Van Schependom\}, Jeroen and Trung, \{Nguyen Linh\} and Guy Nagels",
note = "Funding Information: This work was supported by the National Foundation for Science and Technology Development (NAFOSTED) of Vietnam under Grant 102.04-2021.55. Publisher Copyright: {\textcopyright} 2024 European Signal Processing Conference, EUSIPCO. All rights reserved.; 32nd European Signal Processing Conference, EUSIPCO 2024 ; Conference date: 26-08-2024 Through 30-08-2024",
year = "2024",
doi = "10.23919/eusipco63174.2024.10715238",
language = "English",
series = "European Signal Processing Conference",
publisher = "European Signal Processing Conference, EUSIPCO",
pages = "1446--1450",
booktitle = "32nd European Signal Processing Conference, EUSIPCO 2024 - Proceedings",
}