Deep Learning Model for Prediction of Dementia Severity based on EEG Signals

This study aimed to determine variations in the electroencephalograms (EEGs) of 15 individuals who were diagnosed with mild cognitive impairment (MCI) following stroke, 5 individuals suffering from vascular dementia (VD) and 15 healthy normal control (NC) individuals who performed a working memory...

Full description

Saved in:
Bibliographic Details
Main Authors: Noor Kamal Al-Qazzaz, Sawal Hamid Bin Mohd Ali, Siti Anom Ahmad
Format: Article
Language:English
Published: Al-Khwarizmi College of Engineering – University of Baghdad 2024-12-01
Series:Al-Khawarizmi Engineering Journal
Online Access:https://alkej.uobaghdad.edu.iq/index.php/alkej/article/view/938
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850058952268578816
author Noor Kamal Al-Qazzaz
Sawal Hamid Bin Mohd Ali
Siti Anom Ahmad
author_facet Noor Kamal Al-Qazzaz
Sawal Hamid Bin Mohd Ali
Siti Anom Ahmad
author_sort Noor Kamal Al-Qazzaz
collection DOAJ
description This study aimed to determine variations in the electroencephalograms (EEGs) of 15 individuals who were diagnosed with mild cognitive impairment (MCI) following stroke, 5 individuals suffering from vascular dementia (VD) and 15 healthy normal control (NC) individuals who performed a working memory task. Conventional filters including notch and bandpass filters were utilised to remove noise from the EEG data. The proposed method comprises computing the estimates of the attention entropy (AttEn), bubble entropy (BubbEn) and symbolic dynamic entropy (SyDyEn) of univariate data sequence features. The long short-term memory (LSTM) deep learning neural network was used to automatically classify dementia severity through noninvasive EEG-based recordings. The LSTM classification result with AttEn exceeds an average of 88.9% than BubbEn and SyDyEn, with classification results of 69.2% and 77.7%, respectively. The analysis of the brain EEG-based dementia severity dataset suggests that AttEn could potentially serve as a biomarker for detecting dementia severity. AttEn can capture relevant patterns and features in the EEG data and may be indicative of the severity of dementia with LSTM RNN to differentiate patients with VD, patients with MCI and NC individuals.
format Article
id doaj-art-1005f631de8b45a3bb43f16b5bb0fa3f
institution DOAJ
issn 1818-1171
2312-0789
language English
publishDate 2024-12-01
publisher Al-Khwarizmi College of Engineering – University of Baghdad
record_format Article
series Al-Khawarizmi Engineering Journal
spelling doaj-art-1005f631de8b45a3bb43f16b5bb0fa3f2025-08-20T02:51:00ZengAl-Khwarizmi College of Engineering – University of BaghdadAl-Khawarizmi Engineering Journal1818-11712312-07892024-12-0120410.22153/kej.2024.08.002Deep Learning Model for Prediction of Dementia Severity based on EEG SignalsNoor Kamal Al-Qazzaz 0Sawal Hamid Bin Mohd Ali 1Siti Anom Ahmad 2Department of Biomedical Engineering, Al-Khwarizmi College of Engineering, University of Baghdad, Baghdad 47146, IraqDepartment of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, UKM Bangi, Selangor 43600, Malaysia4Department of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra Malaysia, UPM Serdang, Selangor 43400, Malaysia This study aimed to determine variations in the electroencephalograms (EEGs) of 15 individuals who were diagnosed with mild cognitive impairment (MCI) following stroke, 5 individuals suffering from vascular dementia (VD) and 15 healthy normal control (NC) individuals who performed a working memory task. Conventional filters including notch and bandpass filters were utilised to remove noise from the EEG data. The proposed method comprises computing the estimates of the attention entropy (AttEn), bubble entropy (BubbEn) and symbolic dynamic entropy (SyDyEn) of univariate data sequence features. The long short-term memory (LSTM) deep learning neural network was used to automatically classify dementia severity through noninvasive EEG-based recordings. The LSTM classification result with AttEn exceeds an average of 88.9% than BubbEn and SyDyEn, with classification results of 69.2% and 77.7%, respectively. The analysis of the brain EEG-based dementia severity dataset suggests that AttEn could potentially serve as a biomarker for detecting dementia severity. AttEn can capture relevant patterns and features in the EEG data and may be indicative of the severity of dementia with LSTM RNN to differentiate patients with VD, patients with MCI and NC individuals. https://alkej.uobaghdad.edu.iq/index.php/alkej/article/view/938
spellingShingle Noor Kamal Al-Qazzaz
Sawal Hamid Bin Mohd Ali
Siti Anom Ahmad
Deep Learning Model for Prediction of Dementia Severity based on EEG Signals
Al-Khawarizmi Engineering Journal
title Deep Learning Model for Prediction of Dementia Severity based on EEG Signals
title_full Deep Learning Model for Prediction of Dementia Severity based on EEG Signals
title_fullStr Deep Learning Model for Prediction of Dementia Severity based on EEG Signals
title_full_unstemmed Deep Learning Model for Prediction of Dementia Severity based on EEG Signals
title_short Deep Learning Model for Prediction of Dementia Severity based on EEG Signals
title_sort deep learning model for prediction of dementia severity based on eeg signals
url https://alkej.uobaghdad.edu.iq/index.php/alkej/article/view/938
work_keys_str_mv AT noorkamalalqazzaz deeplearningmodelforpredictionofdementiaseveritybasedoneegsignals
AT sawalhamidbinmohdali deeplearningmodelforpredictionofdementiaseveritybasedoneegsignals
AT sitianomahmad deeplearningmodelforpredictionofdementiaseveritybasedoneegsignals