An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer's disease and frontotemporal dementia

The early and accurate diagnosis of Alzheimer's Disease and Frontotemporal Dementia remains a critical challenge, particularly with traditional machine learning models which often fail to provide transparency in their predictions, reducing user confidence and treatment effectiveness. To address...

Full description

Saved in:
Bibliographic Details
Main Authors: Waqar Khan, Muhammad Shahbaz Khan, Sultan Noman Qasem, Wad Ghaban, Faisal Saeed, Muhammad Hanif, Jawad Ahmad
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1590201/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850104034488221696
author Waqar Khan
Muhammad Shahbaz Khan
Sultan Noman Qasem
Sultan Noman Qasem
Wad Ghaban
Faisal Saeed
Muhammad Hanif
Jawad Ahmad
author_facet Waqar Khan
Muhammad Shahbaz Khan
Sultan Noman Qasem
Sultan Noman Qasem
Wad Ghaban
Faisal Saeed
Muhammad Hanif
Jawad Ahmad
author_sort Waqar Khan
collection DOAJ
description The early and accurate diagnosis of Alzheimer's Disease and Frontotemporal Dementia remains a critical challenge, particularly with traditional machine learning models which often fail to provide transparency in their predictions, reducing user confidence and treatment effectiveness. To address these limitations, this paper introduces an explainable and lightweight deep learning framework comprising temporal convolutional networks and long short-term memory networks that efficiently classifies Frontotemporal dementia (FTD), Alzheimer's Disease (AD), and healthy controls using electroencephalogram (EEG) data. Feature engineering has been conducted using modified Relative Band Power (RBP) analysis, leveraging six EEG frequency bands extracted through power spectrum density (PSD) calculations. The model achieves high classification accuracies of 99.7% for binary tasks and 80.34% for multi-class classification. Furthermore, to enhance the transparency and interpretability of the framework, SHAP (SHapley Additive exPlanations) has been utilized as an explainable artificial intelligence technique that provides insights into feature contributions.
format Article
id doaj-art-1d1c9be5de934476ad79aee29de4e820
institution DOAJ
issn 2296-858X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-1d1c9be5de934476ad79aee29de4e8202025-08-20T02:39:25ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-07-011210.3389/fmed.2025.15902011590201An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer's disease and frontotemporal dementiaWaqar Khan0Muhammad Shahbaz Khan1Sultan Noman Qasem2Sultan Noman Qasem3Wad Ghaban4Faisal Saeed5Muhammad Hanif6Jawad Ahmad7Department of Cybersecurity, Pakistan Navy Engineering College, National University of Sciences and Technology, Karachi, PakistanSchool of Computing, Engineering and the Built Environment, Edinburgh Napier University, Edinburgh, United KingdomComputer Science Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi ArabiaKing Salman Center for Disability Research, Riyadh, Saudi ArabiaApplied College, University of Tabuk, Tabuk, Saudi ArabiaCollege of Computing, Birmingham City University, Birmingham, United KingdomDepartment of Informatics, School of Business, Örebro Universitet, Örebro, SwedenCybersecurity Center, Prince Mohammad Bin Fahd University, Al-Khobar, Saudi ArabiaThe early and accurate diagnosis of Alzheimer's Disease and Frontotemporal Dementia remains a critical challenge, particularly with traditional machine learning models which often fail to provide transparency in their predictions, reducing user confidence and treatment effectiveness. To address these limitations, this paper introduces an explainable and lightweight deep learning framework comprising temporal convolutional networks and long short-term memory networks that efficiently classifies Frontotemporal dementia (FTD), Alzheimer's Disease (AD), and healthy controls using electroencephalogram (EEG) data. Feature engineering has been conducted using modified Relative Band Power (RBP) analysis, leveraging six EEG frequency bands extracted through power spectrum density (PSD) calculations. The model achieves high classification accuracies of 99.7% for binary tasks and 80.34% for multi-class classification. Furthermore, to enhance the transparency and interpretability of the framework, SHAP (SHapley Additive exPlanations) has been utilized as an explainable artificial intelligence technique that provides insights into feature contributions.https://www.frontiersin.org/articles/10.3389/fmed.2025.1590201/fullexplainable AIXAIAlzheimer's diseasetemporal convolutional networkslong short-term memoryfrontotemporal dementia
spellingShingle Waqar Khan
Muhammad Shahbaz Khan
Sultan Noman Qasem
Sultan Noman Qasem
Wad Ghaban
Faisal Saeed
Muhammad Hanif
Jawad Ahmad
An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer's disease and frontotemporal dementia
Frontiers in Medicine
explainable AI
XAI
Alzheimer's disease
temporal convolutional networks
long short-term memory
frontotemporal dementia
title An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer's disease and frontotemporal dementia
title_full An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer's disease and frontotemporal dementia
title_fullStr An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer's disease and frontotemporal dementia
title_full_unstemmed An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer's disease and frontotemporal dementia
title_short An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer's disease and frontotemporal dementia
title_sort explainable and efficient deep learning framework for eeg based diagnosis of alzheimer s disease and frontotemporal dementia
topic explainable AI
XAI
Alzheimer's disease
temporal convolutional networks
long short-term memory
frontotemporal dementia
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1590201/full
work_keys_str_mv AT waqarkhan anexplainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT muhammadshahbazkhan anexplainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT sultannomanqasem anexplainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT sultannomanqasem anexplainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT wadghaban anexplainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT faisalsaeed anexplainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT muhammadhanif anexplainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT jawadahmad anexplainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT waqarkhan explainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT muhammadshahbazkhan explainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT sultannomanqasem explainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT sultannomanqasem explainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT wadghaban explainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT faisalsaeed explainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT muhammadhanif explainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia
AT jawadahmad explainableandefficientdeeplearningframeworkforeegbaseddiagnosisofalzheimersdiseaseandfrontotemporaldementia