Fuzzy RNN Model-Based Classification of Alzheimer’s Disease and Dementia Using Brain EEG Signals
- 19 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (2) , 5559-5568
Abstract
Alzheimer’s Disease (AD) and Dementia represent critical healthcare challenges worldwide, underscoring the need for reliable and early diagnostic tools. This study presents an innovative classification framework that combines the strengths of fuzzy logic and Recurrent Neural Networks (RNNs) to enhance the detection of AD and dementia. Leveraging Electroencephalogram (EEG) signals, a non-invasive and informative modality reflecting cognitive function, we propose a Fuzzy RNN model that integrates the sequential learning capabilities of RNNs with the interpretability and uncertainty handling of fuzzy logic. The model is trained on a comprehensive dataset comprising EEG recordings from individuals with Alzheimer’s Disease, various types of dementia, and healthy controls. Evaluation metrics, including sensitivity (96.49%–97.19%), specificity (96.72%–97.85%), and accuracy (97.82%–98.82%), highlight the model’s robustness in differentiating between diagnostic categories. Comparative analyses against traditional classifiers demonstrate the Fuzzy RNN’s superior ability to capture intricate temporal patterns in EEG signals, establishing its potential as a reliable tool for early and accurate dementia diagnosis.Keywords
This publication has 33 references indexed in Scilit:
- Classification of Moderate and Advanced Alzheimer's Patients Using Radial Basis Function Based Neural Networks Initialized with Fuzzy LogicIRBM, 2023
- Early dementia diagnosis, MCI‐to‐dementia risk prediction, and the role of machine learning methods for feature extraction from integrated biomarkers, in particular for EEG signal analysisAlzheimer's & Dementia, 2022
- Machine learning techniques for diagnosis of alzheimer disease, mild cognitive disorder, and other types of dementiaBiomedical Signal Processing and Control, 2022
- Deep Learning Approach for Early Detection of Alzheimer’s DiseaseCognitive Computation, 2021
- Early detection of Alzheimer’s disease from EEG signals using Hjorth parametersBiomedical Signal Processing and Control, 2021
- Convolutional neural networks for classification of Alzheimer's disease: Overview and reproducible evaluationMedical Image Analysis, 2020
- Multi-modal deep learning model for auxiliary diagnosis of Alzheimer’s diseaseNeurocomputing, 2019
- Machine learning based hierarchical classification of frontotemporal dementia and Alzheimer's diseaseNeuroImage: Clinical, 2019
- Quantitative EEG and LORETA: valuable tools in discerning FTD from AD?Neurobiology of Aging, 2012
- Differences in quantitative EEG between frontotemporal dementia and Alzheimer’s disease as revealed by LORETAClinical Neurophysiology, 2011