Enhancing Multiclass Dementia Detection with EEG Signals: A Feature-Driven LSTM Approach
Received: 26 September 2025 | Revised: 14 October 2025 and 2 November 2025 | Accepted: 3 November 2025 | Online: 4 December 2025
Corresponding author: Rageshri Bakare
Abstract
Early and accurate differentiation of dementia subtypes remains a major challenge in clinical neurophysiology and is crucial for timely intervention and personalized care. This study introduces a novel EEG-based deep learning framework for classifying Alzheimer's Disease (AD), Mild Cognitive Impairment (MCI), Subjective Cognitive Decline (SCD), and Healthy Controls (HC). Resting-state EEG data from 139 participants (>45 years) were analyzed through spectral and connectivity features, focusing on Theta-Beta activity linked to cognitive dysfunction. A feature-enriched Long Short-Term Memory (LSTM) model integrated Pearson's correlation-based connectivity measures with optimized dimensionality reduction techniques to enhance class separability and computational efficiency. The proposed PCC-PCA-LSTM model achieved 99.47% classification accuracy and an AUC of 1.00 across all classes, significantly outperforming conventional EEG-based diagnostic approaches. These findings demonstrate the model's potential as a clinically viable and scalable tool for early detection, continuous monitoring, and decision support in dementia care, bridging the gap between neurophysiological insight and practical diagnostic utility.
Keywords:
Electroencephalography (EEG), dementia detection, Alzheimer's, Mild Cognitive Impairment (MCI), feature engineering, PCA, LDA, LSTMDownloads
References
P. H. Kachare, S. B. Sangle, D. V. Puri, M. M. Khubrani, and I. Al-Shourbaji, ''STEADYNet: Spatiotemporal EEG analysis for dementia detection using convolutional neural network,'' Cognitive Neurodynamics, vol. 18, no. 5, pp. 3195–3208, Oct. 2024. DOI: https://doi.org/10.1007/s11571-024-10153-6
H. Uyanik, A. Sengur, M. Salvi, R. Tan, J. H. Tan, and U. R. Acharya, ''Automated Detection of Neurological and Mental Health Disorders Using EEG Signals and Artificial Intelligence: A Systematic Review,'' WIREs Data Mining and Knowledge Discovery, vol. 15, no. 1, Mar. 2025, Art. no. e70002. DOI: https://doi.org/10.1002/widm.70002
S. G. Burd, A. V. Lebedeva, Y. V. Rubleva, N. V. Pantina, A. P. Efimenko, and I. I. Kovaleva, ''EEG Changes in Patients with Alzheimer’s Disease,'' Neuroscience and Behavioral Physiology, vol. 54, no. 6, pp. 866–869, July 2024. DOI: https://doi.org/10.1007/s11055-024-01687-7
E. Lopez, L. Sigillo, F. Colonnese, M. Panella, and D. Comminiello, ''Guess What I Think: Streamlined EEG-to-Image Generation with Latent Diffusion Models,'' in ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, Apr. 2025, pp. 1–5. DOI: https://doi.org/10.1109/ICASSP49660.2025.10890059
H. Azami et al., ''Electroencephalogram and Event-Related Potential in Mild Cognitive Impairment: Recent Developments in Signal Processing, Machine Learning, and Deep Learning,'' IEEE Journal of Selected Areas in Sensors, vol. 2, pp. 162–184, 2025. DOI: https://doi.org/10.1109/JSAS.2025.3552546
P. Prado et al., ''Dementia ConnEEGtome: Towards multicentric harmonization of EEG connectivity in neurodegeneration,'' International Journal of Psychophysiology, vol. 172, pp. 24–38, Feb. 2022. DOI: https://doi.org/10.1016/j.ijpsycho.2021.12.008
H. Azami et al., ''Beta to theta power ratio in EEG periodic components as a potential biomarker in mild cognitive impairment and Alzheimer’s dementia,'' Alzheimer’s Research & Therapy, vol. 15, no. 1, Aug. 2023, Art. no. 133. DOI: https://doi.org/10.1186/s13195-023-01280-z
A. Parihar and P. D Swami, ''Analysis of EEG signals with the use of wavelet transform for accurate classification of Alzheimer Disease, Frontotemporal Dementia and healthy subjects using Machine Learning Models,'' Fusion: Practice and Applications, vol. 14, no. 2, pp. 43–55, 2024. DOI: https://doi.org/10.54216/FPA.140203
M. Nour, U. Senturk, and K. Polat, ''A novel hybrid model in the diagnosis and classification of Alzheimer’s disease using EEG signals: Deep ensemble learning (DEL) approach,'' Biomedical Signal Processing and Control, vol. 89, Mar. 2024, Art. no. 105751. DOI: https://doi.org/10.1016/j.bspc.2023.105751
U. Lal, A. V. Chikkankod, and L. Longo, ''A Comparative Study on Feature Extraction Techniques for the Discrimination of Frontotemporal Dementia and Alzheimer’s Disease with Electroencephalography in Resting-State Adults,'' Brain Sciences, vol. 14, no. 4, Mar. 2024, Art. no. 335. DOI: https://doi.org/10.3390/brainsci14040335
M. Khosravi, H. Parsaei, K. Rezaee, and M. S. Helfroush, ''Fusing convolutional learning and attention-based Bi-LSTM networks for early Alzheimer’s diagnosis from EEG signals towards IoMT,'' Scientific Reports, vol. 14, no. 1, Oct. 2024, Art. no. 26002. DOI: https://doi.org/10.1038/s41598-024-77876-8
A. Said and H. Göker, ''Spectral analysis and Bi-LSTM deep network-based approach in detection of mild cognitive impairment from electroencephalography signals,'' Cognitive Neurodynamics, vol. 18, no. 2, pp. 597–614, Apr. 2024. DOI: https://doi.org/10.1007/s11571-023-10010-y
G. Anuradha and D. N. Jamal, ''Classification of Dementia in EEG with a Two-Layered Feed Forward Artificial Neural Network,'' Engineering, Technology & Applied Science Research, vol. 11, no. 3, pp. 7135–7139, June 2021. DOI: https://doi.org/10.48084/etasr.4112
C. Bunterngchit, T. Chearanai, and Y. Bunterngchit, ''Advanced EEG-Based Classification of Alzheimer’s Disease Using CNN-LSTM-Attention Architecture,'' in 2024 22nd International Conference on Research and Education in Mechatronics (REM), Amman, Jordan, Sept. 2024, pp. 107–112. DOI: https://doi.org/10.1109/REM63063.2024.10735597
A. M. Alvi, S. Siuly, and H. Wang, ''A Long Short-Term Memory Based Framework for Early Detection of Mild Cognitive Impairment From EEG Signals,'' IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 7, no. 2, pp. 375–388, Apr. 2023. DOI: https://doi.org/10.1109/TETCI.2022.3186180
M. Alessandrini, G. Biagetti, P. Crippa, L. Falaschetti, S. Luzzi, and C. Turchetti, ''EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network,'' Sensors, vol. 22, no. 10, May 2022, Art. no. 3696. DOI: https://doi.org/10.3390/s22103696
L. Falaschetti, G. Biagetti, M. Alessandrini, C. Turchetti, S. Luzzi, and P. Crippa, ''Multi-Class Detection of Neurodegenerative Diseases from EEG Signals Using Lightweight LSTM Neural Networks,'' Sensors, vol. 24, no. 20, Oct. 2024, Art. no. 6721. DOI: https://doi.org/10.3390/s24206721
F. Demirdöğen, Ç. Danacı, S. A. Tuncer, M. Akkuş, and S. Yıldız, ''Deep Convolutional Neural Network Model for the Differential Diagnosis of Schizophrenia Using EEG Signals,'' Hitit Medical Journal, vol. 6, no. 3, pp. 257–265, Oct. 2024. DOI: https://doi.org/10.52827/hititmedj.1440548
M. Kim, Y. C. Youn, and J. Paik, ''Deep learning-based EEG analysis to classify normal, mild cognitive impairment, and dementia: Algorithms and dataset,'' NeuroImage, vol. 272, May 2023, Art. no. 120054. DOI: https://doi.org/10.1016/j.neuroimage.2023.120054
N. P. Tigga, N. Kumari, and A. J. Tigga, ''Integrating Advanced EEG Features with Graph Convolution Transformers for Alzheimer’s Detection,'' Procedia Computer Science, vol. 258, pp. 3241–3250, 2025. DOI: https://doi.org/10.1016/j.procs.2025.04.582
K. Li, B. Ao, X. Wu, Q. Wen, E. U. Haq, and J. Yin, ''Parkinson’s disease detection and classification using EEG based on deep CNN-LSTM model,'' Biotechnology and Genetic Engineering Reviews, vol. 40, no. 3, pp. 2577–2596, Nov. 2024. DOI: https://doi.org/10.1080/02648725.2023.2200333
I. Lazarou, K. Georgiadis, S. Nikolopoulos, V. Oikonomou, and I. Kompatsiaris, ''Resting-State High-Density EEG using EGI GES 300 with 256 Channels of Healthy Elders, People with Subjective and Mild Cognitive Impairment and Alzheimer’s Disease,'' Zenodo, Dec. 23, 2020.
Downloads
How to Cite
License
Copyright (c) 2025 Rageshri Bakare, Virendra Shete, Magda Tsolaki, Spiros Nikolopoulos
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
