Early Alzheimer’s Disease Detection Using EEG Brain Signals

Abstract

Alzheimer\'s Disease (AD) is a progressive neurodegenerative disease, and early detection is essential for meaningful interventions to improve patient outcomes. While there are diagnostic modalities such as PET scans that can be effective in detecting AD, they tend to be expensive, invasive, or impractical, illustrating the need for more usable alternatives to monitor the progression of AD. Electroencephalography (EEG) is a non-invasive and inexpensive way to monitor brain activity, and it has the potential of being a useful way to identify early markers of AD before significant cognitive decline as well. However, a reliable EEG detection model still must overcome the two significant challenges of a lack of large- scale labelled datasets sufficient for training, and considerable variability in EEG signals across individuals, which can ultimately greatly affect the generalizability of EEG models for helpful detection of AD through these differences. In this paper, we propose a novel deep learning framework to address these challenges with self-supervised learning. Our framework consists of a pre- training phase from a large, unlabelled corpus of general EEG data to extract the universal features of brain signals without needing to depend on scarce AD-specific labels. We then use a fine-tuning phase to adapt the model to the classification problem using a smaller, labelled AD dataset. The model architecture can acquire both spatial and temporal features from EEG signals, which EADDs to a more comprehensive method of analysis. The experimental results clearly indicate that this approach offers a substantial improvement in AD detecting performance and that there was an increase in F1 scores at both the sample and the subject level over the current state f-the-art methods. This research outlines the ability of self- supervised contrastive learning to mitigate the problems of data scarcity and inter-subject variability and can contribute towards more accurate and scalable AD diagnostic tools.

Introduction

Alzheimer’s disease (AD) is a progressive neurological disorder that affects memory, cognitive abilities, and daily functioning. Early detection is essential for timely intervention and improved patient care. Traditional diagnostic methods, such as neuroimaging and cerebrospinal fluid analysis, can be expensive, invasive, or difficult to access. Therefore, electroencephalography (EEG) offers a promising alternative because it is non-invasive, relatively cost-effective, and capable of recording brain activity.

The proposed system aims to develop an EEG-based Alzheimer’s disease detection framework using self-supervised contrastive learning and deep learning techniques. It uses EEG datasets from multiple sources, including ADNI, AIBL, and OASIS, to learn patterns associated with Alzheimer’s disease and healthy brain activity.

The methodology includes EEG data collection, preprocessing, feature extraction, model training, and classification. Preprocessing involves noise and artifact removal, filtering, normalization, and segmentation into fixed-length epochs. Different machine learning and deep learning models, including Support Vector Machines (SVM), Random Forest, Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), hybrid CNN-LSTM networks, and transformer-based architectures, are considered for identifying relevant temporal and spatial EEG patterns.

A key contribution is the use of sample-level and subject-level contrastive learning to improve feature representation, robustness, and generalization across datasets. Features from temporal and spatial branches are combined and fine-tuned using labelled data to classify subjects into Alzheimer’s disease (AD) and Normal Control (NC) categories. Multiple EEG epoch predictions are combined through majority voting to obtain a final subject-level result.

The system’s performance is evaluated using subject-wise cross-validation and cross-dataset testing, with metrics such as accuracy, precision, recall, F1-score, and area under the ROC curve (AUC). The reported results include accuracies of 90.47% on ADFTD, 89.98% on BrainLat, and 100% on CNBPM, with an improvement of up to 9.31% in subject-level F1-score over the reported state-of-the-art comparison. These figures require verification through consistent evaluation protocols and independent testing before clinical conclusions can be drawn.

Conclusion

The EEG-based Alzheimer’s detection system provides an efficient and accurate method for early diagnosis of Alzheimer’s disease. By acquiring and preprocessing EEG signals, the system ensures clean and reliable data for analysis. Feature extraction in time, frequency, and wavelet domains captures essential patterns indicative of cognitive decline. Advanced machine learning and deep learning models, including CNN, LSTM, SVM, and Random Forest, enable precise classification of Normal, MCI, and Alzheimer’s cases. Secure storage of patient data and EEG records allows for longitudinal monitoring and research. The intuitive user interface presents results, probability scores, and reports for clinicians and researchers. The system reduces diagnostic time and supports timely intervention. It also provides a scalable framework for integrating new datasets and models. This project demonstrates the potential of combining EEG analysis with AI for neurological disease detection. Overall, it contributes significantly to improving healthcare outcomes through technology-driven solutions.

References

[1] R. Swarnalatha, “A Greedy Optimized Intelligent Framework for Early Detection of Alzheimer’s Disease Using EEG Signal,” Computational Intelligence and Neuroscience, vol. 2023, Article ID 4808841, pp. 1–10, Feb. 2023. [2] B. Jiao, R. Li, H. Zhou, K. Qing, H. Liu, H. Pan, Y. Lei, W. Fu, X. Wang, X. Xiao, X. Liu, Q. Yang, X. Liao, Y. Zhou, L. Fang, Y. Dong, Y. Yang, H. Jiang, S. Huang, and L. Shen, “Neural Biomarker Diagnosis and Prediction [3] To Mild Cognitive Impairment and Alzheimer’s Disease Using EEG Technology,” Alzheimer’s Research & Therapy, vol. 15, no. 32, pp. 1–14, 2023. [4] Suhad Al-Shoukry; Taha H. Rassem; Nasrin M. Makbo Alzheimer’s Diseases Detection by Using Deep Learning Algorithms [5] Jifa Zhang1, Yinglu Zhang1, Jiaxing Wang 2, Yilin Xia1, Jiaxian Zhang1 and Lei Chen1Recent advances in Alzheimer’s disease: mechanisms, clinical trials and new drug development strategies, 23 August 2024. [6] Yong Peng 1,2*, Hong Jin 1, Ya-hui Xue 1,2 Quan Chen 1, Shun-yu Yao 1,2 Miao-qiao Du 1,2 Current and future therapeutic strategies for Alzheimer’s disease: an overview of drug development bottlenecks. [7] E. Perez-Valero, C. Morillas, M. A. Lopez-Gordo, and J. Minguillon, “Supporting the Detection of Early Alzheimer’s Disease with a Four-Channel EEG Analysis,” International Journal of Neural Systems, vol. 33, no. 4, pp. 1–17, Feb. 2023. [8] W. Xia, R. Zhang, X. Zhang, and M. Usman, “A Novel Method for Diagnosing Alzheimer’s Disease Using Deep Pyramid CNN Based on EEG Signals,” Heliyon, vol. 9, no. 3, e14858, pp. 1–10, Mar. 2023. [9] S. Dogan, M. Baygin, B. Tasci, H. W. Loh, P. D. Barua, T. Tuncer, R.-S. Tan, and [10] U. R. Acharya, “Primate Brain Pattern-Based Automated Alzheimer’s Disease Detection Model Using EEG Signals,” Cognitive Neurodynamics, vol. 17, pp. 647–659, Aug. 2022. [11] K. Alsharabi, Y. Bin Salamah, A. M. Abdurraqee, M. Aljalal, and F. A. Alturki, “EEG Signal Processing for Alzheimer’s Disorders Using Discrete Wavelet Transform and Machine Learning Approaches,” IEEE Access, vol. 10, pp. 89781–89795, Aug. 2022, At .et.

Copyright

Copyright © 2026 Dhruv Patil, Srushti Raul, Utkarsha Bhoir, Simran Patil. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.