Stroke Detection Using EEG and Deep Learning: A Comparative Study of Feature Engineering Techniques
Downloads
Strokes remain one of the leading causes of disability and mortality worldwide, underscoring the need for effective early detection and intervention methods. Recently, researchers have shown a growing interest in harnessing bio-signals, natural indicators produced by the human body, as potential markers for stroke detection. Multiple types of bio-signals, such as electroencephalography (EEG), are currently being explored in stroke diagnostic studies. This approach is promising because it offers a non-invasive, cost-effective, accurate, and portable means of detecting strokes. The objectives of this research are to investigate the effectiveness of deep learning (DL) techniques, including Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), Recurrent Neural Networks (RNN), CNN-LSTM hybrid models, and CNN-Gated Recurrent Unit (CNN-GRU) models, for detecting early-stage strokes based on EEG data. In addition, the impact of diverse feature extraction techniques, including utilizing all features, selecting features with a Decision Tree (DT) based on different thresholds, Principal Component Analysis (PCA), and Independent Component Analysis (ICA), is analyzed to evaluate their influence on model performance. A comparative discussion is conducted across multiple experimental setups to identify the most effective DL and feature engineering combinations for stroke detection. Across 35 different experiments, the CNN-LSTM model with seven selected features using the DT method yields the best results, achieving 86% accuracy, 99% precision, 81% recall, and an F1-score of 89%.
Downloads
[1] Gupta, S., & Raheja, S. (2022). Stroke Prediction using Machine Learning Methods. 2022 12th International Conference on Cloud Computing, Data Science & Engineering (Confluence), 553–558. doi:10.1109/Confluence52989.2022.9734197.
[2] Shoily, T. I., Islam, T., Jannat, S., Tanna, S. A., Alif, T. M., & Ema, R. R. (2019). Detection of Stroke Disease using Machine Learning Algorithms. 2019 10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019, 1–6. doi:10.1109/ICCCNT45670.2019.8944689.
[3] Yu, J., Park, S., Kwon, S. H., Ho, C. M. B., Pyo, C. S., & Lee, H. (2020). AI-based stroke disease prediction system using real-time electromyography signals. Applied Sciences (Switzerland), 10(19), 6791. doi:10.3390/app10196791.
[4] Chiaramonte, R., Pavone, P., & Vecchio, M. (2020). Speech rehabilitation in dysarthria after stroke: A systematic review of the studies. European Journal of Physical and Rehabilitation Medicine, 56(5), 547–562. doi:10.23736/S1973-9087.20.06185-7.
[5] Aldossary, M. I., Alghamedy, F. H., Alabbad, D. A., Alnuaim, R. A., Altaweel, M. S., Alshami, R. A. H., … Olatunji, S. O. (2025). ML and DL Models for Stroke Prediction from Bio-Signals: A Systematic Review and Bibliometric Analysis. HighTech and Innovation Journal, 6(3), 1062–1078. doi:10.28991/HIJ-2025-06-03-019.
[6] Thayumanavan, M., & Ramasamy, A. (2023). Deep Learning Based Stroke Disease Prediction using Multi Modal Biosignals. 2023 International Conference on Next Generation Electronics, NEleX 2023, 1–6. doi:10.1109/NEleX59773.2023.10421131.
[7] Yoon, D., Jang, J. H., Choi, B. J., Kim, T. Y., & Han, C. H. (2020). Discovering hidden information in biosignals from patients using artificial intelligence. Korean Journal of Anesthesiology, 73(4), 275–284. doi:10.4097/kja.19475.
[8] Shreve, L., Kaur, A., Vo, C., Wu, J., Cassidy, J. M., Nguyen, A., Zhou, R. J., Tran, T. B., Yang, D. Z., Medizade, A. I., Chakravarthy, B., Hoonpongsimanont, W., Barton, E., Yu, W., Srinivasan, R., & Cramer, S. C. (2019). Electroencephalography Measures are Useful for Identifying Large Acute Ischemic Stroke in the Emergency Department. Journal of Stroke and Cerebrovascular Diseases, 28(8), 2280–2286. doi:10.1016/j.jstrokecerebrovasdis.2019.05.019.
[9] Mak, J., Kocanaogullari, D., Huang, X., Kersey, J., Shih, M., Grattan, E. S., Skidmore, E. R., Wittenberg, G. F., Ostadabbas, S., & Akcakaya, M. (2022). Detection of Stroke-Induced Visual Neglect and Target Response Prediction Using Augmented Reality and Electroencephalography. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 30, 1840–1850. doi:10.1109/TNSRE.2022.3188184.
[10] Hussain, I., & Park, S. J. (2020). HealthSOS: Real-Time Health Monitoring System for Stroke Prognostics. IEEE Access, 8, 213574–213586. doi:10.1109/ACCESS.2020.3040437.
[11] Zhang, H., Zhou, Q. Q., Chen, H., Hu, X. Q., Li, W. G., Bai, Y., Han, J. X., Wang, Y., Liang, Z. H., Chen, D., Cong, F. Y., Yan, J. Q., & Li, X. L. (2023). The applied principles of EEG analysis methods in neuroscience and clinical neurology. Military Medical Research, 10(1). doi:10.1186/s40779-023-00502-7.
[12] Chicco, D., Karaiskou, A. I., & De Vos, M. (2024). Ten quick tips for electrocardiogram (ECG) signal processing. PeerJ Computer Science, 10, 1–22. doi:10.7717/PEERJ-CS.2295.
[13] Mehendale, N., & Gohel, V. (2020). Review on Electromyography Signal Acquisition, Processing and Its Applications. SSRN Electronic Journal. doi:10.2139/ssrn.3598928.
[14] Park, J., Seok, H. S., Kim, S. S., & Shin, H. (2022). Photoplethysmogram Analysis and Applications: An Integrative Review. Frontiers in Physiology, 12. doi:10.3389/fphys.2021.808451.
[15] Choi, Y. A., Park, S. J., Jun, J. A., Pyo, C. S., Cho, K. H., Lee, H. S., & Yu, J. H. (2021). Deep learning-based stroke disease prediction system using real-time bio signals. Sensors, 21(13), 4269. doi:10.3390/s21134269.
[16] Kalahasty, R., & Motati, L. S. (2022). An EEG-Based Diagnostic Framework for Strokes Using Spectral Analysis and Deep Learning. 2022 IEEE MIT Undergraduate Research Technology Conference (URTC), 1–5. doi:10.1109/URTC56832.2022.10002236.
[17] Kumar, S., & Sengupta, A. (2022). EEG Classification For Stroke Detection Using Deep Learning Networks. 2022 2nd International Conference on Emerging Frontiers in Electrical and Electronic Technologies, ICEFEET 2022. doi:10.1109/ICEFEET51821.2022.9847883.
[18] Anand Kumar, M., Abirami, N., Guru Prasad, M. S., & Mohankumar, M. (2022). Stroke Disease Prediction based on ECG Signals using Deep Learning Techniques. 2022 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), 453–458. doi:10.1109/CISES54857.2022.9844403.
[19] Kunwar, P., & Choudhary, P. (2023). A stacked ensemble model for automatic stroke prediction using only raw electrocardiogram. Intelligent Systems with Applications, 17, 200165. doi:10.1016/j.iswa.2022.200165.
[20] Elbagoury, B. M., Vladareanu, L., Vlădăreanu, V., Salem, A. B., Travediu, A. M., & Roushdy, M. I. (2023). A Hybrid Stacked CNN and Residual Feedback GMDH-LSTM Deep Learning Model for Stroke Prediction Applied on Mobile AI Smart Hospital Platform. Sensors, 23(7), 3500. doi:10.3390/s23073500.
[21] Goren, N., Avery, J., Dowrick, T., Mackle, E., Witkowska-Wrobel, A., Werring, D., & Holder, D. (2018). Multi-frequency electrical impedance tomography and neuroimaging data in stroke patients. Scientific Data, 5(1), 180112. doi:10.1038/sdata.2018.112.
[22] Theng, D., & Bhoyar, K. K. (2024). Feature selection techniques for machine learning: a survey of more than two decades of research. Knowledge and Information Systems, 66(3), 1575–1637. doi:10.1007/s10115-023-02010-5.
[23] Jollife, I. T., & Cadima, J. (2016). Principal component analysis: A review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 374(2065), 20150202. doi:10.1098/rsta.2015.0202.
[24] Subasi, A., & Gursoy, M. I. (2010). EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Systems with Applications, 37(12), 8659–8666. doi:10.1016/j.eswa.2010.06.065.
[25] Gramfort, A., Luessi, M., Larson, E., Engemann, D. A., Strohmeier, D., Brodbeck, C., ... & Hämäläinen, M. (2013). MEG and EEG data analysis with MNE-Python. Frontiers in Neuroinformatics, 7, 267. doi:10.3389/fnins.2013.00267.
[26] Hao-Cun, W. U. (2007). Independent Component Analysis and Its Applications in Finance Independent Component Analysis. Thesis, University of Hong Kong, Pokfulam, Hong Kong. doi:10.5353/th_b3955909.
[27] Mienye, I. D., & Jere, N. (2024). A Survey of Decision Trees: Concepts, Algorithms, and Applications. IEEE Access, 12, 86716–86727. doi:10.1109/ACCESS.2024.3416838.
[28] Zhao, Y., Huang, Y., Wang, Z., & Liu, X. (2024). A new feature selection method based on importance measures for crude oil return forecasting. Neurocomputing, 581, 127470. doi:10.1016/j.neucom.2024.127470.
[29] Gautam, A., & Raman, B. (2021). Towards effective classification of brain hemorrhagic and ischemic stroke using CNN. Biomedical Signal Processing and Control, 63, 102178. doi:10.1016/j.bspc.2020.102178.
[30] Ruan, D., Wang, J., Yan, J., & Gühmann, C. (2023). CNN parameter design based on fault signal analysis and its application in bearing fault diagnosis. Advanced Engineering Informatics, 55, 101877. doi:10.1016/j.aei.2023.101877.
[31] Waqas, M., & Humphries, U. W. (2024). A critical review of RNN and LSTM variants in hydrological time series predictions. MethodsX, 13, 102946. doi:10.1016/j.mex.2024.102946.
[32] Kuila, S., Dhanda, N., & Joardar, S. (2022). ECG signal classification and arrhythmia detection using ELM-RNN. Multimedia Tools and Applications, 81(18), 25233–25249. doi:10.1007/s11042-022-11957-6.
[33] Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. doi:10.1162/neco.1997.9.8.1735.
[34] Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1724–1734. doi:10.3115/v1/d14-1179.
[35] Xu, S., Li, J., Liu, K., & Wu, L. (2019). A Parallel GRU Recurrent Network Model and its Application to Multi-Channel Time-Varying Signal Classification. IEEE Access, 7, 118739–118748. doi:10.1109/ACCESS.2019.2936516.
[36] Wang, J., Yu, L.-C., Lai, K. R., & Zhang, X. (2016). Dimensional Sentiment Analysis Using a Regional CNN-LSTM Model. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 225–230. doi:10.18653/v1/p16-2037.
[37] Dua, N., Singh, S. N., & Semwal, V. B. (2021). Multi-input CNN-GRU based human activity recognition using wearable sensors. Computing, 103(7), 1461–1478. doi:10.1007/s00607-021-00928-8.
[38] Cao, B., Shang, H., Fan, M., & Sun, F. (2024). CNN-GRU based method for peak location of reflected Terahertz signals from thermal barrier coatings. Nondestructive Testing and Evaluation, 39(8), 2132–2149. doi:10.1080/10589759.2023.2288880.
[39] Khan, H. A., Ul Ain, R., Kamboh, A. M., Butt, H. T., Shafait, S., Alamgir, W., Stricker, D., & Shafait, F. (2022). The NMT Scalp EEG Dataset: An Open-Source Annotated Dataset of Healthy and Pathological EEG Recordings for Predictive Modeling. Frontiers in Neuroscience, 15. doi:10.3389/fnins.2021.755817.
[40] Roy, S., Kiral-Kornek, I., & Harrer, S. (2019). ChronoNet: A Deep Recurrent Neural Network for Abnormal EEG Identification. In: Riaño, D., Wilk, S., ten Teije, A. (eds) Artificial Intelligence in Medicine. AIME 2019. Lecture Notes in Computer Science. Springer, Cham, Switzerland. doi:10.1007/978-3-030-21642-9_8.
[41] Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13(2), 281-305.
[42] Shlens, J. (2014). A tutorial on independent component analysis. arXiv Preprint, arXiv:1404.2986. doi:10.48550/arXiv.1404.2986.
[43] Wilkinson, C. M., Burrell, J. I., Kuziek, J. W. P., Thirunavukkarasu, S., Buck, B. H., & Mathewson, K. E. (2020). Predicting stroke severity with a 3-min recording from the Muse portable EEG system for rapid diagnosis of stroke. Scientific Reports, 10(1),18465. doi:10.1038/s41598-020-75379-w.
[44] Jafari, M., Shoeibi, A., Khodatars, M., Bagherzadeh, S., Shalbaf, A., García, D. L., Gorriz, J. M., & Acharya, U. R. (2023). Emotion recognition in EEG signals using deep learning methods: A review. Computers in Biology and Medicine, 165, 107450. doi:10.1016/j.compbiomed.2023.107450.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
