Privacy-Preserving Deep Learning Models For Alcoholism Diagnosis Through EEG Data Analysis Using Differential Privacy ‎Mechanisms

  • Authors

    • Varalatchoumy M Department of Artificial Intelligence and Machine Learning, Cambridge Institute of Technology, Bengaluru, Karnataka 560036, India
    • A. Srinivasa Reddy Department of Computer Science and Engineering (Data Science), CVR College of Engineering, Hyderabad, Telangana 501510, India
    • S .Sagar Imambi Department of Computer Science & Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh 522302, ‎India
    • Gaurav Kumar Ameta Department of Computer Science and Engineering, Parul Institute of Technology, Parul University, Vadodara, Gujarat 391760, India
    • K . Thaiyalnayaki Department of Electronics and Communication Engineering, Chennai Institute of Technology, Chennai, Tamil Nadu 600069, India
    • S. K. Logesh Department of Electrical and Electronics Engineering, Kongu Engineering College, Perundurai, Erode, Tamil Nadu 638060, India
    • S . Dhivya Department of Research and Innovation, Saveetha School of Engineering, SIMATS, Chennai, Tamil Nadu, India
    • K Mu‎thulakshmi Department of Information Technology, Panimalar Engineering College, Chennai, Tamil Nadu 600123, India
    https://doi.org/10.14419/7gtxb837

    Received date: May 10, 2025

    Accepted date: June 18, 2025

    Published date: June 30, 2025

  • Electroencephalogram (EEG); Gaussian Differential Privacy (GDP); Differential Privacy; Deep learning

  • Abstract

    Alcoholism diagnosis through electroencephalogram (EEG) data analysis offers a promising alternative to traditional methods by identifying ‎specific brain activity patterns associated with alcohol dependency. While deep learning techniques have demonstrated high accuracy in ‎classifying EEG signals, privacy concerns related to sensitive medical data remain prevalent. Ensuring the privacy of patient data is critical ‎for building trust and enabling the adoption of these tools in real-world clinical settings. This study develops deep learning models with ‎enhanced privacy guarantees by incorporating differential privacy mechanisms, including (ϵ, δ)-Differential Privacy and Gaussian Differential Privacy (GDP). We compare their efficacy in preserving data privacy while maintaining model utility. Experiments show that convolu-‎tional and long-short-term-memory models optimized with Adam excel in utility and stability. GDP outperforms (ϵ, δ)-DP by requiring less ‎noise, while DP-Adam surpasses DP-SGD in privacy and utility, particularly for fast convergence. Larger datasets further enhance this ‎balance, emphasizing the importance of effective privacy mechanisms and sufficient data. By balancing privacy and utility, this work con-‎contributes a novel approach to privacy-preserving AI for sensitive health applications, emphasizing scalable models that maintain diagnostic ‎accuracy‎.

  • References

    1. Akbari, H., Sadiq, M. T., Payan, M., Esmaili, S. S., Baghri, H., & Bagheri, H. (2021). Depression detection based on geometrical features extracted from SODP shape of EEG signals and binary PSO. Traitement du Signal, 38, 43–46. https://doi.org/10.18280/ts.380102.
    2. Shi, W., Feng, H., Zhang, X., & Yeh, C.-H. (2023). Amplitude modulation multiscale entropy characterizes complexity and brain states. Chaos, Solitons & Fractals, 173, 113646. https://doi.org/10.1016/j.chaos.2023.113646.
    3. Sadiq, M. T., Akbari, H., Rehman, A. U., Nishtar, Z., Masood, B., Ghazvini, M., Hamedi, N., & Kaabar, M. K. A. (2021). Exploiting feature selec-tion and neural network techniques for identification of focal and nonfocal EEG signals in TQWT domain. Journal of Healthcare Engineering, 2021, 1–24. https://doi.org/10.1155/2021/6283900.
    4. Yeh, C. H., Zhang, C., Shi, W., Lo, M. T., Tinkhauser, G., & Oswal, A. (2023). Cross-frequency coupling and intelligent neuromodulation. Cyborg and Bionic Systems, 4, 34. https://doi.org/10.34133/cbsystems.0034.
    5. Sadiq, M. T., Akbari, H., Siuly, S., Li, Y., & Wen, P. (2022). Alcoholic EEG signals recognition based on phase space dynamic and geometrical features. Chaos, Solitons & Fractals, 158, 112036. https://doi.org/10.1016/j.chaos.2022.112036.
    6. Cohen, S., Katz, O., Presil, D., Arbili, O., & Rokach, L. (2023). Ensemble learning for alcoholism classification using EEG signals. IEEE Sensors Journal, 23, 17714–17724. https://doi.org/10.1109/JSEN.2023.3279904.
    7. Pain, S., Roy, S., Sarma, M., & Samanta, D. (2023). Detection of alcoholism by combining EEG local activations with brain connectivity features and graph neural network. Biomedical Signal Processing and Control, 85, 104851. https://doi.org/10.1016/j.bspc.2023.104851.
    8. Salankar, N., Qaisar, S. M., Pławiak, P., Tadeusiewicz, R., & Hammad, M. (2022). EEG based alcoholism detection by oscillatory modes decompo-sition, second order difference plots and machine learning. Biocybernetics and Biomedical Engineering, 42, 173–186. https://doi.org/10.1016/j.bbe.2021.12.009.
    9. Anuragi, A., & Sisodia, D. (2020). Empirical wavelet transform based automated alcoholism detecting using EEG signal features. Biomedical Sig-nal Processing and Control, 57, 101777. https://doi.org/10.1016/j.bspc.2019.101777.
    10. Sadiq, M. T., Aziz, M. Z., Almogren, A., Yousaf, A., Siuly, S., & Rehman, A. U. (2022). Exploiting pre-trained CNN models for the development of an EEG-based robust BCI framework. Computers in Biology and Medicine, 143, 105242. https://doi.org/10.1016/j.compbiomed.2022.105242.
    11. Browarska, N., Kawala-Sterniuk, A., Zygarlicki, J., Podpora, M., Pelc, M., Martinek, R., & Gorzelanczyk, E. J. (2021). Comparison of smoothing filters’ influence on quality of data recorded with the Emotiv Epoc Flex brain–computer interface headset during audio stimulation. Brain Sciences, 11, 98. https://doi.org/10.3390/brainsci11010098.
    12. Anuragi, A., Sisodia, D., & Pachori, R. B. (2021). Automated FBSE-EWT based learning framework for detection of epileptic seizures using time-segmented EEG signals. Computers in Biology and Medicine, 136, 104708. https://doi.org/10.1016/j.compbiomed.2021.104708.
    13. Farsi, L., Siuly, S., Kabir, E., & Wang, H. (2021). Classification of alcoholic EEG signals using a deep learning method. IEEE Sensors Journal, 21, 3552–3560. https://doi.org/10.1109/JSEN.2020.3026830.
    14. Li, H., & Wu, L. (2022). EEG classification of normal and alcoholic by deep learning. Brain Sciences, 12(6), 819. https://doi.org/10.3390/brainsci12060778.
    15. Ahmadi, N., Pei, Y., & Pechenizkiy, M. (2017). Detection of alcoholism based on EEG signals and functional brain network features extraction. IEEE International Conference Proceedings, 2017-June, 179–184. https://doi.org/10.1109/CBMS.2017.46.
    16. Farsi, L., Siuly, S., Kabir, E., & Wang, H. (2021). Classification of alcoholic EEG signals using a deep learning method. IEEE Sensors Journal, 21(3), 3552–3560. https://doi.org/10.1109/JSEN.2020.3026830.
    17. Balle, B., Barthe, G., Gaboardi, M., & Hsu, J. (2020). Privacy amplification by subsampling: Tight analyses via couplings and divergences. Journal of Privacy and Confidentiality, 10(S1), 1–39. https://doi.org/10.29012/jpc.726.
    18. Sherstinsky, J. (2020). Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phe-nomena, 404, 132306. https://doi.org/10.1016/j.physd.2019.132306.
    19. Brunnhuber, F., Slater, J., Goyal, S., Amin, D., Thorvardsson, G., Freestone, D. R., & Richardson, M. P. (2020). Past, present and future of home video-electroencephalographic telemetry: A review of the development of in-home video-electroencephalographic recordings. Epilepsia, 61(S1), S3–S10. https://doi.org/10.1111/epi.16578.
    20. Ko, L. W., Komarov, O., Lai, W. K., Liang, W. G., & Jung, T. P. (2020). Eyeblink recognition improves fatigue prediction from single-channel forehead EEG in a realistic sustained attention task. Journal of Neural Engineering, 17(3), 036015. https://doi.org/10.1088/1741-2552/ab909f.
    21. Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006). Calibrating noise to sensitivity in private data analysis. In Theory of Cryptography Con-ference (TCC), Lecture Notes in Computer Science (Vol. 3876, pp. 265–284). Springer. https://doi.org/10.1007/11681878_14.
    22. Porjesz, B., Rangaswamy, M., Kamarajan, C., Jones, K. A., Padmanabhapillai, A., & Begleiter, H. (2005). The utility of neurophysiological markers in the study of alcoholism. Clinical Neurophysiology, 116(5), 993–1018. https://doi.org/10.1016/j.clinph.2004.12.016.
    23. Floridi, L., & Taddeo, M. (2018). What is data ethics? Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 376(2133), 20180081. https://doi.org/10.1098/rsta.2018.0081

  • Downloads

  • How to Cite

    M, V. ., Reddy , A. S. ., Imambi, S. .Sagar ., Ameta, G. K. ., Thaiyalnayaki, K. . ., Logesh , S. K. ., Dhivya, S. . ., & Mu‎thulakshmi, K. . (2025). Privacy-Preserving Deep Learning Models For Alcoholism Diagnosis Through EEG Data Analysis Using Differential Privacy ‎Mechanisms. International Journal of Basic and Applied Sciences, 14(2), 493-503. https://doi.org/10.14419/7gtxb837