A Multimodal Explainable-AI Approach for Deep-Learning-based Epileptic Seizure Detection

Ashwini Patil; Megharani  Patil

doi:10.35882/jeeemi.v8i2.1380

Ashwini Patil Department of Computer Engineering, Thakur College of Engineering and Technology, Mumbai, India https://orcid.org/0009-0004-7271-7884
Megharani Patil Department of Computer Engineering, Thakur College of Engineering and Technology, Mumbai, India https://orcid.org/0000-0001-9845-9597

DOI: https://doi.org/10.35882/jeeemi.v8i2.1380

Keywords: Epileptic Seizure Detection, Multimodal Explainable AI, Transformer, DenseNet121, Transfer Learning, SHAP

Abstract

Epilepsy carries a high risk of sudden death and increased premature mortality, highlighting the importance of automatic seizure detection to support faster diagnosis and treatment. The opacity of existing deep learning models limits their real-world application in diagnosing epileptic seizures, underscoring the need for more transparent and explainable systems. Limited research studies are available on Explainable Artificial Intelligence (XAI)-based epileptic seizure detection, and these studies provide only a visual explanation for the model’s behaviour. Additionally, these studies lack validation of the XAI outputs using quantitative measures. Thus, this research aims to develop an explainable epileptic seizure detection model to address the limitations of existing black-box deep learning approaches. It proposes a novel Hybrid Transformer-DenseNet121-XAI (HTD-MXAI) integrated model for detecting epileptic seizures from EEG data. The proposed model leverages advanced deep learning architectures, namely the Transformer and DenseNet121, for automatic feature extraction, while simultaneously extracting handcrafted features from the time, frequency, and spatial domains. The XAI techniques, such as Attention Weights, Saliency Maps, and SHapley Additive eXplanations (SHAP), are integrated with the proposed model to provide multimodal explainability for the model’s decision-making process. The results demonstrate that the proposed model outperforms state-of-the-art models for seizure detection. It achieves an overall (aggregated across subjects) accuracy of 99.14%, Sensitivity of 98.49%, and Specificity of 99.68% when applied to the CHB-MIT dataset. The Faithfulness score of 40.94% and completeness score of 1.00 indicate that the explanations provided by the XAI method for the model’s prediction are highly reliable. In conclusion, the proposed model offers a promising solution to the constraints, including the interpretability of black box models, limited multimodal explainability, and the validation of XAI techniques in the context of epileptic seizure detection.

Downloads

Download data is not yet available.

References

G. Alarcon and A. Valentin, Introduction to Epilepsy. Cambridge, UK: Cambridge University Press, 2012.

M. K. Alharthi, K. M. Moria, D. M. Alghazzawi, and H. O. Tayeb, "Epileptic disorder detection of seizures using EEG signals," Sensors, vol. 22, no. 17, p. 6592, 2022, doi:10.3390/s22176592.

G. Amrani, A. Adadi, M. Berrada, Z. Souirti, and S. Boujraf, "EEG signal analysis using deep learning: A systematic literature review," in Proc. 5th Int. Conf. Intell. Comput. Data Sci. (ICDS), 2021, pp. 1-6.

M. Sazgar and M. G. Young, Absolute Epilepsy and EEG Rotation Review: Essentials for Trainees. Berlin, Germany: Springer, 2019.doi:10.1007/978-3-030-03511-2.

A. A. Ein Shoka, M. M. Dessouky, A. El-Sayed, and E. E.-D. Hemdan, “EEG seizure detection: Concepts, techniques, challenges, and future trends,” Multimed. Tools Appl., pp. 1-31, 2023. doi: 10.1007/s11042-023-15052-2.

J. Yuan, X. Ran, K. Liu, C. Yao, Y. Yao, H. Wu, and Q. Liu, “Machine learning applications on neuroimaging for diagnosis and prognosis of epilepsy: A review,” J. Neurosci. Methods, vol. 368, p. 109441, 2022. doi: 10.1016/j.jneumeth.2021.109441.

D. D. Spencer, J. L. Gerrard, and H. P. Zaveri, “The roles of surgery and technology in understanding focal epilepsy and its comorbidities,” Lancet Neurology, vol. 17, no. 4, pp. 373-382, 2018, doi: 10.1016/S1474-4422(18)30031-0.

M. Sameer and B. Gupta, “CNN-based framework for detection of epileptic seizures,” Multimedia Tools and Applications, vol. 81, no. 12, pp. 17057-17070, 2022, doi:10.1007/s11042-022-12702-9

X. Wang, T. Ristaniemi, and F. Cong, “One and two-dimensional convolutional neural networks for seizure detection using EEG signals,” in Proc. 28th Eur. Signal Process. Conf. (EUSIPCO), Amsterdam, Netherlands, Jan. 2021, pp. 1387-1391,doi:10.23919/Eusipco47968.2020.9287640

S. Das, S. A. Mumu, M. A. H. Akhand, A. Salam, and M. A. S. Kamal, “Epileptic seizure detection from decomposed EEG signal through 1D and 2D feature representation and convolutional neural network,” Information, vol. 15, no. 5, p. 256,2024, doi:10.3390/info15050256

B. Zhang, W. Wang, Y. Xiao, S. Xiao, S. Chen, S. Chen, and W. Che, “Cross-subject seizure detection in EEGs using deep transfer learning,” Comput. Math. Methods Med., vol. 2020, p. 7902072, 2020, doi:10.1155/2020/7902072

H. S. Nogay and H. Adeli, “Detection of epileptic seizure using pretrained deep convolutional neural network and transfer learning,” Eur. Neurol., vol. 83, no. 6, pp. 602-614, Jan. 2021. [Online]. Available: https://doi.org/10.1159/000512985

A. Narin, “Detection of focal and non-focal epileptic seizure using continuous wavelet transform-based scalogram images and pre-trained deep neural networks,” IRBM, vol. 43, no. 1, pp. 22-31, 2022. [Online]. Available: https://doi.org/10.1016/j.irbm.2020.11.002

A. A. Ein Shoka, M. M. Dessouky, A. El-Sayed, and E. E.-D. Hemdan, “An efficient CNN-based epileptic seizures detection framework using encrypted EEG signals for secure telemedicine applications,” Alexandria Eng. J., vol. 65, pp. 399-412, 2023. [Online]. Available: https://doi.org/10.1016/j.aej.2022.10.014

S. Pattnaik, B. N. Rao, N. K. Rout, et al., “Transfer learning-based epileptic seizure classification using scalogram images of EEG signals,” Multimed. Tools Appl., vol. 83, pp. 84179-84193, 2024. [Online]. Available: https://doi.org/10.1007/s11042-024-19129-4

Zhao, W., Jiang, X., Zhang, B. et al. CTNet: a convolutional transformer network for EEG-based motor imagery classification. Sci Rep 14, 20237 (2024). https://doi.org/10.1038/s41598-024-71118-7

S. Y. Shah, H. Larijani, R. M. Gibson, and D. Liarokapis, “Random neural network-based epileptic seizure episode detection exploiting electroencephalogram signals,” Sensors, vol. 22, no. 7, p. 2466, 2022, doi:10.3390/s22072466

M. N. A. Tawhid, S. Siuly, and T. Li, “A convolutional long short-term memory-based neural network for epileptic seizure detection from EEG,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1-11, 2022, doi: 10.1109/TIM.2022.3217515

Y. Zhang, S. Yao, R. Yang, X. Liu, W. Qiu, L. Han, et al., “Epileptic seizure detection based on bidirectional gated recurrent unit network,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 30, pp. 135-145, 2022, doi: 10.1109/TNSRE.2022.3142270

I. D. Mienye, T. G. Swart, and G. Obaido, “Recurrent neural networks: A comprehensive review of architectures, variants, and applications,” Information, vol. 15, no. 9, Art. no. 517, 2024, doi: 10.3390/info15090517.

N. Ke, T. Lin, Z. Lin, X. Zhou, and T. Ji, “Convolutional transformer networks for epileptic seizure detection,” in Proc. 31st ACM Int. Conf. Inf. Knowl. Manag. (CIKM '22), 2022, pp. 4109-4113, doi: 10.1145/3511808.3557568.

S. Rukhsar and A. K. Tiwari, “Lightweight convolution transformer for cross-patient seizure detection in multi-channel EEG signals,” Comput. Methods Prog. Biomed., vol. 242, p. C, Dec. 2023, doi: 10.1016/j.cmpb.2023.107856.

Y. Ru, G. An, Z. Wei, and H. Chen, “Epilepsy detection based on multi-head self-attention mechanism,” PLoS One, vol. 19, no. 6, p. e0305166, 2024, doi: 10.1371/journal.pone.0305166.

T. Zhou, Y. Feng, J. Wang, Y. Tian, J. Feng and J. Li, "Real-Time Epileptic Seizure Detection Based on Deep Learning," 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Sydney, Australia, 2023, pp. 1-4, doi: 10.1109/EMBC40787.2023.10340706.

J. Xu, S. Yuan, J. Shang, J. Wang, K. Yan, and Y. Yang, “Spatiotemporal network based on GCN and BiGRU for seizure detection,” IEEE J. Biomed. Health Inform., 2024, doi: 10.1109/JBHI.2024.3349583.

X. Dong, Y. Wen, D. Ji, S. Yuan, Z. Liu, W. Shang, and W. Zhou, “Epileptic seizure detection with an end-to-end temporal convolutional network and bidirectional long short-term memory model,” Int. J. Neural Syst., vol. 34, no. 3, Art. no. 2450012, 2024, doi:10.1142/S0129065724500126.

E. Tjoa and C. Guan, “A survey on explainable artificial intelligence (XAI): Toward medical XAI,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 11, pp. 4793-4813, 2021. [Online]. Available: https://doi.org/10.1109/TNNLS.2020.3027314

P. Rathod and S. Naik, “Review on epilepsy detection with explainable artificial intelligence,” in Proc. 10th Int. Conf. Emerging Trends Eng. Technol. - Signal Inf. Process. (ICETET-SIP-22), 2022.

M. Mansour, F. Khnaisser, and H. Partamian, “An explainable model for EEG seizure detection based on connectivity features,” arXiv Preprint, arXiv: Learning, 2020, doi:10.48550/arXiv.2009.12566.

X. Zhang, L. Yao, M. Dong, et al., “Adversarial representation learning for robust patient-independent epileptic seizure detection,” IEEE J. Biomed. Health Inform., vol. 24, no. 10, pp. 2852-2859, 2020, doi: 10.1109/JBHI.2020.2971610.

V. Gabeff, T. Teijeiro, M. Zapater, L. Cammoun, S. Rheims, P. Ryvlin, and D. Atienza, “Interpreting deep learning models for epileptic seizure detection on EEG signals,” Artif. Intell. Med., vol. 117, p. 102084, 2021, doi: 10.1016/j.artmed.2021.102084.

D. Raab, A. Theissler, and M. Spiliopoulou, “XAI4EEG: spectral and spatio-temporal explanation of deep learning-based seizure detection in EEG time series,” Neural Comput. Appl., vol. 35, pp. 10051-10068, 2022, doi: 10.1007/s00521-022-07809-x.

P. S. Rathod, J. M. Bhalodiya, and S. Naik, “Epilepsy detection using Bi-LSTM with explainable artificial intelligence,” in 2022 1st IEEE India Conf. (INDICON), 2022, pp. 1-6, doi: 10.1109/INDICON56171.2022.10039816.

X. Zhao, N. Yoshida, T. Ueda, H. Sugano, and T. Tanaka, “Epileptic seizure detection by using interpretable machine learning models,” J. Neural Eng., vol. 20, no. 1, p. 015002, 2023, doi: 10.1088/1741-2552/acb089.

I. Al-Hussaini and C. S. Mitchell, “SeizFt: Interpretable machine learning for seizure detection using wearables,” Bioengineering, vol. 10, no. 8, p. 918, 2023, doi: 10.3390/bioengineering10080918.

J. C. Vieira, L. A. Guedes, M. R. Santos, and I. Sanchez-Gendriz, “Using explainable artificial intelligence to obtain efficient seizure-detection models based on electroencephalography signals,” Sensors, vol. 23, no. 24, p. 9871, 2023, doi: 10.3390/s23249871.

Y. Ding and W. Zhao, “Channel selection for seizure detection based on explainable AI with Shapley values,” IEEE Sens. J., pp. 1-1, 2024, doi: 10.1109/jsen.2024.3422388.

S. E. Sánchez-Hernández, S. Torres-Ramos, I. Román-Godínez, and R. A. Salido-Ruiz, “Evaluation of the relation between ictal EEG features and XAI explanations,” Brain Sci., vol. 14, no. 4, p. 306, 2024, doi: 10.3390/brainsci14040306.

A. Ijaz, Y. Chen, L. Lin, C. Yan, Z. Liu, I. Ullah, M. Shabaz, X. Wang, K. Huang, G. Li, G. Zhao, O. Williams, S. Chen, “An efficient feature selection and explainable classification method for EEG-based epileptic seizure detection,” J. Inf. Secur. Appl., 2024, doi: 10.1016/j.jisa.2023.103654.

D. S. Udayantha, K. Weerasinghe, N. Wickramasinghe, A. Abeyratne, K. Wickramasinghe, J. Wanigasinghe, A. D. Silva, and C. U. Edussooriya, “Using explainable AI for EEG-based reduced montage neonatal seizure detection,” in 2024 IEEE Int. Conf. Syst., Man, Cybern. (SMC), 2024, pp. 463-468.

S. Mazurek, R. Blanco, J. Falcó-Roget, and A. Crimi, “Explainable graph neural networks for EEG classification and seizure detection in epileptic patients,” in 2024 IEEE Int. Symp. Biomed. Imaging (ISBI), 2024, doi: 10.1109/ISBI56570.2024.10635821.

S. Liu, Y. Zhou, X. Yang, X. Wang, and J. Yin, “A robust automatic epilepsy seizure detection algorithm based on interpretable features and machine learning,” Electronics, vol. 13, no. 14, p. 2727, 2024, doi: 10.3390/electronics13142727.

P. Rathod, S. Naik, and J. M. Bhalodiya, “Epilepsy detection with CNN and explanation with layer-wise relevance propagation,” in 2024 15th Int. Conf. Comput. Commun. Networking Technol. (ICCCNT), 2024, pp. 1-6.

F. A. Khan, Z. Umar, A. Jolfaei, et al., “Explainable AI for epileptic seizure detection in Internet of Medical Things,” Digit. Commun. Netw., 2024, doi: 10.1016/j.dcan.2024.08.013.

M. T. Ribeiro, S. Singh, and C. Guestrin, "“Why should I trust you?” Explaining the predictions of any classifier," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), San Francisco, CA, USA, 2016, pp. 1135-1144, doi: 10.1145/2939672.2939778.

A. Shoeb, “CHB-MIT Scalp EEG Database,” physionet.org, Accessed on 20 December 2024.

I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” in Advances in neural information processing systems, 2014, pp. 2672-2680

A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, "Attention is all you need," in Proc. 31st Int. Conf. Neural Information Processing Systems (NIPS), Red Hook, NY, USA, 2017, pp. 6000-6010.

G. Huang, Z. Liu, L. Van Der Maaten and K. Q. Weinberger, "Densely Connected Convolutional Networks," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 2261-2269, doi: 10.1109/CVPR.2017.243.

Lin, M., Chen, Q., & Yan, S. (2013). Network In Network. CoRR, abs/1312.4400 doi:10.48550/arXiv.1312.4400.

S. Sanei and J. A. Chambers, EEG Signal Processing. Chichester, U.K.: John Wiley & Sons, 2007.

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.

L. S. Shapley, "A value for n-person games," in Contributions to the Theory of Games, Vol. II, A. W. Tucker and R. L. Luce, Eds. Princeton, NJ, USA: Princeton Univ. Press, 1953, pp. 307-317.

I. Šimić, E. Veas, and V. Sabol, "A comprehensive analysis of perturbation methods in explainable AI feature attribution validation for neural time series classifiers,"Scientific Reports, vol. 15, Art. no. 26607, 2025 doi: 10.1038/s41598-025-09538-2, .

Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S. I. (2020). From Local Explanations to Global Understanding with Explainable AI for Trees. Nature machine intelligence, 2(1),56-67. doi:10.1038/s42256-019-0138-9

E. Niedermeyer and F. L. da Silva, Electroencephalography: Basic Principles, Clinical Applications, and Related Fields, 5th ed. Philadelphia, PA, USA: Lippincott Williams & Wilkins, 2005.