Explainable AI for epileptic seizure detection in Internet of Medical Things^☆

Abstract

In the field of precision healthcare, where accurate decision-making is paramount, this study underscores the indispensability of eXplainable Artificial Intelligence (XAI) in the context of epilepsy management within the Internet of Medical Things (IoMT). The methodology entails meticulous preprocessing, involving the application of a band-pass filter and epoch segmentation to optimize the quality of Electroencephalograph (EEG) data. The subsequent extraction of statistical features facilitates the differentiation between seizure and non-seizure patterns. The classification phase integrates Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest classifiers. Notably, SVM attains an accuracy of 97.26%, excelling in the precision, recall, specificity, and F1 score for identifying seizures and non-seizure instances. Conversely, KNN achieves an accuracy of 72.69%, accompanied by certain trade-offs. The Random Forest classifier stands out with a remarkable accuracy of 99.89%, coupled with an exceptional precision (99.73%), recall (100%), specificity (99.80%), and F1 score (99.86%), surpassing both SVM and KNN performances. XAI techniques, namely Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanation (SHAP), enhance the system's transparency. This combination of machine learning and XAI not only improves the reliability and accuracy of the seizure detection system but also enhances trust and interpretability. Healthcare professionals can leverage the identified important features and their dependencies to gain deeper insights into the decision-making process, aiding in informed diagnosis and treatment decisions for patients with epilepsy.

Keywords

Epileptic seizure / Epilepsy / EEG / Explainable AI / Machine learning

CRediT authorship contribution statement

Faiq Ahmad Khan: Writing - review & editing, Writing - original draft, Validation, Methodology, Investigation, Formal analysis, Data curation, Conceptualization. Zainab Umar: Writing - review & editing, Supervision. Alireza Jolfaei: Writing - review & editing, Supervision. Muhammad Tariq: Writing - review & editing, Writing - original draft, Supervision, Methodology, Investigation.

Declaration of Competing Interest

We claim no conflict of interest.

References

[1] P.N. Banerjee, D. Filippi, W.A. Hauser, The descriptive epidemiology of epilepsy—a review, Epilepsy Res. 85 (1) (2009) 31-45.

[2] R.D. Thijs, R. Surges, T.J. O’Brien, J.W. Sander, Epilepsy in adults, Lancet 393 (10172) (2019) 689-701.

[3] A.T. Tzallas, M.G. Tsipouras, D.G. Tsalikakis, E.C. Karvounis, L. Astrakas, S. Konitsi-otis, M. Tzaphlidou, Automated epileptic seizure detection methods: a review study, in: Epilepsy-Histological, Electroencephalographic and Psychological Aspects, 2012, pp. 2027-2036.

[4] E. Trinka, P. Kwan, B. Lee, A. Dash, Epilepsy in Asia: disease burden, management barriers, and challenges, Epilepsia 60 (2019) 7-21.

[5] W. H. Organization, G. C. against Epilepsy, P. for Neurological Diseases, N. W. H. Or-ganization), I. B. for Epilepsy, W. H. O. D. of Mental Health, S. Abuse, I. B. of Epilepsy, I. L. against Epilepsy, Atlas: epilepsy care in the world, World Health Organization, 2005.

[6] M. Teplan, et al., Fundamentals of EEG measurement, Meas. Sci. Rev. 2 (2) (2002) 1-11.

[7] S. Sanei, J.A. Chambers, EEG Signal Processing, John Wiley & Sons, 2013.

[8] J. Askamp, M.J. van Putten, Mobile EEG in epilepsy, Int. J. Psychophysiol. 91 (1) (2014) 30-35.

[9] S. Noachtar, J. Rémi, The role of EEG in epilepsy: a critical review, Epilepsy Behav. 15 (1) (2009) 22-33.

[10] P. Van Mierlo, M. Papadopoulou, E. Carrette, P. Boon, S. Vandenberghe, K. Vonck, D. Marinazzo, Functional brain connectivity from EEG in epilepsy: seizure prediction and epileptogenic focus localization, Prog. Neurobiol. 121 (2014) 19-35.

[11] J.S. Duncan, Antiepileptic drugs and the electroencephalogram, Epilepsia 28 (3) (1987) 259-266.

[12] L. Ricci, G. Assenza, P. Pulitano, V. Simonelli, L. Vollero, J. Lanzone, O. Mecarelli, V. Di Lazzaro, M. Tombini, Measuring the effects of first antiepileptic medication in temporal lobe epilepsy: predictive value of quantitative-EEG analysis, Clin. Neuro-physiol. 132 (1) (2021) 25-35.

[13] A.B. Arrieta, N. Díaz-Rodríguez, J. Del Ser, A. Bennetot, S. Tabik, A. Barbado, S. Gar-cía, S. Gil-López, D. Molina, R. Benjamins, et al., Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible ai, Inf. Fusion 58 ( 2020) 82-115.

[14] D. Gunning, M. Stefik, J. Choi, T. Miller, S. Stumpf, G.-Z. Yang, XAI—explainable artificial intelligence, Sci. Robot. 4 (37) (2019) eaay7120.

[15] D. Gunning, D. Aha, Darpa’s explainable artificial intelligence (XAI) program, AI Mag. 40 (2) (2019) 44-58.

[16] H.W. Loh, C.P. Ooi, S. Seoni, P.D. Barua, F. Molinari, U.R. Acharya,Application of explainable artificial intelligence for healthcare: a systematic review of the last decade (2011-2022), Comput. Methods Programs Biomed. (2022) 107161.

[17] P. Rathod, S. Naik,Review on epilepsy detection with explainable artificial intelli-gence, in: 2022 10th International Conference on Emerging Trends in Engineering and Technology-Signal and Information Processing (ICETET-SIP-22), IEEE, 2022, pp. 1-6.

[18] A.K. Idrees, S.K. Idrees, R. Couturier, T. Ali-Yahiya, An edge-fog computing-enabled lossless EEG data compression with epileptic seizure detection in iomt networks, IEEE Int. Things J. 9 (15) (2022) 13327-13337.

[19] D.C. Nguyen, K.D. Nguyen, P.N. Pathirana,A mobile cloud based iomt framework for automated health assessment and management, in: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, 2019, pp. 6517-6520.

[20] Y. Li, Y. Liu, W.-G. Cui, Y.-Z. Guo, H. Huang, Z.-Y. Hu, Epileptic seizure detection in eeg signals using a unified temporal-spectral squeeze-and-excitation network, IEEE Trans. Neural Syst. Rehabil. Eng. 28 (4) (2020) 782-794.

[21] A. Pandey, S.K. Singh, S.S. Udmale, K. Shukla, Epileptic seizure classification us-ing battle royale search and rescue optimization-based deep LSTM, IEEE J. Biomed. Health Inform. 26 (11) (2022) 5494-5505.

[22] M. Savadkoohi, T. Oladunni, L. Thompson, A machine learning approach to epilep-tic seizure prediction using electroencephalogram (EEG) signal, Biocybern. Biomed. Eng. 40 (3) (2020) 1328-1341.

[23] K. Polat, M. Nour, Epileptic seizure detection based on new hybrid models with electroencephalogram signals, IRBM 41 (6) (2020) 331-353.

[24] X. Qiu, F. Yan, H. Liu, A difference attention resnet-lstm network for epileptic seizure detection using eeg signal, Biomed. Signal Process. Control 83 (2023) 104652.

[25] M. Varlı, H. Yılmaz, Multiple classification of EEG signals and epileptic seizure di-agnosis with combined deep learning, J. Comput. Sci. 67 (2023) 101943.

[26] A. Shoeibi, N. Ghassemi, M. Khodatars, P. Moridian, R. Alizadehsani, A. Zare, A. Khosravi, A. Subasi, U.R. Acharya, J.M. Gorriz, Detection of epileptic seizures on EEG signals using ANFIS classifier, autoencoders and fuzzy entropies, Biomed. Signal Process. Control 73 (2022) 103417.

[27] A.H. Shoeb,Application of machine learning to epileptic seizure onset detection and treatment, Ph.D. thesis, Massachusetts Institute of Technology, 2009.

[28] K. Pieper, R.P. Spang, P. Prietz, S. Möller, E. Paajanen, M. Vaalgamaa, J.-N. Voigt- Antons, Working with environmental noise and noise-cancelation: a workload as-sessment with EEG and subjective measures, Front. Neurosci. (2021) 1366.