REVIEW ARTICLE
THE USE OF ARTIFICIAL INTELLIGENCE IN EPILEPSY DIAGNOSIS –
AN OVERVIEW OF CONTEMPORARY TOOLS
1
Student Scientific Association of Neurology, Wroclaw Medical University, Wroclaw, Poland
2
Department of Neurology, University Center of Neurology and Neurosurgery,
Wroclaw Medical University, Wroclaw, Poland
Submission date: 2025-11-30
Final revision date: 2025-12-27
Acceptance date: 2026-01-02
Publication date: 2026-01-16
Corresponding author
Julia Naskrent
Student Scientific Association of Neurology, Wroclaw Medical University, Ludwik Pasteur Embankment No 1, 50-367, Wroclaw, Poland
Student Scientific Association of Neurology, Wroclaw Medical University, Ludwik Pasteur Embankment No 1, 50-367, Wroclaw, Poland
Issue Rehabil. Orthop. Neurophysiol. Sport Promot. 2025;52(3):11-20
KEYWORDS
TOPICS
ABSTRACT
Introduction:
Epilepsy is a common neurological disorder in which diagnostic accuracy is often limited by subtle or magnetic resonance imaging (MRI)-negative abnormalities as well as non-specific electroencephalography (EEG) findings. Conventional interpretation of imaging and EEG is time-consuming and depends on experience. Recent advances in artificial intelligence (AI) offer new opportunities for automating and improving the detection, classification and rediction of epileptic activity. This review aimed to summarise recent evidence on AI-based diagnostic applications in epilepsy.
Material and Methods:
A PubMed search (2015–2025) identified almost 50 studies meeting predefined quality and relevance criteria. Included works examined AI models applied to MRI/functional MRI, EEG analysis, seizure detection and prediction, and multimodal diagnostic systems.
Results:
AI significantly improves detection of subtle MRI abnormalities, including hippocampal sclerosis and focal cortical dysplasia, with performance often exceeding expert radiologists. Multimodal approaches combining EEG with MRI/resting state MRI show high accuracy in seizure-onset localization. Deep-learning systems – including convolutional neural networks (CNN), long short-term memory, combined models and transformer-enhanced architectures – achieve sensitivity and specificity above 90% in seizure detection and short-term prediction, with continuous wavelet transform-based CNN models reporting > 95% accuracy.
Conclusions:
AI enhances diagnostic precision, reduces review time, and assists in seizure classification and localization. Ongoing advances suggest that AI will soon play a meaningful role in routine epilepsy diagnostics and clinical decision-support.
Epilepsy is a common neurological disorder in which diagnostic accuracy is often limited by subtle or magnetic resonance imaging (MRI)-negative abnormalities as well as non-specific electroencephalography (EEG) findings. Conventional interpretation of imaging and EEG is time-consuming and depends on experience. Recent advances in artificial intelligence (AI) offer new opportunities for automating and improving the detection, classification and rediction of epileptic activity. This review aimed to summarise recent evidence on AI-based diagnostic applications in epilepsy.
Material and Methods:
A PubMed search (2015–2025) identified almost 50 studies meeting predefined quality and relevance criteria. Included works examined AI models applied to MRI/functional MRI, EEG analysis, seizure detection and prediction, and multimodal diagnostic systems.
Results:
AI significantly improves detection of subtle MRI abnormalities, including hippocampal sclerosis and focal cortical dysplasia, with performance often exceeding expert radiologists. Multimodal approaches combining EEG with MRI/resting state MRI show high accuracy in seizure-onset localization. Deep-learning systems – including convolutional neural networks (CNN), long short-term memory, combined models and transformer-enhanced architectures – achieve sensitivity and specificity above 90% in seizure detection and short-term prediction, with continuous wavelet transform-based CNN models reporting > 95% accuracy.
Conclusions:
AI enhances diagnostic precision, reduces review time, and assists in seizure classification and localization. Ongoing advances suggest that AI will soon play a meaningful role in routine epilepsy diagnostics and clinical decision-support.
REFERENCES (49)
1.
Muhlhofer W, Tan YL, Mueller SG, Knowlton R. MRI-negative temporal lobe epilepsy – what do we know? Epilepsia 2017; 58: 727–742.
2.
Ito Y, Fukuda M, Matsuzawa H, et al. Deep learning-based diagnosis of temporal lobe epi¬lepsy associated with hippocampal sclerosis: an MRI study. Epilepsy Res 2021; 178: 106815. DOI: 10.1016/j.eplepsyres.2021.106815.
3.
Kim D, Lee J, Moon J, Moon T. Interpretable deep learning-based hippocampal sclerosis classification. Epilepsia Open 2022; 7: 747–757.
4.
Sone D. Neurobiological mechanisms of psy¬chosis in epilepsy: findings from neuroimaging studies. Front Psychiatry 2022; 13: 1079295. DOI: 10.3389/fpsyt.2022.1079295.
5.
Jiang Y, Li W, Li J, et al. Identification of four biotypes in temporal lobe epilepsy via machine learning on brain images. Nat Commun 2024; 15: 2221. DOI: 10.1038/s41467-024-46629-6.
6.
Middlebrooks EH, Gupta V, Agarwal AK, et al. Radiologic classification of hippocampal sclero¬sis in epilepsy. AJNR Am J Neuroradiol 2024; 45: 1185–1193.
7.
Belke M, Zahnert F, Steinbrenner M, et al. Au¬tomatic detection of hippocampal sclerosis in patients with epilepsy. Epilepsia 2025; 66: 3852– 3864.
8.
Ripart M, DeKraker J, Eriksson MH, et al. Auto¬mated and interpretable detection of hippocam¬pal sclerosis in temporal lobe epilepsy: AID-HS. Ann Neurol 2024; 97: 62–75.
9.
Lucas A, Revell A, Davis KA. Artificial intelli¬gence in epilepsy – applications and pathways to the clinic. Nat Rev Neurol 2024; 20: 319–336.
10.
Osipowicz K, Sperling MR, Sharan AD, Tracy JI. Functional MRI, resting state fMRI, and DTI for predicting verbal fluency outcome following resective surgery for temporal lobe epilepsy. J Neurosurg 2016; 124: 929–937.
11.
Baumgartner C, Koren JP, Rothmayer M. Auto¬matic computer-based detection of epileptic sei¬zures. Front Neurol 2018; 9: 639. DOI: 10.3389/ fneur.2018.00639.
12.
Hosseini MP, Tran TX, Pompili D, Elisevich K, Soltanian-Zadeh H. Multimodal data analysis of epileptic EEG and rs-fMRI via deep learning and edge computing. Artif Intell Med 2020; 104: 101813. DOI: 10.016/j.artmed.2020.101813.
13.
Jehi L. Machine learning for precision epilepsy surgery. Epilepsy Curr 2023; 23: 78–83.
14.
Mridha MF, Das SC, Kabir MM, Lima AA, Islam MR, Watanobe Y. Brain–computer interface: advancement and challenges. Sensors (Basel) 2021; 21: 5746. DOI: 10.3390/s21175746.
15.
Kuswanto H, Salamah M, Fachruddin MI. Random forest classification and support vec¬tor machine for detecting epilepsy using electroencephalograph records. Am J Appl Sci 2017; 14: 533–539.
16.
Mallick S, Baths V. Novel deep learning frame¬work for detection of epileptic seizures using EEG signals. Front Comput Neurosci 2024; 18: 1340251. DOI: 10.3389/fncom.2024. 1340251.
17.
Al-Marzouki S. Advancing epileptic seizure recognition through bidirectional LSTM net¬works. Front Comput Neurosci 2025; 19: 1668358. DOI:10.3389/fncom.2025.1668358.
18.
Torkey H, Hashish S, Souissi S, Hemdan EE, Sayed A. Seizure detection in medical IoT: hybrid CNN-LSTM-GRU model with data balancing and XAI integration. Algorithms 2025; 18: 77. DOI: 10.3390/a18020077.
19.
Hassan F, Hussain SF, Qaisar SM. Epileptic seizure detection using a hybrid 1D CNN-machine learning approach from EEG data. J Healthc Eng 2022; 2022: 9579422. DOI: 10.1155/2022/9579422.
20.
Zhao W, Wang WF, Patnaik LM, et al. Residual and bidirectional LSTM for epileptic seizure detection. Front Comput Neurosci 2024; 18: 1415967. DOI: 10.3389/fncom.2024.1415967.
21.
Alarfaj M, Zeb MA, Al-Adhaileh MH, Alha- madi AA, Ebrahim N. Deep learning approaches for diagnosing seizure based on EEG signal analysis. Front Hum Neurosci 2025; 19: 1669919. DOI: 10.3389/fnhum.2025.1669919.
22.
Duma GM, Cuozzo S, Danieli A, et al. Dynamic excitation/inhibition balance preceding seizure onset and its link to functional and structural brain architecture. BMC Med 2025; 23: 604. DOI: 10.1186/s12916-025-04447-7.
23.
Abbasi B, Goldenholz DM. Machine learning applications in epilepsy. Epilepsia 2019; 60: 2037–2047.
24.
Sone D, Beheshti I. Clinical application of ma¬chine learning models for brain imaging in epilepsy: a review. Front Neurosci 2021; 15. DOI: 10.3389/fnins.2021.684825.
25.
Hossain MS, Amin SU, Alsulaiman M, Muham¬mad G. Applying deep learning for epilepsy sei¬zure detection and brain mapping visualization. ACM Trans Multimedia Comput Commun Appl 2019; 15: 1–17.
26.
Shoeibi A, Khodatars M, Ghassemi N, et al. Epileptic seizures detection using deep learn¬ing techniques: a review. Int J Environ Res Public Health 2021; 18: 5780. DOI: 10.3390/ ijerph18115780.
27.
Grossmann A, Kronland-Martinet R, Morlet J. Reading and understanding continuous wave¬let transforms. In: Combes JM, Grossmann A, Tchamitchian P, eds. Wavelets: Inverse Problems and Theoretical Imaging. Berlin, Heidelberg: Springer; 1990.
28.
Dişli F, Gedikpınar M, Fırat H, Şengür A, Güldemir H, Koundal D. Epilepsy diagnosis from EEG signals using continuous wavelet transform-based depthwise convolutional neu¬ral network model. Diagnostics (Basel) 2025; 15: 84. DOI: 10.3390/diagnostics15010084.
29.
Kuang Z, Guo L, Wang J, Zhao J, Wang L, Geng K. Seizure onset zone detection based on convolutional neural networks and EEG signals. Brain Sci 2024; 14: 1090. DOI: 10.3390/brainsci14111090.
30.
Liu S, Wang J, Li S, Cai L. Multi-dimensional hybrid bilinear CNN-LSTM models for epi¬leptic seizure detection and prediction using EEG signals. J Neural Eng 2024; 21: 066045. DOI:10.1088/1741-2552/ada0e5.
31.
Cao X, Zhang J, Chen W, Du G. A hybrid CNN-Bi-LSTM model with feature fusion for accurate epilepsy seizure detection. BMC Med Inform Decis Mak 2025; 25: 6. DOI:10.1186/s12911-024-02845-0.
32.
Li C, Li H, Dong X, et al. CNN-Informer: a hy¬brid deep learning model for seizure de¬tection on long-term EEG. Neural Netw 2025; 181: 106855. DOI: 10.1016/j.neunet.2024.106855.
33.
Lemoine É, Toffa D, Xu AQ, et al. Improving di¬agnostic accuracy of routine EEG for epilepsy using deep learning. Brain Commun 2025; 7: fcaf319. DOI: 10.1093/braincomms/fcaf319.
34.
Yang H, Piao Y, Wang G, Zhao H, Shen X. LFSP-DSM: a lightweight framework for seizure prediction based on deep statistical model. Ann N Y Acad Sci 2025; 1552: 428–442. DOI: 10.1111/ nyas.70050.
35.
Zhang T, Chen J, Polat K. Enhanced epileptic seizure detection using CNNs with convolutional block attention and short-term memory net¬works. Behav Brain Res 2026; 496: 115831. DOI: 10.1016/j.bbr.2025.115831.
36.
Alkhrijah Y, Khalid S, Usman SM, et al. Feature fusion ensemble classification ap¬proach for epileptic seizure prediction using electroencephalographic bio-signals. Front Med 2025; 12. DOI: 10.3389/fmed.2025.1566870.
37.
Tara K, Wang R, Matsuda Y, Goto S, Mitsudo T, Yamasaki T, Sugi T. EEG-based cerebral pattern analysis for neurological disorder detection via hybrid machine and deep learning approaches. J Neurosci Methods 2025; 423: 110551. DOI: 10.1016/j.jneumeth.2025.110551.
38.
Afzal MF, Desai SA, Barry W, et al. AI-driven electrographic seizure classification and sei¬zure onset detection using image- and time-series-based approaches. IEEE Trans Biomed Eng 2025; PP. Online ahead of print. DOI: 10.1109/TBME.2025.3594592.
39.
Zhang F, Zhang X. Prediction of epilepsy seizure based on cepstrum analysis and deep learning. Interdiscip Sci 2025; 17: 906–916.
40.
Kaur T, Diwakar A, Kirandeep M, et al. Artificial intelligence in epilepsy. Neurol India 2021; 69: 560–566.
41.
Kashefi Amiri H, Zarei M, Daliri MR. Epileptic seizure detection from electroencephalogram sig¬nals based on 1D CNN-LSTM deep learning model using discrete wavelet transform. Sci Rep 2025; 15: 32820. DOI: 10.1038/s41598-025-18479-9.
42.
Konomatsu K, Kashiwada Y, Kubota T, et al. Dif¬ferentiation between epileptic and functional/ dissociative seizures using density spectral array of ictal single-channel EEG with deep learning. Epilepsy Behav 2025; 172: 110713. DOI: 10.1016/ j.yebeh.2025.110713.
43.
Zhang S, Zhuang Y, Luo Y, Zhu F, Zhao W, Zeng H. Deep learning-based automated lesion segmen¬tation on pediatric focal cortical dysplasia II preoperative MRI: a reliable approach. Insights Imaging 2024; 15: 71. DOI: 10.1186/s13244-024- 01635-6.
44.
Gill RS, Lee HM, Caldairou B, et al. Multi¬center validation of a deep learning detection algorithm for focal cortical dysplasia. Neu¬rology 2021; 97: e1571–e1582. DOI: 10.1212/ WNL.0000000000012698.
45.
Arnold TC, Muthukrishnan R, Pattnaik AR, et al. Deep learning-based automated segmenta¬tion of resection cavities on postsurgical epilepsy MRI. Neuroimage Clin 2022; 36: 103154. DOI: 10.1016/j.nicl.2022.103154.
46.
Spitzer H, Ripart M, Whitaker K, et al. Interpret¬able surface-based detection of focal cortical dysplasias: a multi-centre epilepsy lesion detec¬tion study. Brain 2022; 145: 3859–3871.
47.
Zhang Q, Liao Y, Wang X, et al. A deep learning framework for 18F-FDG PET imaging diag¬nosis in pediatric patients with temporal lobe epilepsy. Eur J Nucl Med Mol Imaging 2021; 48: 2476–2485.
48.
Shih YC, Lee TH, Yu HY, Chou CC, Lee CC, Lin PT, Peng SJ. Machine learning quantitative analysis of FDG PET images of medial temporal lobe epi¬lepsy patients. Clin Nucl Med 2022; 47: 287–293.
49.
Park S, Clark JS, Viana PF, et al. Seizure detection using ultra-long-term subcutane¬ous electroencephalography: a deep learning CNN-BiLSTM approach. Epilepsia 2025. Online ahead of print. DOI: 10.1111/epi.18652.
| ISSN: | 2300-0767 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
