Increased coherence predicts medical refractoriness in patients with temporal lobe epilepsy on monotherapy.
Electroencephalography
Machine learning
Optimized feature selection
Prediction
Refractory epilepsy
Temporal lobe epilepsy
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
04 09 2024
04 09 2024
Historique:
received:
03
07
2024
accepted:
29
08
2024
medline:
4
9
2024
pubmed:
4
9
2024
entrez:
3
9
2024
Statut:
epublish
Résumé
Among patients with epilepsy, 30-40% experience recurrent seizures even after adequate antiseizure medications therapies, making them refractory. The early identification of refractory epilepsy is important to provide timely surgical treatment for these patients. In this study, we analyze interictal electroencephalography (EEG) data to predict drug refractoriness in patients with temporal lobe epilepsy (TLE) who were treated with monotherapy at the time of the first EEG acquisition. Various EEG features were extracted, including statistical measurements and interchannel coherence. Feature selection was performed to identify the optimal features, and classification was conducted using different classifiers. Functional connectivity and graph theory measurements were calculated to identify characteristics of refractory TLE. Among the 48 participants, 34 (70.8%) were responsive, while 14 (29.2%) were refractory over a mean follow-up duration of 38.5 months. Coherence feature within the gamma frequency band exhibited the most favorable performance. The light gradient boosting model, employing the mutual information filter-based feature selection method, demonstrated the highest performance (AUROC = 0.821). Compared to the responsive group, interchannel coherence displayed higher values in the refractory group. Interestingly, graph theory measurements using EEG coherence exhibited higher values in the refractory group than in the responsive group. Our study has demonstrated a promising method for the early identification of refractory TLE utilizing machine learning algorithms.
Identifiants
pubmed: 39227730
doi: 10.1038/s41598-024-71583-0
pii: 10.1038/s41598-024-71583-0
doi:
Substances chimiques
Anticonvulsants
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
20530Subventions
Organisme : Korea Health Industry Development Institute
ID : RS-2023-00265638
Informations de copyright
© 2024. The Author(s).
Références
Fisher, R. S. et al. Instruction manual for the ILAE 2017 operational classification of seizure types. Epilepsia 58, 531–542. https://doi.org/10.1111/epi.13671 (2017).
doi: 10.1111/epi.13671
pubmed: 28276064
Chen, Z., Brodie, M. J., Liew, D. & Kwan, P. Treatment outcomes in patients with newly diagnosed epilepsy treated with established and new antiepileptic drugs: A 30-year longitudinal cohort study. JAMA Neurol. 75, 279–286. https://doi.org/10.1001/jamaneurol.2017.3949 (2018).
doi: 10.1001/jamaneurol.2017.3949
pubmed: 29279892
Kwan, P. et al. Definition of drug resistant epilepsy: Consensus proposal by the ad hoc Task Force of the ILAE Commission on therapeutic strategies. Epilepsia 51, 1069–1077. https://doi.org/10.1111/j.1528-1167.2009.02397.x (2010).
doi: 10.1111/j.1528-1167.2009.02397.x
pubmed: 19889013
Brodie, M. J. & Sills, G. J. Combining antiepileptic drugs—Rational polytherapy? Seizure 20, 369–375. https://doi.org/10.1016/j.seizure.2011.01.004 (2011).
doi: 10.1016/j.seizure.2011.01.004
pubmed: 21306922
Simasathien, T. et al. Improved outcomes with earlier surgery for intractable frontal lobe epilepsy. Ann. Neurol. 73, 646–654. https://doi.org/10.1002/ana.23862 (2013).
doi: 10.1002/ana.23862
pubmed: 23494550
Kwan, P. & Brodie, M. J. Epilepsy after the first drug fails: Substitution or add-on? Seizure 9, 464–468. https://doi.org/10.1053/seiz.2000.0442 (2000).
doi: 10.1053/seiz.2000.0442
pubmed: 11034869
Yao, L. et al. Prediction of antiepileptic drug treatment outcomes of patients with newly diagnosed epilepsy by machine learning. Epilepsy Behav. 96, 92–97. https://doi.org/10.1016/j.yebeh.2019.04.006 (2019).
doi: 10.1016/j.yebeh.2019.04.006
pubmed: 31121513
An, S. et al. Predicting drug-resistant epilepsy—A machine learning approach based on administrative claims data. Epilepsy Behav. 89, 118–125. https://doi.org/10.1016/j.yebeh.2018.10.013 (2018).
doi: 10.1016/j.yebeh.2018.10.013
pubmed: 30412924
pmcid: 6461470
Elger, C. E. & Hoppe, C. Diagnostic challenges in epilepsy: Seizure under-reporting and seizure detection. Lancet Neurol. 17, 279–288. https://doi.org/10.1016/s1474-4422(18)30038-3 (2018).
doi: 10.1016/s1474-4422(18)30038-3
pubmed: 29452687
Kwan, P. & Brodie, M. J. Early identification of refractory epilepsy. N. Engl. J. Med. 342, 314–319. https://doi.org/10.1056/nejm200002033420503 (2000).
doi: 10.1056/nejm200002033420503
pubmed: 10660394
Xue-Ping, W., Hai-Jiao, W., Li-Na, Z., Xu, D. & Ling, L. Risk factors for drug-resistant epilepsy: A systematic review and meta-analysis. Medicine 98, e16402. https://doi.org/10.1097/md.0000000000016402 (2019).
doi: 10.1097/md.0000000000016402
pubmed: 31348240
pmcid: 6708813
Aaberg, K. M. et al. Short-term seizure outcomes in childhood epilepsy. Pediatrics 141, 16. https://doi.org/10.1542/peds.2017-4016 (2018).
doi: 10.1542/peds.2017-4016
Berg, A. T. et al. Early development of intractable epilepsy in children: A prospective study. Neurology 56, 1445–1452. https://doi.org/10.1212/wnl.56.11.1445 (2001).
doi: 10.1212/wnl.56.11.1445
pubmed: 11402099
Ko, T. S. & Holmes, G. L. EEG and clinical predictors of medically intractable childhood epilepsy. Clin. Neurophysiol. 110, 1245–1251. https://doi.org/10.1016/s1388-2457(99)00068-1 (1999).
doi: 10.1016/s1388-2457(99)00068-1
pubmed: 10423189
Peng, G., Nourani, M., Harvey, J. & Dave, H. Personalized EEG feature selection for low-complexity seizure monitoring. Int. J. Neural Syst. 31, 2150018. https://doi.org/10.1142/s0129065721500180 (2021).
doi: 10.1142/s0129065721500180
pubmed: 33752579
Hakeem, H. et al. Development and validation of a deep learning model for predicting treatment response in patients with newly diagnosed epilepsy. JAMA Neurol. https://doi.org/10.1001/jamaneurol.2022.2514 (2022).
doi: 10.1001/jamaneurol.2022.2514
pubmed: 36036923
pmcid: 9425285
Grigsby, J., Kramer, R. E., Schneiders, J. L., Gates, J. R. & Brewster Smith, W. Predicting outcome of anterior temporal lobectomy using simulated neural networks. Epilepsia 39, 61–66. https://doi.org/10.1111/j.1528-1157.1998.tb01275.x (1998).
doi: 10.1111/j.1528-1157.1998.tb01275.x
pubmed: 9578014
Armañanzas, R. et al. Machine learning approach for the outcome prediction of temporal lobe epilepsy surgery. PLoS ONE 8, e62819. https://doi.org/10.1371/journal.pone.0062819 (2013).
doi: 10.1371/journal.pone.0062819
pubmed: 23646148
pmcid: 3640010
Zhang, J. H. et al. Personalized prediction model for seizure-free epilepsy with levetiracetam therapy: A retrospective data analysis using support vector machine. Br. J. Clin. Pharmacol. 84, 2615–2624. https://doi.org/10.1111/bcp.13720 (2018).
doi: 10.1111/bcp.13720
pubmed: 30043454
pmcid: 6177722
Croce, P. et al. Machine learning for predicting levetiracetam treatment response in temporal lobe epilepsy. Clin. Neurophysiol. 132, 3035–3042. https://doi.org/10.1016/j.clinph.2021.08.024 (2021).
doi: 10.1016/j.clinph.2021.08.024
pubmed: 34717224
Lin, L. C. et al. Early prediction of medication refractoriness in children with idiopathic epilepsy based on scalp EEG analysis. Int. J. Neural Syst. 24, 1450023. https://doi.org/10.1142/s0129065714500233 (2014).
doi: 10.1142/s0129065714500233
pubmed: 25164248
Wang, B. et al. An integrative prediction algorithm of drug-refractory epilepsy based on combined clinical-EEG functional connectivity features. J. Neurol. 269, 1501–1514. https://doi.org/10.1007/s00415-021-10718-z (2022).
doi: 10.1007/s00415-021-10718-z
pubmed: 34308506
Matos, J. et al. Diagnosis of epilepsy with functional connectivity in EEG after a suspected first seizure. Bioengineering 9, 690. https://doi.org/10.3390/bioengineering9110690 (2022).
doi: 10.3390/bioengineering9110690
pubmed: 36421091
pmcid: 9687589
Jiruska, P. et al. High-frequency network activity, global increase in neuronal activity, and synchrony expansion precede epileptic seizures in vitro. J. Neurosci. 30, 5690–5701. https://doi.org/10.1523/jneurosci.0535-10.2010 (2010).
doi: 10.1523/jneurosci.0535-10.2010
pubmed: 20410121
pmcid: 6632330
Engel, J. Jr., Bragin, A., Staba, R. & Mody, I. High-frequency oscillations: What is normal and what is not? Epilepsia 50, 598–604. https://doi.org/10.1111/j.1528-1167.2008.01917.x (2009).
doi: 10.1111/j.1528-1167.2008.01917.x
pubmed: 19055491
Fisher, R. S., Webber, W. R., Lesser, R. P., Arroyo, S. & Uematsu, S. High-frequency EEG activity at the start of seizures. J. Clin. Neurophysiol. 9, 441–448. https://doi.org/10.1097/00004691-199207010-00012 (1992).
doi: 10.1097/00004691-199207010-00012
pubmed: 1517412
Pereda, E., Quiroga, R. Q. & Bhattacharya, J. Nonlinear multivariate analysis of neurophysiological signals. Prog. Neurobiol. 77, 1–37. https://doi.org/10.1016/j.pneurobio.2005.10.003 (2005).
doi: 10.1016/j.pneurobio.2005.10.003
pubmed: 16289760
Horstmann, M. T. et al. State dependent properties of epileptic brain networks: Comparative graph-theoretical analyses of simultaneously recorded EEG and MEG. Clin. Neurophysiol. 121, 172–185. https://doi.org/10.1016/j.clinph.2009.10.013 (2010).
doi: 10.1016/j.clinph.2009.10.013
pubmed: 20045375
van Diessen, E., Otte, W. M., Braun, K. P., Stam, C. J. & Jansen, F. E. Improved diagnosis in children with partial epilepsy using a multivariable prediction model based on EEG network characteristics. PLoS ONE 8, e59764. https://doi.org/10.1371/journal.pone.0059764 (2013).
doi: 10.1371/journal.pone.0059764
pubmed: 23565166
pmcid: 3614973
Lee, H. J. & Park, K. M. Intrinsic hippocampal and thalamic networks in temporal lobe epilepsy with hippocampal sclerosis according to drug response. Seizure 76, 32–38. https://doi.org/10.1016/j.seizure.2020.01.010 (2020).
doi: 10.1016/j.seizure.2020.01.010
pubmed: 31986443
Shin, Y. et al. Using spectral and temporal filters with EEG signal to predict the temporal lobe epilepsy outcome after antiseizure medication via machine learning. Sci. Rep. 13, 22532. https://doi.org/10.1038/s41598-023-49255-2 (2023).
doi: 10.1038/s41598-023-49255-2
pubmed: 38110465
pmcid: 10728218
Päivinen, N. et al. Epileptic seizure detection: A nonlinear viewpoint. Comput. Methods Progr. Biomed. 79, 151–159. https://doi.org/10.1016/j.cmpb.2005.04.006 (2005).
doi: 10.1016/j.cmpb.2005.04.006
Tanveer, M., Pachori, R. B. & Angami, N. V. Classification of seizure and seizure-free EEG signals using Hjorth parameters. In 2018 IEEE Symposium Series on Computational Intelligence (SSCI) 2180–2185 (2018).
Gemein, L. A. W. et al. Machine-learning-based diagnostics of EEG pathology. Neuroimage 220, 117021. https://doi.org/10.1016/j.neuroimage.2020.117021 (2020).
doi: 10.1016/j.neuroimage.2020.117021
pubmed: 32534126
Lanzone, J. et al. The effect of Perampanel on EEG spectral power and connectivity in patients with focal epilepsy. Clin. Neurophysiol. 132, 2176–2183. https://doi.org/10.1016/j.clinph.2021.05.026 (2021).
doi: 10.1016/j.clinph.2021.05.026
pubmed: 34284253
Ricci, L. et al. Measuring the effects of first antiepileptic medication in temporal lobe epilepsy: Predictive value of quantitative-EEG analysis. Clin. Neurophysiol. 132, 25–35. https://doi.org/10.1016/j.clinph.2020.10.020 (2021).
doi: 10.1016/j.clinph.2020.10.020
pubmed: 33248432
Pyrzowski, J. et al. Zero-crossing patterns reveal subtle epileptiform discharges in the scalp EEG. Sci. Rep. 11, 4128. https://doi.org/10.1038/s41598-021-83337-3 (2021).
doi: 10.1038/s41598-021-83337-3
pubmed: 33602954
pmcid: 7892826
ShahidiZandi, A., Tafreshi, R., Javidan, M. & Dumont, G. A. Predicting temporal lobe epileptic seizures based on zero-crossing interval analysis in scalp EEG. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. 2010, 5537–5540. https://doi.org/10.1109/iembs.2010.5626764 (2010).
doi: 10.1109/iembs.2010.5626764
Morgan, V. L. et al. Magnetic resonance imaging connectivity for the prediction of seizure outcome in temporal lobe epilepsy. Epilepsia 58, 1251–1260. https://doi.org/10.1111/epi.13762 (2017).
doi: 10.1111/epi.13762
pubmed: 28448683
pmcid: 5498250
Antony, A. R. et al. Functional connectivity estimated from intracranial EEG predicts surgical outcome in intractable temporal lobe epilepsy. PLoS ONE 8, e77916. https://doi.org/10.1371/journal.pone.0077916 (2013).
doi: 10.1371/journal.pone.0077916
pubmed: 24205027
pmcid: 3813548
Peng, G., Nourani, M., Dave, H. & Harvey, J. SEEG-based epileptic seizure network modeling and analysis for pre-surgery evaluation. Comput. Biol. Med. 167, 107692. https://doi.org/10.1016/j.compbiomed.2023.107692 (2023).
doi: 10.1016/j.compbiomed.2023.107692
pubmed: 37976827
van Mierlo, P. et al. Functional brain connectivity from EEG in epilepsy: Seizure prediction and epileptogenic focus localization. Prog. Neurobiol. 121, 19–35. https://doi.org/10.1016/j.pneurobio.2014.06.004 (2014).
doi: 10.1016/j.pneurobio.2014.06.004
pubmed: 25014528
Zaveri, H. P. et al. Localization-related epilepsy exhibits significant connectivity away from the seizure-onset area. Neuroreport 20, 891–895. https://doi.org/10.1097/WNR.0b013e32832c78e0 (2009).
doi: 10.1097/WNR.0b013e32832c78e0
pubmed: 19424095
Chandrashekar, G. & Sahin, F. A survey on feature selection methods. Comput. Electr. Eng. 40, 16–28. https://doi.org/10.1016/j.compeleceng.2013.11.024 (2014).
doi: 10.1016/j.compeleceng.2013.11.024
Guyon, I., Weston, J., Barnhill, S. & Vapnik, V. Gene selection for cancer classification using support vector machines. Mach. Learn. 46, 389–422. https://doi.org/10.1023/A:1012487302797 (2002).
doi: 10.1023/A:1012487302797
Breiman, L. Random Forests. Mach. Learn. 45, 5–32. https://doi.org/10.1023/A:1010933404324 (2001).
doi: 10.1023/A:1010933404324
Chen, T. & Guestrin, C. XGBoost: A scalable tree boosting system. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016).
Ke, G. et al. Neural Information Processing Systems.
Lundberg, S. M. & Lee, S.-I. Neural Information Processing Systems.
Hagberg, A., Swart, P. & Chult, D. Exploring Network Structure, Dynamics, and Function Using NetworkX (Los Alamos National Lab, 2008).
doi: 10.25080/TCWV9851
Abraham, A. et al. Machine learning for neuroimaging with scikit-learn. Front. Neuroinform. 8, 14. https://doi.org/10.3389/fninf.2014.00014 (2014).
doi: 10.3389/fninf.2014.00014
pubmed: 24600388
pmcid: 3930868