Utilizing machine learning techniques for EEG assessment in the diagnosis of epileptic seizures in the brain: A systematic review and meta-analysis

被引：0

作者：

Chawla, Dikshit ^{[1
]}

Sharma, Eshita ^{[2
]}

Rajab, Numa ^{[3
]}

Lajczak, Pawel ^{[4
]}

Silva, Yasmin P. ^{[5
]}

Baptista, Joao Marcelo ^{[6
]}

Pomianoski, Beatriz W. ^{[7
]}

Ahmed, Aisha R. ^{[8
]}

Majeed, Mir wajid ^{[9
]}

de Sousa, Yan G. ^{[10
]}

Pinto, Manoela L. ^{[11
]}

Sahin, Oguz K. ^{[12
]}

Ibrahim, Muhaison H. ^{[13
]}

Guedes, Idrys H. L. ^{[14
]}

Chatterjee, Anoushka ^{[5
]}

Barbosa, Ramon Guerra ^{[15
]}

Fagundes, Walter ^{[16
]}

机构：

[1] Govt Med Coll Patiala, Patiala, India

[2] UCLA, David Geffen Sch Med, Los Angeles, CA USA

[3] Sulaiman AlRajhi Univ, Al Bukayriyah, Saudi Arabia

[4] Med Univ Silesia, Katowice, Poland

[5] Univ Debrecen, Fac Med, Debrecen, Hungary

[6] Univ Estadual Maringa, Dept Med, Maringa, Parana, Brazil

[7] Univ Nove Julho, Sao Paulo, Brazil

[8] Jinnah Med & Dent Coll, Karachi, Pakistan

[9] Govt Med Coll Srinagar, Srinagar, India

[10] State Univ Ceara UECE, Fortaleza, Ceara, Brazil

[11] Fed Univ Hlth Sci Porto Alegre, Porto Alegre, Brazil

[12] Acibadem Mehmet Ali Aydinlar Univ, Sch Med, Istanbul, Turkiye

[13] Univ Wisconsin, Sch Med & Publ Hlth, Madison, WI USA

[14] Univ Fed Campina Grande, Campina Grande, Paraiba, Brazil

[15] Clin Medular, Dept Neurosurg, Montes Claros, Brazil

[16] Univ Fed Espirito Santo, Dept Dent, Vitoria, Brazil

来源：

SEIZURE-EUROPEAN JOURNAL OF EPILEPSY | 2025年 / 126卷

关键词：

Electroencephalogram; Epilepsy; Machine-learning; Deep neural network; Seizures;

D O I：

10.1016/j.seizure.2025.01.021

中图分类号：

R74 [神经病学与精神病学];

学科分类号：

摘要：

Purpose: Advancements in Machine Learning (ML) techniques have revolutionized diagnosing and monitoring epileptic seizures using Electroencephalogram (EEG) signals. This analysis aims to determine the effectiveness of ML techniques in recognizing patterns of epileptic seizures in the brain using EEG signals. Methods: We searched PubMed, Scopus, and Google Scholar for relevant RCTs, cohort studies, and case-control studies involving patients with prior epileptic seizures who underwent EEG analysis aided by ML techniques. Using the STATA software, we evaluated the accuracy of predicting epileptic seizures, measured using metrics such as Area under the curve (AUC), Sensitivity, and Specificity. Results: The random effects bivariate model of 4 studies with 214 patients revealed high diagnostic performance for ML techniques in detecting epileptic signals in EEGs. The estimated sensitivity was 0.97 (95 % CI: 0.92-0.99), indicating its ability to accurately detect the condition in 97 % of cases. Similarly, the estimated specificity was 0.99 (95 % CI: 0.98-0.99), demonstrating its ability to correctly identify the absence of the condition in 99 % of cases. There was also a high AUC (1.00, 95 % CI: 0.99-1.00), indicating ML techniques can distinguish epileptic seizures from no seizures in EEG signals 100 % of the time. These findings underscore the test's robust diagnostic utility in sensitivity and specificity. There was a significant between-study variability (heterogeneity) with a chisquare p-value <0.001 and an I2 value of 95 %. A bivariate box plot further confirmed the heterogeneity. Deek's test for publication bias showed a non-significant p-value (p = 0.06) indicating the absence of publication bias. Conclusion: ML techniques can potentially enhance diagnostic accuracy in epilepsy detection, offering valuable insights into developing advanced diagnostic tools for clinical practice.

引用

页码：16 / 23

页数：8

共 13 条

[1] World Health Organization
[2] Niedermeyer E., Et al., Intracranial pressure monitoring and decompressive craniectomy in pediatric severe traumatic brain injury, Childs Nerv Syst, 21, 7, pp. 536-543, (2005)
[3] Acharya S., Et al., Management of decompressive craniectomy in traumatic brain injury patients: a systematic review and meta-analysis, Surg Neurol Int, 4, pp. S223-S229, (2013)
[4] Zhang H., Zhou Q.Q., Chen H., Et al., The applied principles of EEG analysis methods in neuroscience and clinical neurology, Mil Med Res, 10, 1, (2023)
[5] Qian Y., Alhaskawi A., Dong Y., Ni J., Abdalbary S., Lu H., Transforming medicine: artificial intelligence integration in the peripheral nervous system, Front Neurol, 15, (2024)
[6] Li X., Liao Z., Liang Z., Wang S., Tang J., A review of machine learning methods for epileptic seizure detection using EEG signals, Brain Informatics, 7, 3, (2020)
[7] Ein Shoka A.A., Dessouky M.M., El-Sayed A., Hemdan E.E.D., EEG seizure detection: concepts, techniques, challenges, and future trends, Multimed Tools Appl, 4, pp. 1-31, (2023)
[8] E S.L., Frey L., Et al., Electroencephalography (EEG): an introductory text and atlas of normal and abnormal findings in adults, children, and infants, (2016)
[9] Thakor N.V., Handbook of neuroengineering, (2023)
[10] Wang X., Ling Y., Ling X., Et al., A particle swarm algorithm optimization-based SVM–KNN algorithm for epileptic EEG recognition, Int J Intell Syst, 37, 12, pp. 11233-11249, (2022)

← 1 2 →