A hybrid unsupervised and supervised learning approach for postictal generalized EEG suppression detection

被引:0
作者
Li, Xiaojin [1 ,2 ]
Huang, Yan [1 ,2 ]
Lhatoo, Samden D. D. [1 ,2 ]
Tao, Shiqiang [1 ,2 ]
Bertran, Laura Vilella [1 ,2 ]
Zhang, Guo-Qiang [1 ,2 ,3 ]
Cui, Licong [2 ,3 ]
机构
[1] Univ Texas Hlth Sci Ctr Houston, Dept Neurol, Houston, TX 77030 USA
[2] Univ Texas Hlth Sci Ctr Houston, Texas Inst Restorat Neurotechnol, Houston, TX 77030 USA
[3] Univ Texas Hlth Sci Ctr Houston, Sch Biomed Informat, Houston, TX 77030 USA
基金
美国国家卫生研究院;
关键词
epilepsy; generalized tonic-clonic seizure; postictal generalized EEG suppression; EEG; unsupervised learning; hybrid classifier; SUDDEN UNEXPECTED DEATH; EMPIRICAL MODE DECOMPOSITION; ELECTROPHYSIOLOGICAL BIOMARKERS; NEURAL-NETWORK; EPILEPSY; CLASSIFICATION; CHANNEL; IMMOBILITY; SIGNALS; RISK;
D O I
10.3389/fninf.2022.1040084
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Sudden unexpected death of epilepsy (SUDEP) is a catastrophic and fatal complication of epilepsy and is the primary cause of mortality in those who have uncontrolled seizures. While several multifactorial processes have been implicated including cardiac, respiratory, autonomic dysfunction leading to arrhythmia, hypoxia, and cessation of cerebral and brainstem function, the mechanisms underlying SUDEP are not completely understood. Postictal generalized electroencephalogram (EEG) suppression (PGES) is a potential risk marker for SUDEP, as studies have shown that prolonged PGES was significantly associated with a higher risk of SUDEP. Automated PGES detection techniques have been developed to efficiently obtain PGES durations for SUDEP risk assessment. However, real-world data recorded in epilepsy monitoring units (EMUs) may contain high-amplitude signals due to physiological artifacts, such as breathing, muscle, and movement artifacts, making it difficult to determine the end of PGES. In this paper, we present a hybrid approach that combines the benefits of unsupervised and supervised learning for PGES detection using multi-channel EEG recordings. A K-means clustering model is leveraged to group EEG recordings with similar artifact features. We introduce a new learning strategy for training a set of random forest (RF) models based on clustering results to improve PGES detection performance. Our approach achieved a 5-second tolerance-based detection accuracy of 64.92%, a 10-second tolerance-based detection accuracy of 79.85%, and an average predicted time distance of 8.26 seconds with 286 EEG recordings using leave-one-out (LOO) cross-validation. The results demonstrated that our hybrid approach provided better performance compared to other existing approaches.
引用
收藏
页数:14
相关论文
共 73 条
[1]  
Abou-Abbas L., 2021, LECT NOTES COMPUTER, V12940, P63, DOI [10.1007/978-3-030-88163-4_6, DOI 10.1007/978-3-030-88163-4_6]
[2]   Ensemble Empirical Mode Decomposition Analysis of EEG Data Collected during a Contour Integration Task [J].
Al-Subari, Karema ;
Al-Baddai, Saad ;
Tome, Ana Maria ;
Volberg, Gregor ;
Hammwoehner, Rainer ;
Lang, Elmar W. .
PLOS ONE, 2015, 10 (04)
[3]   Risk factors of postictal generalized EEG suppression in generalized convulsive seizures [J].
Alexandre, Veriano ;
Mercedes, Blanca ;
Valton, Luc ;
Maillard, Louis ;
Bartolomei, Fabrice ;
Szurhaj, William ;
Hirsch, Edouard ;
Marchal, Cecile ;
Chassoux, Francine ;
Petit, Jerome ;
Crespel, Arielle ;
Nica, Anca ;
Navarro, Vincent ;
Kahane, Philippe ;
De Toffol, Bertrand ;
Thomas, Pierre ;
Rosenberg, Sarah ;
Denuelle, Marie ;
Jonas, Jacques ;
Ryvlin, Philippe ;
Rheims, Sylvain .
NEUROLOGY, 2015, 85 (18) :1598-1603
[4]  
[Anonymous], 2008, ADV NEURAL INF PROCE
[5]   Two predictors of postictal generalized EEG suppression: Tonic phase duration and postictal immobility period [J].
Asadollahi, Marjan ;
Noorbakhsh, Mahyar ;
Simani, Leila ;
Ramezani, Mahtab ;
Gharagozli, Kurosh .
SEIZURE-EUROPEAN JOURNAL OF EPILEPSY, 2018, 61 :135-138
[6]  
Aslan M., 2021, CUMHUR SCI J, V42, P508, DOI [10.17776/csj.682734, DOI 10.17776/csj.682734]
[7]   Electrophysiology in epilepsy surgery: Roles and limitations [J].
Bertram, Edward H. .
ANNALS OF INDIAN ACADEMY OF NEUROLOGY, 2014, 17 :S40-S44
[8]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[9]   Postictal generalized EEG suppression and postictal immobility: what do we know? [J].
Bruno, Elisa ;
Richardson, Mark P. .
EPILEPTIC DISORDERS, 2020, 22 (03) :245-251
[10]   Self-evaluated automatic classifier as a decision-support tool for sleep/wake staging [J].
Charbonnier, S. ;
Zoubek, L. ;
Lesecq, S. ;
Chapotot, F. .
COMPUTERS IN BIOLOGY AND MEDICINE, 2011, 41 (06) :380-389