A hybrid unsupervised and supervised learning approach for postictal generalized EEG suppression detection
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...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-12-01
|
| Series: | Frontiers in Neuroinformatics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fninf.2022.1040084/full |
| _version_ | 1798004987846983680 |
|---|---|
| author | Xiaojin Li Xiaojin Li Yan Huang Yan Huang Samden D. Lhatoo Samden D. Lhatoo Shiqiang Tao Shiqiang Tao Laura Vilella Bertran Laura Vilella Bertran Guo-Qiang Zhang Guo-Qiang Zhang Guo-Qiang Zhang Licong Cui Licong Cui |
| author_facet | Xiaojin Li Xiaojin Li Yan Huang Yan Huang Samden D. Lhatoo Samden D. Lhatoo Shiqiang Tao Shiqiang Tao Laura Vilella Bertran Laura Vilella Bertran Guo-Qiang Zhang Guo-Qiang Zhang Guo-Qiang Zhang Licong Cui Licong Cui |
| author_sort | Xiaojin Li |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-11T12:32:08Z |
| format | Article |
| id | doaj.art-398c3117a836447ca825df3c8476e351 |
| institution | Directory Open Access Journal |
| issn | 1662-5196 |
| language | English |
| last_indexed | 2024-04-11T12:32:08Z |
| publishDate | 2022-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroinformatics |
| spelling | doaj.art-398c3117a836447ca825df3c8476e3512022-12-22T04:23:43ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962022-12-011610.3389/fninf.2022.10400841040084A hybrid unsupervised and supervised learning approach for postictal generalized EEG suppression detectionXiaojin Li0Xiaojin Li1Yan Huang2Yan Huang3Samden D. Lhatoo4Samden D. Lhatoo5Shiqiang Tao6Shiqiang Tao7Laura Vilella Bertran8Laura Vilella Bertran9Guo-Qiang Zhang10Guo-Qiang Zhang11Guo-Qiang Zhang12Licong Cui13Licong Cui14Department of Neurology, The University of Texas Health Science Center at Houston, Houston, TX, United StatesTexas Institute for Restorative Neurotechnologies, The University of Texas Health Science Center at Houston, Houston, TX, United StatesDepartment of Neurology, The University of Texas Health Science Center at Houston, Houston, TX, United StatesTexas Institute for Restorative Neurotechnologies, The University of Texas Health Science Center at Houston, Houston, TX, United StatesDepartment of Neurology, The University of Texas Health Science Center at Houston, Houston, TX, United StatesTexas Institute for Restorative Neurotechnologies, The University of Texas Health Science Center at Houston, Houston, TX, United StatesDepartment of Neurology, The University of Texas Health Science Center at Houston, Houston, TX, United StatesTexas Institute for Restorative Neurotechnologies, The University of Texas Health Science Center at Houston, Houston, TX, United StatesDepartment of Neurology, The University of Texas Health Science Center at Houston, Houston, TX, United StatesTexas Institute for Restorative Neurotechnologies, The University of Texas Health Science Center at Houston, Houston, TX, United StatesDepartment of Neurology, The University of Texas Health Science Center at Houston, Houston, TX, United StatesTexas Institute for Restorative Neurotechnologies, The University of Texas Health Science Center at Houston, Houston, TX, United StatesSchool of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United StatesTexas Institute for Restorative Neurotechnologies, The University of Texas Health Science Center at Houston, Houston, TX, United StatesSchool of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, United StatesSudden 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.https://www.frontiersin.org/articles/10.3389/fninf.2022.1040084/fullepilepsygeneralized tonic-clonic seizurepostictal generalized EEG suppressionEEGunsupervised learninghybrid classifier |
| spellingShingle | Xiaojin Li Xiaojin Li Yan Huang Yan Huang Samden D. Lhatoo Samden D. Lhatoo Shiqiang Tao Shiqiang Tao Laura Vilella Bertran Laura Vilella Bertran Guo-Qiang Zhang Guo-Qiang Zhang Guo-Qiang Zhang Licong Cui Licong Cui A hybrid unsupervised and supervised learning approach for postictal generalized EEG suppression detection Frontiers in Neuroinformatics epilepsy generalized tonic-clonic seizure postictal generalized EEG suppression EEG unsupervised learning hybrid classifier |
| title | A hybrid unsupervised and supervised learning approach for postictal generalized EEG suppression detection |
| title_full | A hybrid unsupervised and supervised learning approach for postictal generalized EEG suppression detection |
| title_fullStr | A hybrid unsupervised and supervised learning approach for postictal generalized EEG suppression detection |
| title_full_unstemmed | A hybrid unsupervised and supervised learning approach for postictal generalized EEG suppression detection |
| title_short | A hybrid unsupervised and supervised learning approach for postictal generalized EEG suppression detection |
| title_sort | hybrid unsupervised and supervised learning approach for postictal generalized eeg suppression detection |
| topic | epilepsy generalized tonic-clonic seizure postictal generalized EEG suppression EEG unsupervised learning hybrid classifier |
| url | https://www.frontiersin.org/articles/10.3389/fninf.2022.1040084/full |
| work_keys_str_mv | AT xiaojinli ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT xiaojinli ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT yanhuang ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT yanhuang ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT samdendlhatoo ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT samdendlhatoo ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT shiqiangtao ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT shiqiangtao ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT lauravilellabertran ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT lauravilellabertran ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT guoqiangzhang ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT guoqiangzhang ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT guoqiangzhang ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT licongcui ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT licongcui ahybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT xiaojinli hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT xiaojinli hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT yanhuang hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT yanhuang hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT samdendlhatoo hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT samdendlhatoo hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT shiqiangtao hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT shiqiangtao hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT lauravilellabertran hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT lauravilellabertran hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT guoqiangzhang hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT guoqiangzhang hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT guoqiangzhang hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT licongcui hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection AT licongcui hybridunsupervisedandsupervisedlearningapproachforpostictalgeneralizedeegsuppressiondetection |