Prediction of seizure recurrence using electroencephalogram analysis with multiscale deep neural networks before withdrawal of antiepileptic drugs
Background: The decision to continue or discontinue antiepileptic drug (AED) treatment in patients who are seizure free for a prolonged time is critical. Studies have used certain risk factors or electroencephalogram (EEG) findings to predict seizure recurrence after the withdrawal of AEDs. However,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-05-01
|
| Series: | Pediatrics and Neonatology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1875957222000468 |
| _version_ | 1818232244480770048 |
|---|---|
| author | Lung-Chang Lin Ming-Yuh Chang Yi-Hung Chiu Ching-Tai Chiang Rong-Ching Wu Rei-Cheng Yang Chen-Sen Ouyang |
| author_facet | Lung-Chang Lin Ming-Yuh Chang Yi-Hung Chiu Ching-Tai Chiang Rong-Ching Wu Rei-Cheng Yang Chen-Sen Ouyang |
| author_sort | Lung-Chang Lin |
| collection | DOAJ |
| description | Background: The decision to continue or discontinue antiepileptic drug (AED) treatment in patients who are seizure free for a prolonged time is critical. Studies have used certain risk factors or electroencephalogram (EEG) findings to predict seizure recurrence after the withdrawal of AEDs. However, applicable biomarkers to guide the withdrawal of AEDs are lacking. Methods: In this study, we used EEG analysis based on multiscale deep neural networks (MSDNN) to establish a method for predicting seizure recurrence after the withdrawal of AEDs. A total of 60 patients with epilepsy were divided into two groups (30 in the recurrence group and 30 in the non-recurrence group). All patients were seizure free for at least 2 years. Before AED withdrawal, an EEG was performed for each patient, which showed no epileptiform discharges. These EEG recordings were classified using MSDNN. Results: We found that the performance indices of classification between recurrence and non-recurrence groups had a mean sensitivity, mean specificity, mean accuracy, and mean area under the receiver operating characteristic curve of 74.23%, 75.83%, 74.66%, and 82.66%, respectively. Conclusion: Our proposed method is a promising tool to help physicians to predict seizure recurrence after AED withdrawal among seizure-free patients. |
| first_indexed | 2024-12-12T11:03:12Z |
| format | Article |
| id | doaj.art-99112afa94a44ab6ace64ac51e3526f4 |
| institution | Directory Open Access Journal |
| issn | 1875-9572 |
| language | English |
| last_indexed | 2024-12-12T11:03:12Z |
| publishDate | 2022-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Pediatrics and Neonatology |
| spelling | doaj.art-99112afa94a44ab6ace64ac51e3526f42022-12-22T00:26:28ZengElsevierPediatrics and Neonatology1875-95722022-05-01633283290Prediction of seizure recurrence using electroencephalogram analysis with multiscale deep neural networks before withdrawal of antiepileptic drugsLung-Chang Lin0Ming-Yuh Chang1Yi-Hung Chiu2Ching-Tai Chiang3Rong-Ching Wu4Rei-Cheng Yang5Chen-Sen Ouyang6Department of Pediatrics, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung City, Taiwan; Department of Pediatrics, School of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung City, TaiwanDepartments of Pediatrics, Changhua Christian Hospital, Changhua, TaiwanDepartment of Information Engineering, I-Shou University, Kaohsiung City, TaiwanDepartment of Computer and Communication, National Pingtung University, Pingtung City, TaiwanDepartment of Electrical Engineering, I-Shou University, Kaohsiung City, TaiwanDepartment of Pediatrics, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung City, Taiwan; Department of Pediatrics, School of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung City, Taiwan; Corresponding author. Department of Pediatrics, Kaohsiung Medical University Hospital, Kaohsiung Medical University, 807, #100, Tzu-you 1st Road, Kaohsiung City, Taiwan.Department of Information Engineering, I-Shou University, Kaohsiung City, Taiwan; Corresponding author.Background: The decision to continue or discontinue antiepileptic drug (AED) treatment in patients who are seizure free for a prolonged time is critical. Studies have used certain risk factors or electroencephalogram (EEG) findings to predict seizure recurrence after the withdrawal of AEDs. However, applicable biomarkers to guide the withdrawal of AEDs are lacking. Methods: In this study, we used EEG analysis based on multiscale deep neural networks (MSDNN) to establish a method for predicting seizure recurrence after the withdrawal of AEDs. A total of 60 patients with epilepsy were divided into two groups (30 in the recurrence group and 30 in the non-recurrence group). All patients were seizure free for at least 2 years. Before AED withdrawal, an EEG was performed for each patient, which showed no epileptiform discharges. These EEG recordings were classified using MSDNN. Results: We found that the performance indices of classification between recurrence and non-recurrence groups had a mean sensitivity, mean specificity, mean accuracy, and mean area under the receiver operating characteristic curve of 74.23%, 75.83%, 74.66%, and 82.66%, respectively. Conclusion: Our proposed method is a promising tool to help physicians to predict seizure recurrence after AED withdrawal among seizure-free patients.http://www.sciencedirect.com/science/article/pii/S1875957222000468antiepileptic drugmultiscale deep neural networkswithdrawal |
| spellingShingle | Lung-Chang Lin Ming-Yuh Chang Yi-Hung Chiu Ching-Tai Chiang Rong-Ching Wu Rei-Cheng Yang Chen-Sen Ouyang Prediction of seizure recurrence using electroencephalogram analysis with multiscale deep neural networks before withdrawal of antiepileptic drugs Pediatrics and Neonatology antiepileptic drug multiscale deep neural networks withdrawal |
| title | Prediction of seizure recurrence using electroencephalogram analysis with multiscale deep neural networks before withdrawal of antiepileptic drugs |
| title_full | Prediction of seizure recurrence using electroencephalogram analysis with multiscale deep neural networks before withdrawal of antiepileptic drugs |
| title_fullStr | Prediction of seizure recurrence using electroencephalogram analysis with multiscale deep neural networks before withdrawal of antiepileptic drugs |
| title_full_unstemmed | Prediction of seizure recurrence using electroencephalogram analysis with multiscale deep neural networks before withdrawal of antiepileptic drugs |
| title_short | Prediction of seizure recurrence using electroencephalogram analysis with multiscale deep neural networks before withdrawal of antiepileptic drugs |
| title_sort | prediction of seizure recurrence using electroencephalogram analysis with multiscale deep neural networks before withdrawal of antiepileptic drugs |
| topic | antiepileptic drug multiscale deep neural networks withdrawal |
| url | http://www.sciencedirect.com/science/article/pii/S1875957222000468 |
| work_keys_str_mv | AT lungchanglin predictionofseizurerecurrenceusingelectroencephalogramanalysiswithmultiscaledeepneuralnetworksbeforewithdrawalofantiepilepticdrugs AT mingyuhchang predictionofseizurerecurrenceusingelectroencephalogramanalysiswithmultiscaledeepneuralnetworksbeforewithdrawalofantiepilepticdrugs AT yihungchiu predictionofseizurerecurrenceusingelectroencephalogramanalysiswithmultiscaledeepneuralnetworksbeforewithdrawalofantiepilepticdrugs AT chingtaichiang predictionofseizurerecurrenceusingelectroencephalogramanalysiswithmultiscaledeepneuralnetworksbeforewithdrawalofantiepilepticdrugs AT rongchingwu predictionofseizurerecurrenceusingelectroencephalogramanalysiswithmultiscaledeepneuralnetworksbeforewithdrawalofantiepilepticdrugs AT reichengyang predictionofseizurerecurrenceusingelectroencephalogramanalysiswithmultiscaledeepneuralnetworksbeforewithdrawalofantiepilepticdrugs AT chensenouyang predictionofseizurerecurrenceusingelectroencephalogramanalysiswithmultiscaledeepneuralnetworksbeforewithdrawalofantiepilepticdrugs |