EEG-based seizure detection in patients with intellectual disability: which EEG and clinical factors are important?

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Uittreksel

Epilepsy is a commonly secondary disability in people with an intellectual disability (ID), affecting 22% of the ID population while 1% of general population. Surprisingly, EEG-based automated seizure detection in the ID population has not yet been sufficiently studied. The reasons are twofold. Firstly, long-term EEG recordings are few due to behavioral problems. Secondly, the annotation of EEG recordings has been proved difficult due to the complex EEG signal abnormalities caused by brain development disorders. As a result, the performance of automated seizure detection for ID people is largely unknown. In this work, we performed automated seizure detection on a retrospective dataset containing 615 h ambulatory scalp EEG from 29 participants with ID, including 91 seizures. To design a generic seizure detector for the ID people, we need to deal with three major problems: highly imbalanced data, heterogeneous dataset and difficult annotation. (1) For the imbalanced data, we used proper performance criteria (e.g., precision and recall curve) and employed a post-processing process (i.e., patient-specific detection thresholds). (2) For the heterogeneous dataset, we employed multi-domain EEG features that showed a better discriminative power in our dataset, and compared the linear and nonlinear (LDA vs. SVM with Gaussian kernel) classifiers and validated using a leave-one-out cross validation (LOOCV). (3) A stepwise EEG annotation procedure was used to improve the accuracy of annotation due to the presence of numerous seizure imitators and unclear contrast between ictal and interictal EEG activities. Results showed that LDA outperformed SVM with a clear margin of sensitivity, and achieved overall sensitivities 63.1–81.3%, a median FD/h of 1.0 and median latency of 11.5 s. Finally, we conclude that EEG signals of the ID population form a heterogeneous entity with respect to important factors: EEG discharge patterns, EEG backgrounds and EEG seizure visibility. The performance of the seizure detection varies significantly with these factors. The results presented here can serve as prior knowledge for designing a generic seizure detector for the ID patients and the non-convulsive seizure states (NCSS).

TaalEngels
Pagina's404-418
Aantal pagina's15
TijdschriftBiomedical Signal Processing and Control
Volume49
DOI's
StatusGepubliceerd - 1 mrt 2019

Vingerafdruk

Electroencephalography
Intellectual Disability
Seizures
Population
Detectors
Brain Diseases
Disabled Persons
Scalp
Visibility
Epilepsy
Brain
Classifiers
Stroke

Trefwoorden

    Citeer dit

    @article{9628dbcb343b4ac4b43ba35a6cb995d6,
    title = "EEG-based seizure detection in patients with intellectual disability: which EEG and clinical factors are important?",
    abstract = "Epilepsy is a commonly secondary disability in people with an intellectual disability (ID), affecting 22{\%} of the ID population while 1{\%} of general population. Surprisingly, EEG-based automated seizure detection in the ID population has not yet been sufficiently studied. The reasons are twofold. Firstly, long-term EEG recordings are few due to behavioral problems. Secondly, the annotation of EEG recordings has been proved difficult due to the complex EEG signal abnormalities caused by brain development disorders. As a result, the performance of automated seizure detection for ID people is largely unknown. In this work, we performed automated seizure detection on a retrospective dataset containing 615 h ambulatory scalp EEG from 29 participants with ID, including 91 seizures. To design a generic seizure detector for the ID people, we need to deal with three major problems: highly imbalanced data, heterogeneous dataset and difficult annotation. (1) For the imbalanced data, we used proper performance criteria (e.g., precision and recall curve) and employed a post-processing process (i.e., patient-specific detection thresholds). (2) For the heterogeneous dataset, we employed multi-domain EEG features that showed a better discriminative power in our dataset, and compared the linear and nonlinear (LDA vs. SVM with Gaussian kernel) classifiers and validated using a leave-one-out cross validation (LOOCV). (3) A stepwise EEG annotation procedure was used to improve the accuracy of annotation due to the presence of numerous seizure imitators and unclear contrast between ictal and interictal EEG activities. Results showed that LDA outperformed SVM with a clear margin of sensitivity, and achieved overall sensitivities 63.1–81.3{\%}, a median FD/h of 1.0 and median latency of 11.5 s. Finally, we conclude that EEG signals of the ID population form a heterogeneous entity with respect to important factors: EEG discharge patterns, EEG backgrounds and EEG seizure visibility. The performance of the seizure detection varies significantly with these factors. The results presented here can serve as prior knowledge for designing a generic seizure detector for the ID patients and the non-convulsive seizure states (NCSS).",
    keywords = "EEG, Imbalanced data, Intellectual disability, LDA, Multilevel analysis, Post-processing, Seizure detection, SVM",
    author = "Lei Wang and Xi Long and Aarts, {Ronald M.} and {van Dijk}, {Johannes P.} and Arends, {Johan B.A.M.}",
    year = "2019",
    month = "3",
    day = "1",
    doi = "10.1016/j.bspc.2018.12.003",
    language = "English",
    volume = "49",
    pages = "404--418",
    journal = "Biomedical Signal Processing and Control",
    issn = "1746-8094",
    publisher = "Elsevier",

    }

    EEG-based seizure detection in patients with intellectual disability : which EEG and clinical factors are important? / Wang, Lei (Corresponding author); Long, Xi; Aarts, Ronald M.; van Dijk, Johannes P.; Arends, Johan B.A.M.

    In: Biomedical Signal Processing and Control, Vol. 49, 01.03.2019, blz. 404-418.

    Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

    TY - JOUR

    T1 - EEG-based seizure detection in patients with intellectual disability

    T2 - Biomedical Signal Processing and Control

    AU - Wang,Lei

    AU - Long,Xi

    AU - Aarts,Ronald M.

    AU - van Dijk,Johannes P.

    AU - Arends,Johan B.A.M.

    PY - 2019/3/1

    Y1 - 2019/3/1

    N2 - Epilepsy is a commonly secondary disability in people with an intellectual disability (ID), affecting 22% of the ID population while 1% of general population. Surprisingly, EEG-based automated seizure detection in the ID population has not yet been sufficiently studied. The reasons are twofold. Firstly, long-term EEG recordings are few due to behavioral problems. Secondly, the annotation of EEG recordings has been proved difficult due to the complex EEG signal abnormalities caused by brain development disorders. As a result, the performance of automated seizure detection for ID people is largely unknown. In this work, we performed automated seizure detection on a retrospective dataset containing 615 h ambulatory scalp EEG from 29 participants with ID, including 91 seizures. To design a generic seizure detector for the ID people, we need to deal with three major problems: highly imbalanced data, heterogeneous dataset and difficult annotation. (1) For the imbalanced data, we used proper performance criteria (e.g., precision and recall curve) and employed a post-processing process (i.e., patient-specific detection thresholds). (2) For the heterogeneous dataset, we employed multi-domain EEG features that showed a better discriminative power in our dataset, and compared the linear and nonlinear (LDA vs. SVM with Gaussian kernel) classifiers and validated using a leave-one-out cross validation (LOOCV). (3) A stepwise EEG annotation procedure was used to improve the accuracy of annotation due to the presence of numerous seizure imitators and unclear contrast between ictal and interictal EEG activities. Results showed that LDA outperformed SVM with a clear margin of sensitivity, and achieved overall sensitivities 63.1–81.3%, a median FD/h of 1.0 and median latency of 11.5 s. Finally, we conclude that EEG signals of the ID population form a heterogeneous entity with respect to important factors: EEG discharge patterns, EEG backgrounds and EEG seizure visibility. The performance of the seizure detection varies significantly with these factors. The results presented here can serve as prior knowledge for designing a generic seizure detector for the ID patients and the non-convulsive seizure states (NCSS).

    AB - Epilepsy is a commonly secondary disability in people with an intellectual disability (ID), affecting 22% of the ID population while 1% of general population. Surprisingly, EEG-based automated seizure detection in the ID population has not yet been sufficiently studied. The reasons are twofold. Firstly, long-term EEG recordings are few due to behavioral problems. Secondly, the annotation of EEG recordings has been proved difficult due to the complex EEG signal abnormalities caused by brain development disorders. As a result, the performance of automated seizure detection for ID people is largely unknown. In this work, we performed automated seizure detection on a retrospective dataset containing 615 h ambulatory scalp EEG from 29 participants with ID, including 91 seizures. To design a generic seizure detector for the ID people, we need to deal with three major problems: highly imbalanced data, heterogeneous dataset and difficult annotation. (1) For the imbalanced data, we used proper performance criteria (e.g., precision and recall curve) and employed a post-processing process (i.e., patient-specific detection thresholds). (2) For the heterogeneous dataset, we employed multi-domain EEG features that showed a better discriminative power in our dataset, and compared the linear and nonlinear (LDA vs. SVM with Gaussian kernel) classifiers and validated using a leave-one-out cross validation (LOOCV). (3) A stepwise EEG annotation procedure was used to improve the accuracy of annotation due to the presence of numerous seizure imitators and unclear contrast between ictal and interictal EEG activities. Results showed that LDA outperformed SVM with a clear margin of sensitivity, and achieved overall sensitivities 63.1–81.3%, a median FD/h of 1.0 and median latency of 11.5 s. Finally, we conclude that EEG signals of the ID population form a heterogeneous entity with respect to important factors: EEG discharge patterns, EEG backgrounds and EEG seizure visibility. The performance of the seizure detection varies significantly with these factors. The results presented here can serve as prior knowledge for designing a generic seizure detector for the ID patients and the non-convulsive seizure states (NCSS).

    KW - EEG

    KW - Imbalanced data

    KW - Intellectual disability

    KW - LDA

    KW - Multilevel analysis

    KW - Post-processing

    KW - Seizure detection

    KW - SVM

    UR - http://www.scopus.com/inward/record.url?scp=85059201510&partnerID=8YFLogxK

    U2 - 10.1016/j.bspc.2018.12.003

    DO - 10.1016/j.bspc.2018.12.003

    M3 - Article

    VL - 49

    SP - 404

    EP - 418

    JO - Biomedical Signal Processing and Control

    JF - Biomedical Signal Processing and Control

    SN - 1746-8094

    ER -