Pitfalls in EEG analysis in patients with non-convulsive status epilepticus

Wang, Ying; Zibrandtsen, Ivan C; Lazeron, R.H.C.; Dijk, J.P. van; Long, Xi; Aarts, Ronald M.; Wang, Lei; Arends, Jbam Johan

doi:10.1101/2020.10.02.20205583

Cited by 1 publication

(6 citation statements)

References 25 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the EEG recordings of adults living in a residential care setting and out-patient children during NCSE were analyzed. We retrieved clinical records and EEG recordings from 20 participants diagnosed as NCSE during the period from 2008 to 2016 at the EEG department of Kempenhaeghe, a specialized epilepsy center in the Netherlands (Wang et al 2020). After a recheck on the recordings by a neurologist specialized in epilepsy, four participants were excluded because of non-traceable EEG recording (n = 1), misdiagnosis for symptoms suspected to be NCSE (n = 2), and no consent for scientific research (n = 1).…”

Section: Datasetmentioning

confidence: 99%

“…After a recheck on the recordings by a neurologist specialized in epilepsy, four participants were excluded because of non-traceable EEG recording (n = 1), misdiagnosis for symptoms suspected to be NCSE (n = 2), and no consent for scientific research (n = 1). Ictal discharges during NCSE which were longer than 20 s were annotated by two independent raters and categorized into five morphological patterns ('Spike Wave' , 'Wave' , 'Fast Spike' , 'EMG-like Discharges' , and 'Unknown Type') based on their dominant discharge patterns (Wang et al 2017a(Wang et al , 2020. Interrater agreements were measured using Cohen's kappa and Fleiss' kappa (Wang et al 2020).…”

Section: Datasetmentioning

confidence: 99%

“…Ictal discharges during NCSE which were longer than 20 s were annotated by two independent raters and categorized into five morphological patterns ('Spike Wave' , 'Wave' , 'Fast Spike' , 'EMG-like Discharges' , and 'Unknown Type') based on their dominant discharge patterns (Wang et al 2017a(Wang et al , 2020. Interrater agreements were measured using Cohen's kappa and Fleiss' kappa (Wang et al 2020). Based on the annotations, two participants, whose ictal discharges were not over-20-seconds in length, were excluded in the analysis.…”

Section: Datasetmentioning

confidence: 99%

“…The diagnosis of NCSE is usually confirmed by reading long-duration EEG recordings, but the real-time visual EEG analysis is costly; thus, a computer-assisted analysis system is needed in the NCSE detection. However, we previously found that computer-assisted monitoring systems frequently raise false alarms because of over-interpreting three EEG patterns as seizures (figure 1): abnormal background activity, dense short ictal discharges (EEG activities during clinical seizures) and continuous interictal discharges (EEG activities between two seizures) (Wang et al 2020). The frequent false alarms reduce NCSE diagnosis accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…Other studies either presented a high false positive detection rate (0. In this study, we aimed at reducing false alarms in the NCSE detection in the monitoring of adults and older children based on our previously found EEG patterns related to false alarms (Wang et al 2020). To reduce the false alarms caused by abnormal background activity that confused time-frequency features, we added morphological features using visibility graph (VG) analysis (Lacasa et al 2008) to the commonly used time-frequency features.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

False alarms reduction in non-convulsive status epilepticus detection via continuous EEG analysis

et al. 2020

Self Cite

View full text Add to dashboard Cite

Objective: Frequent false alarms from computer-assisted monitoring systems may harm the safety of patients with non-convulsive status epilepticus (NCSE). In this study, we aimed at reducing false alarms in the NCSE detection based on preventing from three common errors: over-interpretation of abnormal background activity, dense short ictal discharges and continuous interictal discharges as ictal discharges. Approach: We analyzed 10 participants' hospital-archived 127-hour electroencephalography (EEG) recordings with 310 ictal discharges. To reduce the false alarms caused by abnormal background activity, we used morphological features extracted by visibility graph methods in addition to time-frequency features. To reduce the false alarms caused by over-interpreting short ictal discharges and interictal discharges, we created two synthetic classes-'Suspected Non-ictal' and 'Suspected Ictal'-based on the misclassified categories and constructed a synthetic 4-class dataset combining the standard two classes-'Non-ictal' and 'Ictal'-to train a 4-class classifier. Precision-recall curves were used to compare our proposed 4-class classification model and the standard 2-class classification model with or without the morphological features in the leave-one-out cross validation stage. The sensitivity and precision were primarily used as performance metrics for the detection of a seizure event. Main results: The 4-class classification model improved the performance of the standard 2-class model, in particular increasing the precision by 15% at an 80% sensitivity level when only time-frequency features were used. Using the morphological features, the 4-class classification model achieved the best performances: a sensitivity of 93% ± 12% and a precision of 55% ± 30% in the group level. 100% accuracy was reached in a participant's 4.3-hour recording with 5 ictal discharges. Significance: False alarms in the NCSE detection were remarkably reduced using the morphological features and the proposed 4-class classification model.

show abstract

Section: Datasetmentioning

confidence: 99%