F84. Sensitivity of persyst seizure detection for different electrographic seizure patterns in patients with status epilepticus

Zorlu, Musab M.; Chuang, David T.; Kettani, Hind; Zarnegar, Reza

doi:10.1016/j.clinph.2018.04.247

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Those background and interictal rhythms, including ictal-interictal continuum patterns, have been shown to confound automated algorithms, causing a decline in detection performance. 17 Our study extends these prior findings in several ways. First, this is the largest study of the automated seizure detection accuracy on inpatient cEEGs outside the EMU, examining performance at both the individual seizure and study levels.…”

Section: Discussionsupporting

confidence: 79%

“…Those background and interictal rhythms, including ictal-interictal continuum patterns, have been shown to confound automated algorithms, causing a decline in detection performance. 17…”

Section: Discussionmentioning

confidence: 99%

“…16 Critical care patients present an additional challenge for automated seizure detection due to abnormal background rhythms and unusual ictal patterns that may confound automated algorithms. 17 Yet, automated seizure detection is arguably most relevant in the intensive care unit (ICU), where seizures are common, rapid treatment is desired, and manual review is often not immediately available. 6,18,19 We studied the performance of Persyst automated seizure detection in a large sample of continuous ICU EEG recordings.…”

Section: Class Of Evidencementioning

confidence: 99%

See 2 more Smart Citations

Seizure Detection in Continuous Inpatient EEG

Ganguly

Ellis

et al. 2022

Neurology

View full text Add to dashboard Cite

OBJECTIVE:To test the accuracy of Persyst© commercially available automated seizure detection in critical care EEG by comparing automated seizure detections to human review in a manually reviewed cohort as well as on a large scale.METHODS:Automated seizure detections (Persyst v.12 and v.13) were compared to human review in a pilot cohort of 229 seizures from 85 EEG records, and then in an expanded cohort of 7,924 EEG records. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for individual seizures (pilot cohort) and for entire records (pilot and expanded cohorts). We assessed EEG features associated with the accuracy of automated seizure detections.RESULTS:In the pilot cohort, accuracy of automated detection for individual seizures was modest (sensitivity 0.50, PPV 0.60). At the record level (did the recording contain seizures or not?), sensitivity was higher (pilot cohort 0.78, expanded cohort 0.91), PPV was low (pilot cohort 0.40, expanded cohort 0.08), whereas NPV was high (pilot cohort 0.88, expanded cohort 0.97). Different software versions (v.12 versus v.13) performed similarly. Sensitivity was higher for records containing focal-onset seizures compared to generalized-onset seizures (0.93 vs 0.85, p = 0.012).CONCLUSIONS:In critical care continuous EEG recordings, automated detection of individual seizures had rates of both false negatives and false positives that question its utility as a seizure alarm in clinical practice. At the level of entire EEG records, the absence of automated detections accurately predicted EEG records without true seizures. The true value of Persyst© automated seizure detection appears to lie in triaging of low-risk EEGs.CLASSIFICATION OF EVIDENCE:This study provides Class II evidence that an automated seizure detection program cannot accurately identify EEG records that contain seizures.

show abstract

Section: Discussionsupporting

confidence: 79%

“…Those background and interictal rhythms, including ictal-interictal continuum patterns, have been shown to confound automated algorithms, causing a decline in detection performance. 17…”

Section: Discussionmentioning

confidence: 99%

Section: Class Of Evidencementioning

confidence: 99%

See 1 more Smart Citation

Seizure Detection in Continuous Inpatient EEG

Ganguly

Ellis

et al. 2022

Neurology

View full text Add to dashboard Cite

show abstract

“…These features include cross-channel correlation [ 6 ], spectral power [ 7 , 8 ], approximate entropy [ 9 ], Lyapunov exponents [ 10 ], and wavelet coefficients [ 11 ]. While informative, these features are not robust to patient heterogeneity [ 12 ] and the high-amplitude artifacts present in EEG data. As a result, traditional seizure detectors were trained and evaluated on a patient-specific basis [ 6 , 7 , 13 ], which is impractical during a prospective clinical review.…”

Section: Introductionmentioning

confidence: 99%

Automated seizure activity tracking and onset zone localization from scalp EEG using deep neural networks

Craley

Jouny²,

Johnson³

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

We propose a novel neural network architecture, SZTrack, to detect and track the spatio-temporal propagation of seizure activity in multichannel EEG. SZTrack combines a convolutional neural network encoder operating on individual EEG channels with recurrent neural networks to capture the evolution of seizure activity. Our unique training strategy aggregates individual electrode level predictions for patient-level seizure detection and localization. We evaluate SZTrack on a clinical EEG dataset of 201 seizure recordings from 34 epilepsy patients acquired at the Johns Hopkins Hospital. Our network achieves similar seizure detection performance to state-of-the-art methods and provides valuable localization information that has not previously been demonstrated in the literature. We also show the cross-site generalization capabilities of SZTrack on a dataset of 53 seizure recordings from 14 epilepsy patients acquired at the University of Wisconsin Madison. SZTrack is able to determine the lobe and hemisphere of origin in nearly all of these new patients without retraining the network. To our knowledge, SZTrack is the first end-to-end seizure tracking network using scalp EEG.

show abstract