EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY-NC-ND 4.0

Accuracy of the rapid‐response electroencephalography's Automated Seizure Burden Estimator: A follow‐up validation study of version 8 ( AccuRASE II )

Zubeda B Sheikh iD, Michael W K Fong iD, Monica B Dhakar iD, Wei Fang iD, Neishay Ayub iD, Janine Molino iD, Hiba A Haider iD, Brandon Foreman iD, Emily J Gilmore iD, Moshe Mizrahi iD, Ioannis Karakis iD, Sarah Schmitt iD und 3 weitere

Epilepsia · 2026

DOI: 10.1002/epi.70352 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Epilepsia, 2026. Verfasst von Zubeda B Sheikh und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Yale University School of Medicine, New Haven, Connecticut, USA. Hauptthemen laut MEDLINE: Electroencephalography, Seizures, Status Epilepticus. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Ceribell Inc.'s point‐of‐care electroencephalographic (EEG) system and artificial intelligence‐based Automated Seizure Burden Estimator (ASBE; ClarityPro) have US Food and Drug Administration clearance for diagnosing electrographic status epilepticus (ESE). The AccuRASE study using ASBE version 6 (V6) showed high negative predictive value (NPV) but limited sensitivity and positive predictive value (PPV) at certain thresholds. Version 8 (V8) is the updated algorithm trained with additional EEG samples.

Methods

We tested V8 on the previously used rapid‐response EEG test dataset (not used to train V8). Sensitivity, specificity, PPV, and NPV were compared against blinded expert annotations. ESE, ESE and possible ESE (ESE/pESE), electrographic seizures (ESz), and Esz with highly epileptiform patterns (Esz/HEPs) at burden thresholds of >1%, >10%, >20%, >50%, and >90% were analyzed. Additionally, we evaluated the built‐in ESE and ESE/pESE alerts (≥90% over 5 min, ≥20% over 1 h, or ≥10 continuous minutes of seizure).

Results

V8 showed 100% sensitivity at lower thresholds (>10%–20%) for ESE (V6 .86), without a specificity loss (V8 .9 vs. V6 .85), and retained NPV (V8 1.0 vs. V6 .99). Sensitivity at 50% threshold was .86 for ESE (V6 .71), and specificity was .94 (V6 .91); PPV for ESE was 30% for ESE and 80% for ESE/pESE. The specificity for ESE remained high for 90% burden (V8 .96, V6 .97) but the sensitivity dropped (.29 vs. V6 .43). Sensitivity was lower for ESz/HEPs (.54 → .44 at >10% threshold), although the algorithm is not designed to detect HEPs. Built‐in alert analysis showed significantly improved sensitivity for ESE (.57 → .86); specificity and NPV remained high (>.94). Significance ASBE V8 showed meaningful improvements in sensitivity, continued excellent NPV, and improved built‐in alert accuracy for ESE and ESE/pESE. The best seizure burden threshold for ruling out ESE now is 20% (vs. 10% with V6) and that for ruling in ESE/pESE with reasonable certainty is 50% (vs. 90% with V6).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographySeizuresStatus EpilepticusHumansAlgorithmsSensitivity and SpecificityFollow-Up StudiesPredictive Value of TestsArtificial IntelligenceFemaleReproducibility of ResultsPoint-of-Care SystemsMale

Stichwörter der Autor:innen

artificial intelligenceautomatedpoint of care (POC) EEGrapid response EEGseizure detection

Autor:innen und Institutionen

  • Department of Neurology, Yale University School of Medicine, New Haven, Connecticut, USA.
  • Department of Neurology, Virginia Commonwealth University, Richmond, Virginia, USA.
  • Westmead Comprehensive Epilepsy Centre, University of Sydney, Sydney, New South Wales, Australia.
  • Department of Neurology, Brown University, Providence, Rhode Island, USA.
  • Health Sciences Center, University of New Mexico, Albuquerque, New Mexico, USA.
  • Department of Orthopaedics, Warren Alpert Medical School at Brown University; Biostatistics, Epidemiology, Research Design, and Informatics Core, Rhode Island Hospital, Providence, Rhode Island, USA.

ORCID-Profile: Zubeda B Sheikh, Michael W K Fong, Monica B Dhakar, Wei Fang, Neishay Ayub, Janine Molino, Hiba A Haider, Brandon Foreman, Emily J Gilmore, Moshe Mizrahi, Ioannis Karakis, Sarah Schmitt, Gamaleldin Osman, Ji Yeoun Yoo, Lawrence J Hirsch

Zitieren

APA

Sheikh, Z. B., Fong, M. W. K., Dhakar, M. B., Fang, W., Ayub, N., Molino, J., Haider, H. A., Foreman, B., Gilmore, E. J., Mizrahi, M., Karakis, I., Schmitt, S., Osman, G., Yoo, J. Y., & Hirsch, L. J. (2026). Accuracy of the rapid‐response electroencephalography's Automated Seizure Burden Estimator: A follow‐up validation study of version 8 ( AccuRASE II ). Epilepsia. https://doi.org/10.1002/epi.70352

Vancouver

Sheikh ZB, Fong MWK, Dhakar MB, Fang W, Ayub N, Molino J, et al. Accuracy of the rapid‐response electroencephalography's Automated Seizure Burden Estimator: A follow‐up validation study of version 8 ( AccuRASE II ). Epilepsia. 2026. doi:10.1002/epi.70352

BibTeX
@article{Sheikh2026,
  author = {Sheikh, Zubeda B and Fong, Michael W K and Dhakar, Monica B and Fang, Wei and Ayub, Neishay and Molino, Janine and Haider, Hiba A and Foreman, Brandon and Gilmore, Emily J and Mizrahi, Moshe and Karakis, Ioannis and Schmitt, Sarah and Osman, Gamaleldin and Yoo, Ji Yeoun and Hirsch, Lawrence J},
  title = {Accuracy of the rapid‐response electroencephalography's Automated Seizure Burden Estimator: A follow‐up validation study of version 8 ( AccuRASE II )},
  journal = {Epilepsia},
  year = {2026},
  doi = {10.1002/epi.70352}
}
Kostenlos starten →