EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ECG-Based Detection of Epileptic Seizures in Real-World Wearable Settings: Insights from the SeizeIT2 Dataset

Conrad Reintjes, Janosch Fabio Hagenbeck iD, Mohamed Ballo, Tim Rahlmeier iD, Simon Maximilian Wolf iD, Detlef Schoder

Sensors · 2025

DOI: 10.3390/s25247687 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Conrad Reintjes und 5 weiteren Autor:innen. Beteiligte Einrichtung: Cologne Institute for Information Systems, University of Cologne, 50923 Cologne, Germany. Hauptthemen laut MEDLINE: Electrocardiography, Wearable Electronic Devices, Seizures, Epilepsy. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Government of North Rhine Westphalia, the state government of North Rhine-Westphalia, Germany.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Epilepsy is a prevalent neurological disorder where reliable seizure tracking is essential for patient care. Existing documentation often relies on self-reports, which are unreliable, creating a need for objective, wearable-based solutions. Prior work has shown that Electrocardiography (ECG)-based seizure detection is feasible but limited by small datasets. This study addresses this issue by evaluating Matrix Profile, MADRID, and TimeVQVAE-AD on SeizeIT2, the largest open wearable-ECG dataset with 11,640 recording hours and 886 annotated seizures. Using standardized preprocessing and clinically motivated windows, we benchmarked sensitivity, false-alarm rate (FAR), and a Harmonic Mean Score integrating both metrics. Across methods, TimeVQVAE-AD achieved the highest sensitivity, while MADRID produced the lowest FAR, illustrating the trade-off between detecting seizures and minimizing spurious alerts. Our findings show ECG anomaly detection on SeizeIT2 can reach clinically meaningful sensitivity while highlighting the sensitivity–false alarm trade-off. By releasing reproducible benchmarks and code, this work establishes the first open baseline and enables future research on personalization and clinical applicability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectrocardiographyWearable Electronic DevicesSeizuresEpilepsyHumansAlgorithmsSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

anomaly detectionelectrocardiographyepilepsymachine learningseizure detectionwearable sensors

Autor:innen und Institutionen

  • Cologne Institute for Information Systems, University of Cologne, 50923 Cologne, Germany.

ORCID-Profile: Janosch Fabio Hagenbeck, Tim Rahlmeier, Simon Maximilian Wolf

Förderung

  • State Government of North Rhine Westphalia
  • the state government of North Rhine-Westphalia, Germany

Zitieren

APA

Reintjes, C., Hagenbeck, J. F., Ballo, M., Rahlmeier, T., Wolf, S. M., & Schoder, D. (2025). ECG-Based Detection of Epileptic Seizures in Real-World Wearable Settings: Insights from the SeizeIT2 Dataset. Sensors. https://doi.org/10.3390/s25247687

Vancouver

Reintjes C, Hagenbeck JF, Ballo M, Rahlmeier T, Wolf SM, Schoder D. ECG-Based Detection of Epileptic Seizures in Real-World Wearable Settings: Insights from the SeizeIT2 Dataset. Sensors. 2025. doi:10.3390/s25247687

BibTeX
@article{Reintjes2025,
  author = {Reintjes, Conrad and Hagenbeck, Janosch Fabio and Ballo, Mohamed and Rahlmeier, Tim and Wolf, Simon Maximilian and Schoder, Detlef},
  title = {ECG-Based Detection of Epileptic Seizures in Real-World Wearable Settings: Insights from the SeizeIT2 Dataset},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25247687}
}
Kostenlos starten →