EUVIMEDEUVIMED entdecken
Crossref

Interictal Epileptiform Discharge Detection Through Probabilistic Diffusion Models with Maximization of Precision Recall Metrics

Lantian Zhang iD, Duong Nhu iD, Yun Zhao iD, Emma Foster iD, Lyn Millist, Shobi Sivathamboo iD, Patrick Kwan iD, Zongyuan Ge iD, Lan Du iD, Levin Kuhlmann iD

International Journal of Neural Systems · 2026-08 · 36 (08)

DOI: 10.1142/s0129065726500218 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Neural Systems, online erschienen am 17.04.2026. Verfasst von Lantian Zhang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Data Science and AI Faculty of Information Technology Monash University, Wellington Road Clayton, Victoria, Australia. Hauptthemen laut MEDLINE: Electroencephalography, Epilepsy, Models, Statistical. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, automated Interictal Epileptiform Discharge (IED) detection has attracted significant attention as a challenging predictive data analysis task aimed at improving early epilepsy diagnosis. Automated IED detection simplifies visual inspection and assists clinicians in identifying crucial IED waveform patterns in Electroencephalographic (EEG) brain activities. However, IEDs are vastly outnumbered by non-IED or background data, directly training on such data leads to a detrimental impact on model performance. Moreover, most existing methods lack high precision when tested on cross-institution datasets and this will lead to time wasted by the neurologist having to look at predicted IEDs that are not IEDs. To address these issues, we propose a novel approach that employs probabilistic diffusion models for data augmentation alongside Area Under the Precision–Recall Curve (AUPRC) maximization methods. This approach effectively addresses data scarcity and imbalance by combining real and synthesized IEDs to fully balance the training dataset, resulting in a 4.5% increase in precision and a 0.7% improvement in the F1-score during within-data evaluation. Additionally, it proves to be robust and generalizable, as evidenced by a 40.04% and 18.74% enhancement in precision and F1-score when applied to cross-data evaluation using data from another hospital.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyEpilepsyModels, StatisticalHumansSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

AUPRC maximizationInterictal epileptiform discharge (IED)diffusion probabilistic models (DPMs)electroencephalography (EEG)time series classification

Autor:innen und Institutionen

  • Department of Data Science and AI Faculty of Information Technology Monash University, Wellington Road Clayton, Victoria, Australia.
  • Department of Neurosciences The Alfred Hospital, Commercial Road Melbourne, Victoria, Australia.

ORCID-Profile: Lantian Zhang, Duong Nhu, Yun Zhao, Emma Foster, Shobi Sivathamboo, Patrick Kwan, Zongyuan Ge, Lan Du, Levin Kuhlmann

Zitieren

APA

Zhang, L., Nhu, D., Zhao, Y., Foster, E., Millist, L., Sivathamboo, S., Kwan, P., Ge, Z., Du, L., & Kuhlmann, L. (2026). Interictal Epileptiform Discharge Detection Through Probabilistic Diffusion Models with Maximization of Precision Recall Metrics. International Journal of Neural Systems, 36(08). https://doi.org/10.1142/s0129065726500218

Vancouver

Zhang L, Nhu D, Zhao Y, Foster E, Millist L, Sivathamboo S, et al. Interictal Epileptiform Discharge Detection Through Probabilistic Diffusion Models with Maximization of Precision Recall Metrics. International Journal of Neural Systems. 2026;36(08). doi:10.1142/s0129065726500218

BibTeX
@article{Zhang2026,
  author = {Zhang, Lantian and Nhu, Duong and Zhao, Yun and Foster, Emma and Millist, Lyn and Sivathamboo, Shobi and Kwan, Patrick and Ge, Zongyuan and Du, Lan and Kuhlmann, Levin},
  title = {Interictal Epileptiform Discharge Detection Through Probabilistic Diffusion Models with Maximization of Precision Recall Metrics},
  journal = {International Journal of Neural Systems},
  year = {2026},
  volume = {36},
  number = {08},
  doi = {10.1142/s0129065726500218}
}
Kostenlos starten →