Revisiting SUDEP Risk Prediction via Data Augmentation

8 pages•Published: April 19, 2026

Meiyu Li, Juliana Laze, Daniel Friedman, Orrin Devinsky and Zhe Chen

Abstract

Sudden unexpected death in epilepsy (SUDEP) is the leading cause of epilepsy-related mortality. Low-cost and noninvasive interictal biomarkers of SUDEP risk can help clinicians identify high-risk patients and initiate preventive actions. However, the small sample size in SUDEP patients remains a bottleneck for discriminatory analysis or biomarker discovery. Machine-driven data augmentation (DA) techniques can potentially alleviate the sample insufficiency or imbalance problem using synthetic data. Here we revisit an old SUDEP risk prediction problem from a new DA and generative artificial intelligence (AI) perspective, using a multicenter cohort study consisting of multichannel interictal electroencephalography (EEG) and electrocardiography (ECG) data from SUDEP patients and age-matched living epilepsy patient controls. Our results show that DA strategies can not only significantly improve the cross-validated prediction accuracy but also generalize well in newly collected held-out data samples.

Keyphrases: data augmentation, eeg, generative ai, sudep risk

In: Jernej Masnec, Hamid Reza Karimian, Parisa Kordjamshidi and Yan Li (editors). Proceedings of AI for Accelerated Research Symposium, vol 3, pages 57-64.

Links:	https://easychair.org/publications/paper/lKdZ
	https://doi.org/10.29007/7bws

BibTeX entry

@inproceedings{AIAS2025:Revisiting_SUDEP_Risk_Prediction,
  author    = {Meiyu Li and Juliana Laze and Daniel Friedman and Orrin Devinsky and Zhe Chen},
  title     = {Revisiting SUDEP Risk Prediction via Data Augmentation},
  booktitle = {Proceedings of AI for Accelerated Research Symposium},
  editor    = {Jernej Masnec and Hamid Reza Karimian and Parisa Kordjamshidi and Yan Li},
  series    = {EPiC Series in Technology},
  volume    = {3},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2516-2322},
  url       = {/publications/paper/lKdZ},
  doi       = {10.29007/7bws},
  pages     = {57-64},
  year      = {2026}}

Download PDF Open PDF in browser