Skip to content
Open access

Contrastive self-supervised learning for epileptic seizure detection from EEG with calibration and robustness evaluation under physiology-aligned perturbations

Aug 2026 · Discover Artificial Intelligence · Vol 6 · 0 citations · 31 references

TL;DR

A proof-of-concept study applying contrastive self-supervised learning (SSL) to EEG epileptic seizure detection, comparing a SimCLR-style InfoNCE encoder pre-trained on unlabelled EEG against a supervised-only baseline sharing the same backbone, and evaluating both through a framework encompassing discrimination, operating-point behaviour, calibration, and physiology-aligned robustness.

Abstract

Labelled EEG data for epileptic seizure detection are scarce, and clinical recordings routinely suffer from realistic signal degradation including electrode loss, baseline drift, and sampling jitter. We present a proof-of-concept study applying contrastive self-supervised learning (SSL) to EEG epileptic seizure detection, comparing a SimCLR-style InfoNCE encoder pre-trained on unlabelled EEG against a supervised-only baseline sharing the same backbone, and evaluating both through a framework encompassing discrimination, operating-point behaviour, calibration, and physiology-aligned robustness. Stratified random 60/20/20 splits were applied (the Kaggle CHB-MIT derivative lacks patient identifiers; subject leakage is acknowledged as a limitation). On the held-out test set (11,233 segments, 23 channels, 6.26 s at 256 Hz, 6.8:1 imbalance), the SSL model achieves AUROC 0.990 (95% CI: 0.985–0.994) versus 0.989 (0.983–0.994) for the baseline, with overlapping CIs confirming statistical comparability. At threshold 0.5, SSL achieves higher recall (0.951 [0.925, 0.975] versus 0.924 [0.891, 0.953]) at the cost of lower precision (0.669 [0.626, 0.713] versus 0.839 [0.799, 0.878]); non-overlapping CIs confirm the precision gap; the recall advantage has overlapping CIs; both carry alarm-fatigue implications. The baseline is better calibrated on both ECE (0.027 [0.021, 0.034] versus 0.066 [0.057, 0.075]) and Brier score. In robustness tests, SSL is more robust to sampling jitter (± 20%: 0.968 [0.960, 0.976] versus 0.960 [0.947, 0.970]) while the baseline is more robust to strong drift (amplitude 0.40: 0.970 [0.960, 0.979] versus 0.913 [0.894, 0.931]); the drift gap has non-overlapping CIs, the jitter gap marginally overlapping CIs; both trace to augmentation design. Findings inform SSL augmentation design for future EEG monitoring work.

Read PDF

Similar papers

#machine learning Preprint Sep 2026

RobustSeiz: An Open-Source Framework for Benchmarking the Robustness of EEG Seizure Detection Models

Despite strong performance on held-out electroencephalography (EEG) data, seizure detectors may fail under real-world acquisition variability, artifacts, and adversarial inputs. We introduce RobustSeiz, an open-source, model-agnostic framework that provides a standardized, reproducible protocol for stress-testing and c...

Mohammad Mohammadi, Alireza Zarei · 0 citations
Open access Sep 2026

Frequency-aware transformer networks for robust and generalizable EEG-based seizure detection

This work proposes BrainXNet, a novel multi-scale spectro-temporal attention framework that unifies local feature extraction, frequency-aware representation learning, and global temporal modeling within a single architecture and bridges the gap between high-performance experimental models and practical deployment in di...

Mostafa Gamal, Mustafa Abdel-Wanes · 0 citations
#machine learning Preprint Sep 2026

Hybrid Ensemble Learning for EEG-Based Epileptic Seizure Forecasting

A calibrated hybrid ensemble for EEG-based seizure forecasting that combines five deep learning models and three classical machine learning models through a logistic regression stacking meta-learner is proposed, evaluating the framework on CHB-MIT using strict Leave-One-Patient-Out (LOPO) cross-validation.

Mason B. Dana, Khandaker Mamun Ahmed · 0 citations
Open access Oct 2026

Uncertainty-aware few-shot epileptic seizure detection for IoMT edge devices using TinyML and Kolmogorov–Arnold networks

Epileptic seizure detection from electroencephalography (EEG) remains challenging in real-world clinical settings due to severe class imbalance, limited labeled ictal data, inter-patient variability, and the computational constraints of edge deployment. To address these challenges, this paper proposes an uncertainty-aw...

Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui et al. · 0 citations
Open access Aug 2026

Seizure detection using hierarchical temporal trend integration and self-supervised learning

Early, reliable detection of epileptic seizures from electroencephalography (EEG) remains challenging due to label scarcity, inter patient variability, and the non stationary nature of clinical recordings. This work introduces Federated Temporal Learning (FTL), an annotation efficient framework that couples a supervise...

Namitha A. R., Siddartha B K · 0 citations
Open access Oct 2026

Lightweight seizure detection with channel attention and multilayer gated recurrent unit for cross-patient EEG analysis

Real-time epileptic seizure detection from multichannel EEG signals remains a challenging clinical problem due to high inter-patient variability, severe class imbalance, and complex multi-scale ictal dynamics. Existing deep learning approaches predominantly rely on computationally intensive architectures such as Bidire...

Priyanka Soni, Linesh Raja, Vaibhav Bhatnagar et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.