Early Warning Prediction with Automatic Labeling in Epilepsy Patients

TL;DR

The paper addresses the problem of early seizure prediction from EEG when labels are noisy and prediction horizons are long. It introduces a bi-level meta-learning framework with a meta-network for automatic labeling of noisy data (meta-label correction) and a main network for classification, augmented by tipping-point–theoretic early warning signals. A concrete early warning indicator $I_P = f_{oldsymbol{\omega}}(X)$ is derived from the main network and shown to precede variance-based cues in signaling imminent seizures. Experiments on scalp EEG data from epilepsy patients demonstrate significant accuracy gains over LSTM and ResNet baselines across horizons and provide earlier warning signals, highlighting the approach's data efficiency and practical potential.

Abstract

Early warning for epilepsy patients is crucial for their safety and well-being, in particular to prevent or minimize the severity of seizures. Through the patients' EEG data, we propose a meta learning framework to improve the prediction of early ictal signals. The proposed bi-level optimization framework can help automatically label noisy data at the early ictal stage, as well as optimize the training accuracy of the backbone model. To validate our approach, we conduct a series of experiments to predict seizure onset in various long-term windows, with LSTM and ResNet implemented as the baseline models. Our study demonstrates that not only the ictal prediction accuracy obtained by meta learning is significantly improved, but also the resulting model captures some intrinsic patterns of the noisy data that a single backbone model could not learn. As a result, the predicted probability generated by the meta network serves as a highly effective early warning indicator.

Figures (4)

• Figure 1: The framework of meta label generation model.
• Figure 2: A sample of our EEG data: (a) time series for the electrodes; the red part shows seizure states, and the gray part represents rest states; (b) variance of the EEG data.
• Figure 3: Predicted ictal probabilities (blue lines) and true ictal onset moments (red dashed lines): (a-c) for $|X|=20$ and $|Y|=5$; (d-f) for $|X|=20$ and $|Y|=10$.
• Figure 4: A comparison of the proposed indicator $I_{P}$ (red solid line) with the variance indicator (blue dashed line) for EEG data: (a) $|X|=20$, $|Y|=5$; (b) $|X|=20$, $Y=10$.