Kunying Meng

Epilepsy is a complex neurological disorder characterized by nonlinear dynamic interactions among multiple brain regions. The unscented Kalman Filter (UKF), a high-precision algorithm for nonlinear state and parameter estimation, has recently gained prominence in epilepsy research as it infers latent physiological parameters from electrophysiological signals to reveal the underlying seizure mechanisms. This review provides a comprehensive overview of recent progress in applying UKF to epileptic dynamics modeling and signal analysis, focusing on three major aspects: parameter estimation and model optimization based on neural computational models, seizure detection and prediction, and closed-loop control for seizure intervention. Studies have demonstrated that UKF can robustly reconstruct neuronal dynamics under noise and nonstationary conditions, providing real-time tracking of seizure evolution and contributing to a unified framework that integrates modeling, signal interpretation, and intervention. Despite these advances, important challenges remain, including noise covariance selection, high-dimensional parameter estimation, large-scale network modeling, and limited clinical validation. Future research should focus on adaptive mechanisms, improved multi-parameter estimation, and broader validation using multimodal data and real-patient cohorts. Overall, UKF has shown considerable promise as a model-based framework for epilepsy research and, more broadly, as an interpretable engineering approach for latent neural-state estimation from noisy physiological signals, although broader clinical evidence and further methodological refinement are still required before it can be considered a clinically mature framework.

The accurate prediction of epileptic seizures is a significant challenge in the field of epilepsy. Despite numerous studies devoted to improving the prediction accuracy, there are still some difficulties in the application of current methods in clinical practice, such as high computational cost, poor real-time performance, and over-reliance on labeled data. To address these issues, a real-time seizure prediction method with spatio-temporal information transfer learning (RTSPM-STITL) has been proposed in this study. In the RTSPM-STITL method, the human brain is regarded as a time-varying high-dimensional neurodynamic system, in which epileptic seizures are viewed as state transitions caused by time-varying system parameters. Specifically, the spatio-temporal information transfer (STIT) model is firstly constructed by the recurrent neural network (RNN) and trained by the Force Learning (a realtime learning mechanism). Then the trained STIT model is utilized to transform the high-dimensional neurodynamic system data into low-dimensional time series to capture the dynamic features of epileptic seizures. Also, the critical slowing down effect (CSD) of the dynamic features of epileptic seizures is utilized to detect seizure warning signals. The experimental results demonstrate that the proposed method can achieve higher accuracy and sensitivity without labeled data on both the CHB-MIT and Siena scalp EEG databases. Especially, the parameters of the STIT model can be updated in real-time based on patient data, without iterative training. More importantly, the STIT model can maintain high sensitivity and accuracy with only 48400 parameters, which is reduced by more than 91% compared with contrast models in this experiment. Therefore, the proposed method can significantly reduce the computational cost and accurately predict epileptic seizures, as well as with high real-time, practicality, applicability, and interpretability.