Network neuroscience, especially causal brain network, has facilitated drug-resistant epilepsy (DRE) studies, while surgical success rate in patients with DRE is still limited, varying from 30% $\sim ~70$ %. Predicting surgical outcomes can provide additional guidance to adjust treatment plans in time for poorly predicted curative effects. In this retrospective study, we aim to systematically explore biomarkers for surgical outcomes by causal brain network methods and multicenter datasets. Electrocorticogram (ECoG) recordings from 17 DRE patients with 58 seizures were included. Ictal ECoG within clinically annotated epileptogenic zone (EZ) and non-epileptogenic zone (NEZ) were separately computed using six different algorithms to construct causal brain networks. All the brain network results were divided into two groups, successful and failed surgeries. Statistical results based on the Mann-Whitney-U-test show that: causal connectivity of $\alpha $ -frequency band ( $8~\sim ~13$ Hz) in EZ calculated by convergent cross mapping (CCM) gains the most significant differences between the surgical success and failure groups, with a P value of 7.85e-08 and Cohen’s d effect size of 0.77. CCM-defined EZ brain network can also distinguish the successful and failed surgeries considering clinical covariates (clinical centers, DRE types) with ${P}\lt {0}.{001}$ . Based on the brain network features, machine learning models were developed to predict the surgical outcomes. Among them, the SVM classifier with Gaussian kernel function and Bayesian optimization demonstrates the highest average accuracy of 84.48% by 5-fold cross-validation, further indicating that the CCM-defined EZ brain network is a reliable biomarker for predicting DRE surgical outcomes.

Sleep staging plays a critical role in evaluating the quality of sleep. Currently, most studies are either suffering from dramatic performance drops when coping with varying input modalities or unable to handle heterogeneous signals. To handle heterogeneous signals and guarantee favorable sleep staging performance when a single modality is available, a pseudo-siamese neural network (PSN) to incorporate electroencephalography (EEG), electrooculography (EOG) characteristics is proposed (PSEENet). PSEENet consists of two parts, spatial mapping modules (SMMs) and a weight-shared classifier. SMMs are used to extract high-dimensional features. Meanwhile, joint linkages among multi-modalities are provided by quantifying the similarity of features. Finally, with the cooperation of heterogeneous characteristics, associations within various sleep stages can be established by the classifier. The evaluation of the model is validated on two public datasets, namely, Montreal Archive of Sleep Studies (MASS) and SleepEDFX, and one clinical dataset from Huashan Hospital of Fudan University (HSFU). Experimental results show that the model can handle heterogeneous signals, provide superior results under multimodal signals and show good performance with single modality. PSEENet obtains accuracy of 79.1%, 82.1% with EEG, EEG and EOG on Sleep-EDFX, and significantly improves the accuracy with EOG from 73.7% to 76% by introducing similarity information.

Drug-resistant epilepsy (DRE) affects approximately 30% of epilepsy patients, with surgical cure rates below 70%. This challenge drives a fundamental paradigm shift from localizing a discrete epileptogenic zone toward characterizing and modulating the dysfunctional brain networks that initiate and propagate seizures. This review critically synthesizes how computational neuroelectrophysiology and artificial intelligence (AI) converge to propel this shift. We chart the trajectory from quantifying local biomarkers, including high-frequency oscillations and excitation–inhibition balance metrics, to mapping the topological properties of epileptic networks through functional and effective connectivity. The integration of these network features with AI techniques, particularly spatiotemporal deep learning architectures, has demonstrated significant potential for enhancing both the localization of the epileptogenic network and the prediction of postoperative outcomes. However, the translation of this network-centric paradigm into clinical practice remains constrained by several challenges, including spatial sampling bias, the inherent label instability of surgical outcomes, and the ‘black-box’ interpretability crisis. Future directions must emphasize EEG foundation models, causal AI, and the development of interactive multimodal AI agents. The convergence of mechanism-driven network models and data-driven AI frameworks promises a new era of personalized, network-guided therapy for DRE.