Adversarial Spatio-Temporal Attention Networks for Epileptic Seizure Forecasting

• URL: http://arxiv.org/abs/2511.01275v1
• Date: Mon, 03 Nov 2025 06:48:54 GMT
• Title: Adversarial Spatio-Temporal Attention Networks for Epileptic Seizure Forecasting
• Authors: Zan Li, Kyongmin Yeo, Wesley Gifford, Lara Marcuse, Madeline Fields, Bülent Yener,
• Abstract summary: We present an Adversarial Attention Network that models brain connectivity and temporal neural dynamics cascaded attention blocks with alternating spatial temporal modules.<n>A continuous 90-minute pre-seizure monitoring reveals the learned EEG attention patterns that enable early detection.
• Score: 4.750750705838807
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Forecasting epileptic seizures from multivariate EEG signals represents a critical challenge in healthcare time series prediction, requiring high sensitivity, low false alarm rates, and subject-specific adaptability. We present STAN, an Adversarial Spatio-Temporal Attention Network that jointly models spatial brain connectivity and temporal neural dynamics through cascaded attention blocks with alternating spatial and temporal modules. Unlike existing approaches that assume fixed preictal durations or separately process spatial and temporal features, STAN captures bidirectional dependencies between spatial and temporal patterns through a unified cascaded architecture. Adversarial training with gradient penalty enables robust discrimination between interictal and preictal states learned from clearly defined 15-minute preictal windows. Continuous 90-minute pre-seizure monitoring reveals that the learned spatio-temporal attention patterns enable early detection: reliable alarms trigger at subject-specific times (typically 15-45 minutes before onset), reflecting the model's capacity to capture subtle preictal dynamics without requiring individualized training. Experiments on two benchmark EEG datasets (CHB-MIT scalp: 8 subjects, 46 events; MSSM intracranial: 4 subjects, 14 events) demonstrate state-of-the-art performance: 96.6% sensitivity with 0.011 false detections per hour and 94.2% sensitivity with 0.063 false detections per hour, respectively, while maintaining computational efficiency (2.3M parameters, 45 ms latency, 180 MB memory) for real-time edge deployment. Beyond epilepsy, the proposed framework provides a general paradigm for spatio-temporal forecasting in healthcare and other time series domains where individual heterogeneity and interpretability are crucial.

Related papers

• EEG-Titans: Long-Horizon Seizure Forecasting via Dual-Branch Attention and Neural Memory [0.0]
  We propose a dual-branch EEG architecture that incorporates modern neural memory mechanism for long-context modeling.<n>EEG-Titans achieves 99.46% average segment-level sensitivity across 18 subjects.<n>Results indicate that memory-augmented long-context modeling can provide robust seizure forecasting under clinically constrained evaluation.
  arXiv  Detail & Related papers  (2026-01-20T09:03:49Z)
• Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation [67.69345363409835]
  Spiking Neural Networks (SNNs) are considered naturally suited for temporal processing, with membrane potential propagation widely regarded as the core temporal modeling mechanism.<n>We design Non-Stateful (NS) models progressively removing membrane propagation to its stage-wise role. Experiments reveal a counterintuitive phenomenon: moderate removal in shallow layers improves performance, while excessive removal causes collapse.
  arXiv  Detail & Related papers  (2025-12-05T07:05:53Z)
• TARDis: Time Attenuated Representation Disentanglement for Incomplete Multi-Modal Tumor Segmentation and Classification [10.329406702659123]
  Tumor segmentation and diagnosis in contrast-enhanced Computed Tomography (CT) rely heavily on the physiological dynamics of contrast agents.<n>Existing deep learning approaches typically treat missing phases as absent independent channels, ignoring the inherent temporal continuity of hemodynamics.<n>We propose Time Attenuated Representation Disentanglement (TARDis), a novel physics-aware framework that redefines missing modalities as missing sample points on a continuous Time-Attenuation Curve.
  arXiv  Detail & Related papers  (2025-12-04T08:44:50Z)
• Spatio-Temporal Attention Network for Epileptic Seizure Prediction [4.750750705838807]
  We present a deep learning framework that learns complex-temporal correlation structures of EEG signals through a S-Temporal Attention Network (STAN) for accurate predictions of onset seizures for Epilepsy patients.<n>The framework reliably detects preictal states at least 15 minutes before an onset with patient-specific windows to 45 minutes, providing sufficient intervention time for clinical applications.
  arXiv  Detail & Related papers  (2025-10-24T01:45:25Z)
• From Prototypes to Sparse ECG Explanations: SHAP-Driven Counterfactuals for Multivariate Time-Series Multi-class Classification [8.113866195465976]
  We propose a prototype-driven framework for generating sparse counterfactual explanations tailored to 12-lead ECG classification models.<n>Our method employs SHAP-based thresholds to identify critical signal segments and convert them into interval rules.<n>We evaluate three variants of our approach, Original, Sparse, and Aligned Sparse, with class-specific performance ranging from 98.9% validity for MI to challenges with hypertrophy (HYP) detection.
  arXiv  Detail & Related papers  (2025-10-22T12:09:50Z)
• MEET-Sepsis: Multi-Endogenous-View Enhanced Time-Series Representation Learning for Early Sepsis Prediction [50.74903497515021]
  Sepsis is a life-threatening infectious syndrome associated with high mortality in intensive care units (ICUs)<n>Early and accurate sepsis prediction (SP) is critical for timely intervention, yet remains challenging due to subtle early manifestations and rapidly escalating mortality.<n>This paper introduces a Multi-Endogenous-view Representation Enhancement (MERE) mechanism to construct enriched feature views, coupled with a Cascaded Dual-convolution Time-series Attention (CDTA) module for temporal representation learning.<n>The proposed MEET-Sepsis framework achieves competitive prediction accuracy using only 20% of the ICU monitoring time required by SOTA methods, significantly advancing
  arXiv  Detail & Related papers  (2025-10-13T13:38:29Z)
• EEG-Based Inter-Patient Epileptic Seizure Detection Combining Domain Adversarial Training with CNN-BiLSTM Network [1.9662978733004604]
  We propose a detection framework combining domain adversarial training with a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM)<n> evaluation using EEG recordings from 20 patients with focal epilepsy demonstrated superior performance over non-adversarial methods.<n>The integration of adversarial training with temporal modeling enables robust cross-patient seizure detection.
  arXiv  Detail & Related papers  (2025-05-21T07:27:55Z)
• CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis [50.56875995511431]
  We introduce a Cross-Modal Temporal Pattern Discovery (CTPD) framework, designed to efficiently extract meaningful cross-modal temporal patterns from multimodal EHR data.<n>Our approach introduces shared initial temporal pattern representations which are refined using slot attention to generate temporal semantic embeddings.
  arXiv  Detail & Related papers  (2024-11-01T15:54:07Z)
• SPIRIT: Low Power Seizure Prediction using Unsupervised Online-Learning and Zoom Analog Frontends [0.0]
  This work presents SPIRIT: eight-gradient-based Predictor with Integrated Retraining and In situ accuracy Tuning. SPIRIT is a complete system-on-a-chip (SoC) integrating an unsupervised online-learning seizure prediction classifier with 14.4 uW, 0.057 mm2, 90.5 dB dynamic range, Zoom Analog Frontends. Through its online learning algorithm, prediction accuracy improves by up to 15%, and prediction times extend by up to 7x, without any external intervention.
  arXiv  Detail & Related papers  (2024-09-07T14:30:14Z)
• REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates [54.96885726053036]
  This paper introduces a novel graph-based residual state update mechanism (REST) for real-time EEG signal analysis. By leveraging a combination of graph neural networks and recurrent structures, REST efficiently captures both non-Euclidean geometry and temporal dependencies within EEG data. Our model demonstrates high accuracy in both seizure detection and classification tasks.
  arXiv  Detail & Related papers  (2024-06-03T16:30:19Z)
• Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality [39.476378833827184]
  Anomaly detection in dynamic graphs presents a significant challenge due to the temporal evolution of graph structures and attributes. We introduce a novel spatial- temporal memories-enhanced graph autoencoder (STRIPE) STRIPE significantly outperforms existing methods with 5.8% improvement in AUC scores and 4.62X faster in training time.
  arXiv  Detail & Related papers  (2024-03-14T02:26:10Z)
• Continuous time recurrent neural networks: overview and application to forecasting blood glucose in the intensive care unit [56.801856519460465]
  Continuous time autoregressive recurrent neural networks (CTRNNs) are a deep learning model that account for irregular observations. We demonstrate the application of these models to probabilistic forecasting of blood glucose in a critical care setting.
  arXiv  Detail & Related papers  (2023-04-14T09:39:06Z)
• Designing A Clinically Applicable Deep Recurrent Model to Identify Neuropsychiatric Symptoms in People Living with Dementia Using In-Home Monitoring Data [52.40058724040671]
  Agitation is one of the neuropsychiatric symptoms with high prevalence in dementia. Detecting agitation episodes can assist in providing People Living with Dementia (PLWD) with early and timely interventions. This preliminary study presents a supervised learning model to analyse the risk of agitation in PLWD using in-home monitoring data.
  arXiv  Detail & Related papers  (2021-10-19T11:45:01Z)
• SOUL: An Energy-Efficient Unsupervised Online Learning Seizure Detection Classifier [68.8204255655161]
  Implantable devices that record neural activity and detect seizures have been adopted to issue warnings or trigger neurostimulation to suppress seizures. For an implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to neural signal drifts. SOUL was fabricated in TSMC's 28 nm process occupying 0.1 mm2 and achieves 1.5 nJ/classification energy efficiency, which is at least 24x more efficient than state-of-the-art.
  arXiv  Detail & Related papers  (2021-10-01T23:01:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.