Physics-informed graph neural networks for robust cross-patient epileptic seizure prediction via chimera state detection.

Overview

1. Department of Biomedical Engineering, School of Medicine, Kermanshah University of Medical Sciences, Kermanshah, Iran
2. Department of Physiology, School of Medicine, Kermanshah University of Medical Sciences, Kermanshah, Iran
3. Department of Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran

Abstract

Background: Epilepsy affects approximately 50 million individuals worldwide, with 30% experiencing drug-resistant seizures despite optimal pharmacological management. Recent computational neuroscience advances have identified chimera states—spatiotemporal patterns where synchronized and desynchronized neural dynamics coexist—as potential biomarkers preceding seizures by 15–90 minutes. However, clinical translation faces critical challenges: (1) existing detection methods require extensive manual parameter optimization limiting scalability, (2) machine learning approaches show 20–35% accuracy degradation when applied to new patients, and (3) deep learning models lack the interpretability required for clinical validation. This paper seeks to answer the question: Can integrating physics-based constraints from Kuramoto oscillator theory with graph neural networks enable automated, robust, and interpretable chimera-based seizure prediction that generalizes across patients?.

Methods: We developed HP-GNN (Hybrid Physics-Informed Graph Neural Network), a novel architecture integrating data-driven learning with Kuramoto oscillator dynamics. The framework transforms multi-channel EEG into dynamic hypergraphs capturing higher-order neural interactions through: (1) adaptive hypergraph construction using Phase Locking Values with threshold τ = 0.65 for 3-clique detection, (2) three-layer hypergraph convolutions (64 → 128 → 256 dimensions), (3) Mamba state space networks achieving linear O(T) complexity, (4) physics-informed regularization with Kuramoto dynamics (weight λ₁ = 0.03), and (5) multi-task prediction heads. We employed two-stage training: self-supervised pre-training on 844 hours of continuous EEG, followed by supervised fine- tuning. Evaluation used 4-fold cross-validation on CHB-MIT (22 pediatric patients, 182 seizures) with external validation on IEEG.org (16 adults, 87 seizures).

Results: HP-GNN achieved 84.7% chimera detection accuracy (95% CI: 82.3–87.1%), representing 9.2% improvement over Delay Differential Analysis (75.5%, p < 0.001). Seizure prediction demonstrated 89.3% sensitivity with 68.2% maintained at 90-minute horizons, achieving 0.48 false positives per hour. Cross-patient generalization reached 79.8%, improving 14.6% over graph baselines. Physics constraints reduced training requirements by 35% (achieving 80% accuracy with 260 vs 400 patient- hours). Zero-shot transfer from scalp to intracranial recordings achieved 71.3% accuracy. GNNExplainer identified critical electrodes with κ = 0.68 agreement with neurologists. Learned parameters showed biological plausibility: synchronized components at 2.3 ± 0.5 Hz (delta), desynchronized at 9.1 ± 1.3 Hz (alpha).

Conclusions: Integrating physics-based constraints with graph neural networks enables robust seizure prediction addressing key deployment barriers. The combination of improved performance, cross- patient generalization, data efficiency, and clinical interpretability positions HP-GNN as a promising foundation for clinical seizure forecasting systems.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• physionet.org/content/chbmit, at PhysioNet; found in “Data Availability”
• physionet.org/content/siena-scalp-eeg, at PhysioNet; found in “Data Availability”

Data Availability

The datasets used in this study are available as follows: 1. CHB-MIT Scalp EEG Database: Publicly available through PhysioNet at https://physionet.org/content/chbmit/1.0.0/ under the Open Data Commons Open Database License v1.0. 2. SIENA Scalp EEG Database: Publicly available through PhysioNet at https://physionet.org/content/siena-scalp-eeg/1.0.0/. 3. IEEG.org Database: Available upon institutional Data Use Agreement at https://www.ieeg.org. 4. Code and Replication Materials: All source code, trained model weights, preprocessing scripts, evaluation code, and a minimal replication dataset are available with supplementary material.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 3 authors, 5 MeSH terms, 27 references.

Cite

This paper

Amiri, M., Nedaei, E., & Makkiabadi, B. (2026). Physics-informed graph neural networks for robust cross-patient epileptic seizure prediction via chimera state detection. PloS one, 21(4), e0345470. https://doi.org/10.1371/journal.pone.0345470

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1016/j.isci.2026.117068 [code]

Directed graph neural networks with partial directed coherence for seizure prediction and epileptogenic network characterization.

Journal: iScience

In common: physionet.org/content/siena-scalp-eeg, physionet.org/content/chbmit, epilepsy, 2 references

[2] doi:10.3390/s26175623

MF-TopoNet: A Multi-Frequency Topological Neural Network for Epileptic Seizure Prediction.

Journal: Sensors (Basel, Switzerland)

In common: physionet.org/content/siena-scalp-eeg, physionet.org/content/chbmit, epilepsy, EEG, 1 reference

[3] doi:10.1371/journal.pone.0352191 [code]

Bayesian Uncertainty-aware Deep Learning with noisy labels: Tackling annotation ambiguity in EEG seizure detection.

Journal: PloS one

In common: physionet.org/content/siena-scalp-eeg, physionet.org/content/chbmit, epilepsy, EEG

[4] doi:10.1186/s40708-026-00320-2

Effiformer: a unified data-efficient vision transformer-CNN framework for interpretable epileptic seizure detection.

Journal: Brain informatics

In common: physionet.org/content/chbmit, epilepsy, EEG, clinical / translational, 2 references

[5] doi:10.1007/s40120-026-00924-0

Artificial Intelligence and Machine Learning in Pediatric Epilepsy: A Systematic Review.

Journal: Neurology and therapy

In common: physionet.org/content/chbmit, epilepsy, EEG, 1 reference

[6] doi:10.3390/s26134186

CMEpiNet: Complex-Valued Multimodal Epilepsy Detection Network Model.

Journal: Sensors (Basel, Switzerland)

In common: epilepsy, EEG, 3 references

[7] doi:10.3390/e28060599

Large-Scale Synchronization Dynamics During Epileptic Seizures: A Patient-Independent EEG Network Analysis.

Journal: Entropy (Basel, Switzerland)

In common: physionet.org/content/chbmit, epilepsy, EEG, clinical / translational

[8] doi:10.1038/s41598-026-68506-6

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

Journal: Scientific reports

In common: physionet.org/content/chbmit, epilepsy, EEG

[9] doi:10.1038/s41598-026-50003-5

Federated learning-enabled privacy-preserving framework for seizure forecasting and affective state analysis using multi-modal EEG-ECG data.

Journal: Scientific reports

In common: physionet.org/content/chbmit, epilepsy, EEG

[10] doi:10.3389/fnins.2026.1856135

Enhancing seizure prediction using a DC-SA-EBiLSTM framework with self-attention mechanism.

Journal: Frontiers in neuroscience

In common: physionet.org/content/chbmit, epilepsy, EEG

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.