Díaz-Montiel Alan A, Zhang Richard, Lankarany Milad
Krembil Research Institute - University Health Network, Toronto, ON, M5T 0S8, Canada.
McMaster University Faculty of Health Sciences, Hamilton, ON, L8S 4L8, Canada.
Sci Rep. 2025 Jun 4;15(1):19552. doi: 10.1038/s41598-025-01882-7.
In recent years, several machine-learning (ML) solutions have been proposed to solve the problems of seizure detection, seizure phase classification, seizure prediction, and seizure onset zone (SOZ) localization, achieving excellent performance with accuracy levels above 95%. However, none of these solutions has been fully deployed in clinical settings. The primary reason has been a lack of trust from clinicians towards the complex decision-making operability of ML. More recently, research efforts have focused on systematized and generalizable frameworks of ML models that are clinician-friendly. In this paper, we propose a generalizable pipeline that leverages graph representation data structures as a flexible tool for graph neural networks. Moreover, we conducted an analysis of graph neural networks (GNN), a paradigm of artificial neural networks optimized to operate on graph-structured data, as a framework to classify seizure phases (preictal vs. ictal vs. postictal) from intracranial electroencephalographic (iEEG) data. We employed two multi-center international datasets, comprising 23 and 16 patients and 5 and 7 h of iEEG recordings. We evaluated four GNN models, with the highest performance achieving a seizure phase classification accuracy of 97%, demonstrating its potential for clinical application. Moreover, we show that by leveraging t-SNE, a statistical method for visualizing high-dimensional data, we can analyze how GNN's influence the iEEG and graph representation embedding space. We also discuss the scientific implications of our findings and provide insights into future research directions for enhancing the generalizability of ML models in clinical practice.
近年来，人们提出了几种机器学习（ML）解决方案来解决癫痫发作检测、发作期分类、发作预测和发作起始区（SOZ）定位等问题，其准确率超过95%，表现出色。然而，这些解决方案均未在临床环境中得到全面应用。主要原因是临床医生对ML复杂的决策可操作性缺乏信任。最近，研究工作集中在构建对临床医生友好的、系统化且可推广的ML模型框架。在本文中，我们提出了一种可推广的流程，该流程利用图表示数据结构作为图神经网络的灵活工具。此外，我们对图神经网络（GNN）进行了分析，GNN是一种针对图结构数据进行优化操作的人工神经网络范式，我们将其作为从颅内脑电图（iEEG）数据中分类癫痫发作期（发作前期、发作期、发作后期）的框架。我们使用了两个多中心国际数据集，分别包含23名和16名患者以及5小时和7小时的iEEG记录。我们评估了四种GNN模型，性能最佳的模型实现了97%的癫痫发作期分类准确率，证明了其临床应用潜力。此外，我们表明，通过利用t-SNE（一种用于可视化高维数据的统计方法），我们可以分析GNN如何影响iEEG和图表示嵌入空间。我们还讨论了研究结果的科学意义，并为未来研究方向提供见解，以提高ML模型在临床实践中的可推广性。
