PySeizure: A single machine learning classifier framework to detect seizures in diverse datasets

2025-08-10

AI Summary

Existing epilepsy seizure detection methods exhibit poor generalizability and heavily rely on dataset-specific optimization, hindering clinical deployment. This paper proposes an open-source, dataset-agnostic unified framework that standardizes automated preprocessing, employs multiple models for independent second-level predictions, and aggregates results via majority voting—enabling plug-and-play, post-processing-free detection. The framework significantly enhances robustness and cross-center transferability of EEG-based seizure detection. Within-domain AUC scores reach 0.913 on CHB-MIT and 0.867 on TUSZ; cross-domain cross-validation yields AUCs of 0.619 and 0.768, respectively, demonstrating strong generalization. Our key contribution is the first reproducible, modular, and clinically deployable paradigm for universal epilepsy detection—establishing a reliable foundation for real-world AI-assisted neurology applications.

Technology Category

Computer Vision: Multi-modal VisionIntelligent Robots: Multimodal Perception & Sensor FusionMachine Learning: Multi-instance/Multi-view Learning

Application Category

Web Mining and Content Analysis: Large pretrained models with web dataGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsResponsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Reliable seizure detection is critical for diagnosing and managing epilepsy, yet clinical workflows remain dependent on time-consuming manual EEG interpretation. While machine learning has shown promise, existing approaches often rely on dataset-specific optimisations, limiting their real-world applicability and reproducibility. Here, we introduce an innovative, open-source machine-learning framework that enables robust and generalisable seizure detection across varied clinical datasets. We evaluate our approach on two publicly available EEG datasets that differ in patient populations and electrode configurations. To enhance robustness, the framework incorporates an automated pre-processing pipeline to standardise data and a majority voting mechanism, in which multiple models independently assess each second of EEG before reaching a final decision. We train, tune, and evaluate models within each dataset, assessing their cross-dataset transferability. Our models achieve high within-dataset performance (AUC 0.904+/-0.059 for CHB-MIT and 0.864+/-0.060 for TUSZ) and demonstrate strong generalisation across datasets despite differences in EEG setups and populations (AUC 0.615+/-0.039 for models trained on CHB-MIT and tested on TUSZ and 0.762+/-0.175 in the reverse case) without any post-processing. Furthermore, a mild post-processing improved the within-dataset results to 0.913+/-0.064 and 0.867+/-0.058 and cross-dataset results to 0.619+/-0.036 and 0.768+/-0.172. These results underscore the potential of, and essential considerations for, deploying our framework in diverse clinical settings. By making our methodology fully reproducible, we provide a foundation for advancing clinically viable, dataset-agnostic seizure detection systems. This approach has the potential for widespread adoption, complementing rather than replacing expert interpretation, and accelerating clinical integration.

Problem

• Develop a generalizable seizure detection framework for diverse EEG datasets
• Overcome dataset-specific limitations in current machine learning approaches
• Enable robust cross-dataset performance without manual post-processing

Innovation

• Open-source framework for generalisable seizure detection
• Automated pre-processing pipeline standardises diverse EEG data
• Majority voting mechanism enhances decision robustness