Detecting seizure onset and offset times using human intelligence: A critical-transitions-based approach

2026-07-29

AI Summary

This study addresses the challenge of balancing sensitivity and specificity in seizure detection, particularly in the presence of diverse seizure morphologies, interictal discharges, and artifacts—issues often exacerbated by reliance on complex preprocessing or lack of interpretability in existing methods. Drawing on critical transition theory, the authors propose a novel, interpretable algorithm that automatically identifies seizure onset and offset times by analyzing dynamic changes in EEG voltage, without requiring elaborate preprocessing. Evaluated on rodent electrophysiological data using ROC analysis and parameter optimization, the method achieves accuracy approaching expert annotations across multiple seizure types. Notably, it yields a set of generalizable parameters that maintain high performance in cross-session testing, demonstrating strong robustness and generalization capability.

Abstract

Most existing seizure detection algorithms require extensive pre-processing of the data and rely on heuristic or currently unexplainable machine learning approaches. These approaches often struggle with balancing detection sensitivity and specificity in the presence of variable seizure morphologies, interictal epileptiform discharges, and artefacts. Here, we consider an alternative approach: our seizure detection algorithm, which is based on the concept of critical transitions and overcomes the aforementioned limitations. Specifically, we perform a receiver-operating-characteristic analysis to quantify the performance of our algorithm in terms of its agreement with expert annotations of seizure onset and offset times in the voltage recordings of seizure activity in epileptic rodents with different seizure morphologies. We demonstrate how performance depends on algorithm parameters and varies across different rodent recording sessions. We determine the optimal set of algorithm parameters for each recording session, with near expert-level performance achieved in most cases. Finally, we derive a single general set of algorithm parameters applicable across all recording sessions. The algorithm maintains its high performance in this general setting, demonstrating its versatility, robustness across varying seizure morphologies, and potential to complement machine learning algorithms.

Problem

• seizure detection
• critical transitions
• sensitivity and specificity
• seizure morphology
• artifact robustness

Innovation

• critical transitions
• seizure detection
• ROC analysis
• parameter optimization
• generalizable algorithm