Automated Sleep Spindle Analysis in Epilepsy EEG Using Deep Learning

Sleep spindles, together with K-complexes, are hallmark oscillatory events observed in electroencephalographic (EEG) recordings during stage N2 sleep. Alterations in spindle characteristics, including frequency, amplitude, duration, and density, are frequently reported in epilepsy and may reflect underlying disturbances in thalamocortical network function. Quantitative analysis of these alterations has the potential to improve our understanding of epileptiform activity and support the development of clinically useful biomarkers. In this work, we present an automated framework for sleep spindle analysis in EEG recordings from both healthy subjects and patients with epilepsy. The framework integrates deep learning architectures (1D U-Net, SlumberNet, and SEED) with statistical evaluation methods to address two complementary tasks: (i) spindle segmentation and (ii) direct regression-based prediction of spindle characteristics. The proposed approach was validated on two datasets: the open-access Montreal Archive of Sleep Studies (MASS) and a custom clinical database of pediatric epilepsy patients acquired at the Video-EEG Laboratory “Genomed” (Moscow, Russia). Our results demonstrate that while both convolutional and hybrid recurrent–convolutional architectures achieve comparable overall F1-scores, their precision–recall profiles differ substantially. This enables a principled, context-specific selection of models, with U-Net favoring high sensitivity and SEED favoring high precision. Moreover, we show that segmentation-based pipelines consistently outperform direct regression (segmentation-free) approaches for characteristic prediction. These findings provide methodological guidance for the optimal deployment of deep learning models in sleep spindle analysis and establish a foundation for robust, automated, and clinician-independent EEG biomarkers in epilepsy.