Transparency in Sleep Staging: Deep Learning Method for EEG Sleep Stage Classification with Model Interpretability
This addresses the problem of limited practicality and effectiveness in clinical sleep disorder diagnosis by providing an explainable model that aligns with expert insights, though it is incremental as it adapts existing techniques to a specific domain.
The study tackled automated sleep stage classification from single-channel EEG by developing an end-to-end deep learning model that integrates squeeze and excitation blocks with Bi-LSTM, achieving Macro-F1 scores of 82.5, 78.9, and 81.9 on SleepEDF-20, SleepEDF-78, and SHHS datasets, respectively, and enabling 8x faster training with minimal performance loss.
Automated Sleep stage classification using raw single channel EEG is a critical tool for sleep quality assessment and disorder diagnosis. However, modelling the complexity and variability inherent in this signal is a challenging task, limiting their practicality and effectiveness in clinical settings. To mitigate these challenges, this study presents an end-to-end deep learning (DL) model which integrates squeeze and excitation blocks within the residual network to extract features and stacked Bi-LSTM to understand complex temporal dependencies. A distinctive aspect of this study is the adaptation of GradCam for sleep staging, marking the first instance of an explainable DL model in this domain with alignment of its decision-making with sleep expert's insights. We evaluated our model on the publically available datasets (SleepEDF-20, SleepEDF-78, and SHHS), achieving Macro-F1 scores of 82.5, 78.9, and 81.9, respectively. Additionally, a novel training efficiency enhancement strategy was implemented by increasing stride size, leading to 8x faster training times with minimal impact on performance. Comparative analyses underscore our model outperforms all existing baselines, indicating its potential for clinical usage.