SleepExplain: Explainable Non-Rapid Eye Movement and Rapid Eye Movement Sleep Stage Classification from EEG Signal

2026-06-05

AI Summary

This study addresses the challenges of accurate NREM/REM stage classification and limited interpretability in sleep disorder diagnosis by proposing SleepExplain, a novel model that systematically integrates the SHAP (SHapley Additive exPlanations) interpretability framework into sleep staging for the first time. Leveraging electroencephalogram (EEG) signals, the approach combines ensemble learning algorithms—including Random Forest, XGBoost, and Gradient Boosting—and achieves a state-of-the-art classification accuracy of 94.30% with XGBoost on public benchmark datasets. Beyond high predictive performance, SleepExplain generates physiologically meaningful explanations of feature contributions, thereby offering both clinical interpretability and diagnostic reliability essential for real-world medical applications.

Abstract

Classification of sleep stages is one of the most important diagnostic approaches for a variety of sleep-related disorders. Electroencephalography (EEG) is regarded as a powerful tool for examining the association between neurological effects and sleep phases since it correctly identifies sleep-related neurological alterations. During Non-Rapid Eye Movement (NREM) and Rapid Eye Movement (REM) sleep phases, a number of nerve and bodily functions are affected and therefore hold an important role both in their functionalities. This work aims to classify NREM and REM sleep stages from sleep EEG data and present a noble SleepExplain model, an explainable NREM and REM sleep stage classification to explain its predictions. In this work, sleep stages were classified using Random Forest, XGBoost, and Gradient Boosting ensemble classification models. Overall, we obtained an accuracy of 92.54% (Random Forest), 94.25% (Gradient Boosting), and 94.30% (XGBoost). For explainable classification model, we utilized a game theoretic approach, SHAP (SHapley Addictive exPlanations) to offer a convincing explanation for the prediction.

Problem

• sleep stage classification
• EEG
• NREM
• REM
• explainable AI

Innovation

• explainable AI
• sleep stage classification
• EEG signal
• SHAP
• ensemble learning