A Machine Learning Model for Obstructive Sleep Apnea Detection Using Ensemble Learning and Single-Lead EEG Signal Data

Sleep is crucial for cognitive and physical functions, and sleep disorders such as obstructive sleep apnea (OSA) can significantly affect a person’s health. Polysomnography is the gold standard for diagnosing OSA, but despite its effectiveness, it is time-consuming and prone to human errors. To address this issue, this article proposes an ensemble expert system for OSA detection—II (EESOSAD-II) that leverages the single-channel (C4-A1) electroencephalography (EEG) signal and an ensemble learning model. The proposed model uses discrete wavelet transform (DWT) with db8 for efficient EEG subband separation and statistical feature extraction. To enhance the data quality, the proposed model incorporates a Gaussian filter for feature smoothing and an isolation forest (IF) for outlier treatment. To further enhance the preprocessing pipeline, recursive feature elimination (RFE) is used for suboptimal feature set selection, and the extra tree classifier is used for efficient classification of apnea and nonapnea events. The performance of the proposed model is evaluated using multiple evaluation metrics such as precision, recall, accuracy,
$F1$
-score, and ROC–AUC curve for detailed analytical and benchmark comparison. The verification result shows that the proposed model achieved an average accuracy of 86% in comparatively optimized computational time than the state-of-the-art feature selection techniques. Furthermore, the EESOSAD-II outperformed the benchmark OSA detection model with optimal performance margin and achieved efficient performance results.