2020

Yan, Rui; Li, Fan; Wang, Xiaoyu; Ristaniemi, Tapani; Cong, Fengyu

Sleep scoring is a fundamental but time-consuming process in any sleep laboratory. Automatic sleep scoring is crucial and urgent to help address the increasing unmet needs for sleep research. Therefore, this paper aims to develop an automatic sleep scoring toolbox with the capability of multi-signal processing. The toolbox allows the user to choose signal types and the number of target classes. In addition, a user-friendly interface is provided to display sleep structures and related sleep parameters. The proposed approach employs several automatic processes including signal preprocessing, feature extraction and classification in order to save labor costs without compromising accuracy. For the phase of feature extraction, a huge number of features are considered including statistical characters, frequency characters, time-frequency characters, fractal characters, entropy characters and nonlinear characters. Their contribution to distinguishing between different sleep stages are compared in this article. The classifier we used for sleep stages discrimination is the random forest algorithm. The performance of the proposed approach is tested on the patients with sleep apnea by assessing accuracy, sensitivity and precision. The model achieves an accuracy of 82% to 86% for patients with varying degrees of sleep-disordered breathing, which indicates that sleep-disordered breathing does not significantly affect the performance of the proposed model. The proposed automatic scoring toolbox would alleviate the burden of the physicians, speed up sleep scoring, and expedite sleep research.