Combination of expert knowledge and a genetic fuzzy inference system for automatic sleep staging

Objective: In this paper, the genetic fuzzy inference system based on expert knowledge for automatic sleep staging was developed. Methods: Eight features, including temporal and spectrum analyses of the EEG and EMG signals, were utilized as the input variables. The fuzzy rules and the fuzzy sets were constructed based on expert knowledge and the distributions of feature values at different sleep stages. Three experiments were designed to develop and evaluate the proposed system. PSGs of 32 healthy subjects and 16 subjects with insomnia were included in the experiment to develop and evaluate the proposed method. Finally, a complete sleep scoring system integrating two fuzzy inference models with robust performance on various subject groups is developed. Results: The overall agreement and kappa coefficient of this integrated system applied to PSG data from 8 subjects with good sleep efficiency, 8 subjects with poor sleep efficiency and 8 subjects with insomnia were 86.44% and 0.81, respectively. Conclusion: Due to the high performance of the proposed system, it is expected to integrate the proposed method with various PSG systems for sleep monitoring in clinical or homecare applications in the future. Significance: An automatic sleep staging system integrating knowledge of the experts in scoring of PSG data and the elasticity of fuzzy systems in reasoning and decision making is proposed and the robustness and clinical applicability of the proposed method is demonstrated on data from healthy subjects and subjects with insomnia.