Automatic detection of the Cyclic Alternating Pattern of sleep and diagnosis of sleep-related pathologies (Preprint)

Abstract

BACKGROUND The Cyclic Alternating Pattern is a periodic electroencephalogram activity occurring during No Rapid Eye Movement sleep. It is a marker of sleep instability and correlated with several sleep-related pathologies. OBJECTIVE The objective of our study is to automatic detect the Cyclic Alternating Pattern of sleep and to diagnose sleep-related pathologies based on ECG and respiratory signals. METHODS Considering the connection between heart and brain of people, by statistically analysising and comparing the cardiopulmonary characteristics of people with no pathology and patients with sleep-related diseases, an automatic recognition scheme of Cyclic Alternating Pattern is proposed based on the Cardiopulmonary Resonance Indices. Using improved Hidden Markov and Random Forest, the scheme combines both the measurements of coupling state and the stability of the cardiopulmonary system during sleep. RESULTS In this article, the average recognition rate of A-phase reaches 84.67% and F1 score reaches 80.35% on the CAP Sleep Database in MIT-BIH database. CONCLUSIONS The scheme could automatically recognize the Cyclic Alternating Pattern accurately, and diagnose insomnia and narcolepsy using ECG and respiratory signals.