LAUSR

STUDY OBJECTIVES Sleep stability can be studied by evaluating the Cyclic Alternating Pattern (CAP) in electroencephalogram signals. The present study presents a novel approach for assessing sleep stability, developing an index based on the CAP A-phase characteristics to display a sleep stability profile for a whole night's sleep. METHODS Two ensemble classifiers were developed to automatically score the signals, one for "A-phase" and the other for "non-rapid eye movement" estimation. Both were based on three one-dimension convolutional neural networks. Six different inputs were produced from the electroencephalogram signal to feed the ensembles' classifiers. A proposed heuristic-oriented search algorithm individually tuned the classifiers' structures. The outputs of the two ensembles were combined to estimate the A-Phase Index (API). The models can also assess the A-phase subtypes, their API, and the CAP cycles and rate. RESULTS Four dataset variations were considered, examining healthy and sleep-disordered subjects. The A-phase average estimation's accuracy, sensitivity, and specificity range was 82%-87%, 72%-80%, and 82-88%, respectively. A similar performance was attained for the A-phase subtype's assessments, with an accuracy range of 82%-88%. Furthermore, in the examined dataset's variations, the API metric's average error varied from 0.15 to 0.25 (with a median range of 0.11-0.24). These results were attained without manually removing wake or rapid eye movement periods, leading to a methodology suitable to produce a fully automatic CAP scoring algorithm. CONCLUSIONS Metrics based on API can be understood as a new view for CAP analysis, where the goal is to produce and examine a sleep stability profile.