Automatic detection of cyclic alternating pattern (CAP) sequences in sleep: preliminary results

Abstract

Objectives: The analysis of cyclic alternating pattern (CAP) provides important microstructural information on arousal instability and on EEG synchrony modulation in the sleep process. This work presents a methodology for automatic classification of the micro-organization of human sleep EEG, using the CAP paradigm.

Methods: The classification system is composed of 3 parts: feature extraction, detection and classification. The feature extraction part is an EEG generation model-based maximum likelihood estimator. The detector part for the CAP phases A and B is done by a variable length template matched filter, while the classification criteria part is implemented on a state machine ruled-based decision system.

Results and conclusions: The preliminary results of the automatic classifier on a group of 4 middle-aged adults are presented. The high agreement between the detector and visual scoring is very promising in the achievement of a fully automated scoring system, although a more exhaustive evaluation program is needed.