The complexity and variability mapping for prediction and explainability of the sleep apnea syndrome

The paper introduces a research program formulated to uncover and describe a complex nature of the sleep apnea disorders. This study include the physiological sensing and the signal processing oriented towards the mapping of a dynamical profile of physiological system represented by its complexity and variability. To reconstruct a heatmap of the dynamical features significant for triggering sleep disorders we collected a set of procedures dedicated to qualitative and quantitative depiction of the intra- and inter-events, and then adapted them to the use with a polysomnography data. Research protocol was organized with reference to the patients and modified PNEUMA model, and the COMPASS Toolbox devoted to time series exploration. The outcome novelty consists in the complementary characterization of the sleep apnea dynamics, measured at various levels of the system, but also the original statements on the sensitivity of fractal and network oriented algorithms applied to physiological data has been formulated in the report in reference to the temporal patterns encoded in polysomnography data, e.g. a detection of the central sleep apnea with the use of nasal airflow has been documented. The complementary approach proposed in the paper is a prerequisite to understand the SAS phenotyping, predict that modes and the SAS states, and formulate an efficient procedures for personalized patient care.