Probabilistic Modelling of Sleep Stage and Apneaic Events in the University College of Dublin Database (UCDDB)

Publicly available University College of Dublin Database (UCDDB) polysomnogram (PSG) patient cohort is analyzed and classified for archetypal sleep fragmentation in the presence of obstructive sleep apnea (OSA), the most severe sleep disorder. For comparison with Bianchi et al’s analysis of the Sleep Heart Health Study (SHHS) polysomnogram cohort, we first analyze sleep stage hypnograms statically by considering Wake After Sleep Onset (WASO), Rapid Eye Movement (REM), and grouped non-REM stages (Stages 1, 2, and 3/4) probabilistic distributions. We test the universality of Bianchi et al’s multi-exponential and power law models before proposing a third model with greater physical significance: Gaussian. In the absence of a control cohort without OSA, we separate the full PSG hypnogram into apneaic and ‘normal’ components. From this analysis, we observe the rapid decay of sleep stage durations as a result of apneaic events and the fragmentation of the natural 1.5 to 2 hour sleep cycle. To refine our model of the distinctive apnea ‘fingerprint’ on sleep stages, we consider a dynamic, one step Markov Chain model for WASO, REM, and separated NREM sleep stages (Stage 1, 2, 3, and 4) as this approach gives a better measure of sleep fragmentation. Our findings demonstrate that the presence of OSA alters both static and dynamic sleep characteristics which can feed into automatic detection of sleep stage identification and apnea event detection. Significantly, the probability of remaining in REM sleep is reduced from 81.0 percent during ‘normal’ sleep to 13.7 percent following an apneaic event. We conclude by outlining immediate next steps for improving the apnea detection model for integration with our at-home automatic sleep monitoring device. Such a device will augment data collected from oversubscribed sleep clinics to address the undersampling of sleep disorder patient monitoring.