Novel Digital Markers of Sleep Dynamics: A Causal Inference Approach Revealing Age and Gender Phenotypes in Obstructive Sleep Apnea
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Most individuals with sleep-disorders remain undiagnosed due to unawareness of symptoms or the high cost of polysomno-graphic (PSG) studies, impacting quality of life. Despite evidence that sleep-disorders alter sleep-stage-dynamics, clinical practice resists including these parameters in PSG-reports. We introduce a novel digital sleep-fingerprint , leveraging the matrix of sleep-stage-transition-proportions, enabling the derivation of several novel digital-markers and investigation of dynamics mechanisms. Using causal inference we address confounding in an observational clinical database and estimate personalized markers across ages, genders, and Obstructive-Sleep-Apnea (OSA) severities. Notably, our approach adjusts for five categories of sleep-wake-related-comorbidities, an aspect ignored in existing research, impacting 48.6% of OSA-subjects in our data. Key markers proposed, including NREM-REM-oscillations and sleep-stage-specific-fragmentations, were significantly increased across all OSA-severities and demographics. We also identified several OSA-gender-phenotypes, suggesting higher vulnerability of females to awakening and REM-sleep disruptions. Considering advances in automated-sleep-scoring and wearables, our approach can enable novel, low-cost screening tools.