Sleep in the Intensive Care Unit through the Lens of Breathing and Heart Rate Variability: A Cross-Sectional Study

Background. Full polysomnography, the gold standard of sleep measurement, is impractical for widespread use in the intensive care unit (ICU). Wrist-worn actigraphy and subjective sleep assessments do not measure sleep physiology adequately. Here, we explore the feasibility of estimating conventional sleep indices in the ICU with heart rate variability (HRV) and respiration signals using artificial intelligence methods. Methods. We used deep learning models to stage sleep with HRV (through electrocardiogram) and respiratory effort (through a wearable belt) signals in critically ill adult patients admitted to surgical and medical ICUs, and in covariate-matched sleep laboratory patients. We analyzed the agreement of the determined sleep stages between the HRV- and breathing-based models, computed sleep indices, and quantified breathing variables during sleep. Results. We studied 102 adult patients in the ICU across multiple days and nights, and 220 patients in a clinical sleep laboratory. We found that sleep stages predicted by HRV- and breathing-based models showed agreement in 60% of the ICU data and in 81% of the sleep laboratory data. In the ICU, deep NREM (N2 + N3) proportion of total sleep duration was reduced (ICU 39%, sleep laboratory 57%, p<0.01), REM proportion showed heavy-tailed distribution, and the number of wake transitions per hour of sleep (median = 3.6) was comparable to sleep laboratory patients with sleep-disordered breathing (median = 3.9). Sleep in the ICU was also fragmented, with 38% of sleep occurring during daytime hours. Finally, patients in the ICU showed faster and less variable breathing patterns compared to sleep laboratory patients. Conclusions. Cardiovascular and respiratory signals encode sleep state information, which can be utilized to measure sleep state in the ICU. Using these easily measurable variables can provide automated information about sleep in the ICU.