AUTHOR=Ganglberger Wolfgang , Krishnamurthy Parimala Velpula , Quadri Syed A. , Tesh Ryan A. , Bucklin Abigail A. , Adra Noor , Da Silva Cardoso Madalena , Leone Michael J. , Hemmige Aashritha , Rajan Subapriya , Panneerselvam Ezhil , Paixao Luis , Higgins Jasmine , Ayub Muhammad Abubakar , Shao Yu-Ping , Coughlin Brian , Sun Haoqi , Ye Elissa M. , Cash Sydney S. , Thompson B. Taylor , Akeju Oluwaseun , Kuller David , Thomas Robert J. , Westover M. Brandon 

TITLE=Sleep staging in the ICU with heart rate variability and breathing signals. An exploratory cross-sectional study using deep neural networks

JOURNAL=Frontiers in Network Physiology

VOLUME=3

YEAR=2023

URL=https://www.frontiersin.org/journals/network-physiology/articles/10.3389/fnetp.2023.1120390

DOI=10.3389/fnetp.2023.1120390

ISSN=2674-0109

ABSTRACT=<p><bold>Introduction:</bold> To measure sleep in the intensive care unit (ICU), full polysomnography is impractical, while activity monitoring and subjective assessments are severely confounded. However, sleep is an intensely networked state, and reflected in numerous signals. 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</p><p><bold>Methods:</bold> 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 age and sex-matched sleep laboratory patients</p><p><bold>Results:</bold> 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%, <italic>p</italic> &lt; 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</p><p><bold>Conclusion:</bold> The cardiovascular and respiratory networks encode sleep state information, which, together with artificial intelligence methods, can be utilized to measure sleep state in the ICU</p>