Dataset Information

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

ABSTRACT: Introduction: 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 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 age and sex-matched sleep laboratory patients 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 Conclusion: 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.

SUBMITTER: Ganglberger W

PROVIDER: S-EPMC10013021 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Ganglberger Wolfgang W Krishnamurthy Parimala Velpula PV Quadri Syed A SA Tesh Ryan A RA Bucklin Abigail A AA Adra Noor N Da Silva Cardoso Madalena M Leone Michael J MJ Hemmige Aashritha A Rajan Subapriya S Panneerselvam Ezhil E Paixao Luis L Higgins Jasmine J Ayub Muhammad Abubakar MA Shao Yu-Ping YP Coughlin Brian B Sun Haoqi H Ye Elissa M EM Cash Sydney S SS Thompson B Taylor BT Akeju Oluwaseun O Kuller David D Thomas Robert J RJ Westover M Brandon MB

Frontiers in network physiology 20230227

<b>Introduction:</b> 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 <b>Methods:</b> We used deep learning models to s ...[more]

PMID: 36926545

Similar Datasets

Project description:Background: Performance of wrist actigraphy in assessing sleep not only depends on the sensor technology of the actigraph hardware but also on the attributes of the interpretative algorithm (IA). The objective of our research was to improve assessment of sleep quality, relative to existing IAs, through development of a novel IA using deep learning methods, utilizing as input activity count and heart rate variability (HRV) metrics of different window length (number of epochs of data). Methods: Simultaneously recorded polysomnography (PSG) and wrist actigraphy data of 222 participants were utilized. Classic deep learning models were applied to: (a) activity count alone (without HRV), (b) activity count + HRV (30-s window), (c) activity count + HRV (3-min window), and (d) activity count + HRV (5-min window) to ascertain the best set of inputs. A novel deep learning model (Haghayegh Algorithm, HA), founded on best set of inputs, was developed, and its sleep scoring performance was then compared with the most popular University of California San Diego (UCSD) and Actiwatch proprietary IAs. Results: Activity count combined with HRV metrics calculated per 5-min window produced highest agreement with PSG. HA showed 84.5% accuracy (5.3-6.2% higher than comparator IAs), 89.5% sensitivity (6.2% higher than UCSD IA and 6% lower than Actiwatch proprietary IA), 70.0% specificity (8.2-34.3% higher than comparator IAs), and 58.7% Kappa agreement (16-23% higher than comparator IAs) in detecting sleep epochs. HA did not differ significantly from PSG in deriving sleep parameters-sleep efficiency, total sleep time, sleep onset latency, and wake after sleep onset; moreover, bias and mean absolute error of the HA model in estimating them was less than the comparator IAs. HA showed, respectively, 40.9% and 54.0% Kappa agreement with PSG in detecting rapid and non-rapid eye movement (REM and NREM) epochs. Conclusions: The HA model simultaneously incorporating activity count and HRV metrics calculated per 5-min window demonstrates significantly better sleep scoring performance than existing popular IAs.

Project description:BackgroundMaternal sleep-disordered breathing is associated with adverse pregnancy outcomes and is considered to be deleterious to the developing fetus. Maternal obesity potentiates sleep-disordered breathing, which, in turn, may contribute to the effect of maternal obesity on adverse fetal outcomes. However, only a few empirical studies have evaluated the contemporaneous effects of maternal sleep-disordered breathing events on fetal well-being. These events include apnea and hypopnea with accompanying desaturations in oxyhemoglobin.ObjectiveThis study aimed to reconcile contradictory findings on the associations between maternal apnea or hypopnea events and clinical indicators of fetal compromise. It also sought to broaden the knowledge base by examining the fetal heart rate and heart rate variability before, during, and after episodes of maternal apnea or hypopnea. To accomplish this, we employed overnight polysomnography, the gold standard for ascertaining maternal sleep-disordered breathing, and synchronized it with continuous fetal electrocardiography.Study designA total of 84 pregnant women with obesity (body mass index >30 kg/m2) participated in laboratory-based polysomnography with digitized fetal electrocardiography recordings during or near 36 weeks of gestation. Sleep was recorded, on average, for 7 hours. Decelerations in fetal heart rate were identified. Fetal heart rate and heart rate variability were quantified before, during, and after each apnea or hypopnea event. Event-level intensity (desaturation magnitude, duration, and nadir O2 saturation level) and person-level characteristics based on the full overnight recording (apnea-hypopnea index, mean O2 saturation, and O2 saturation variability) were analyzed as potential moderators using linear mixed effects models.ResultsA total of 2936 sleep-disordered breathing events were identified, distributed among all but 2 participants. On average, participants exhibited 8.7 episodes of apnea or hypopnea per hour (mean desaturation duration, 19.1 seconds; mean O2 saturation nadir, 86.6% per episode); nearly half (n=39) of the participants met the criteria for obstructive sleep apnea. Only 45 of 2936 apnea or hypopnea events were followed by decelerations (1.5%). Conversely, most (n=333, 88%) of the 378 observed decelerations, including the prolonged ones, did not follow an apnea or a hypopnea event. Maternal sleep-disordered breathing burden, body mass index, and fetal sex were unrelated to the number of decelerations. Fetal heart rate variability increased during events of maternal apnea or hypopnea but returned to initial levels soon thereafter. There was a dose-response association between the size of the increase in fetal heart rate variability and the maternal apnea-hypopnea index, event duration, and desaturation depth. Longer desaturations were associated with a decreased likelihood of the variability returning to baseline levels after the event. The mean fetal heart rate did not change during episodes of maternal apnea or hypopnea.ConclusionEpisodes of maternal sleep apnea and hypopnea did not evoke decelerations in the fetal heart rate despite the predisposing risk factors that accompany maternal obesity. The significance of the modest transitory increase in fetal heart rate variability in response to apnea and hypopnea episodes is not clear but may reflect compensatory, delimited autonomic responses to momentarily adverse conditions. This study found no evidence that episodes of maternal sleep-disordered breathing pose an immediate threat, as reflected in fetal heart rate responses, to the near-term fetus.

Project description:Sleep is an important indicator of a person's health, and its accurate and cost-effective quantification is of great value in healthcare. The gold standard for sleep assessment and the clinical diagnosis of sleep disorders is polysomnography (PSG). However, PSG requires an overnight clinic visit and trained technicians to score the obtained multimodality data. Wrist-worn consumer devices, such as smartwatches, are a promising alternative to PSG because of their small form factor, continuous monitoring capability, and popularity. Unlike PSG, however, wearables-derived data are noisier and far less information-rich because of the fewer number of modalities and less accurate measurements due to their small form factor. Given these challenges, most consumer devices perform two-stage (i.e., sleep-wake) classification, which is inadequate for deep insights into a person's sleep health. The challenging multi-class (three, four, or five-class) staging of sleep using data from wrist-worn wearables remains unresolved. The difference in the data quality between consumer-grade wearables and lab-grade clinical equipment is the motivation behind this study. In this paper, we present an artificial intelligence (AI) technique termed sequence-to-sequence LSTM for automated mobile sleep staging (SLAMSS), which can perform three-class (wake, NREM, REM) and four-class (wake, light, deep, REM) sleep classification from activity (i.e., wrist-accelerometry-derived locomotion) and two coarse heart rate measures-both of which can be reliably obtained from a consumer-grade wrist-wearable device. Our method relies on raw time-series datasets and obviates the need for manual feature selection. We validated our model using actigraphy and coarse heart rate data from two independent study populations: the Multi-Ethnic Study of Atherosclerosis (MESA; N = 808) cohort and the Osteoporotic Fractures in Men (MrOS; N = 817) cohort. SLAMSS achieves an overall accuracy of 79%, weighted F1 score of 0.80, 77% sensitivity, and 89% specificity for three-class sleep staging and an overall accuracy of 70-72%, weighted F1 score of 0.72-0.73, 64-66% sensitivity, and 89-90% specificity for four-class sleep staging in the MESA cohort. It yielded an overall accuracy of 77%, weighted F1 score of 0.77, 74% sensitivity, and 88% specificity for three-class sleep staging and an overall accuracy of 68-69%, weighted F1 score of 0.68-0.69, 60-63% sensitivity, and 88-89% specificity for four-class sleep staging in the MrOS cohort. These results were achieved with feature-poor inputs with a low temporal resolution. In addition, we extended our three-class staging model to an unrelated Apple Watch dataset. Importantly, SLAMSS predicts the duration of each sleep stage with high accuracy. This is especially significant for four-class sleep staging, where deep sleep is severely underrepresented. We show that, by appropriately choosing the loss function to address the inherent class imbalance, our method can accurately estimate deep sleep time (SLAMSS/MESA: 0.61±0.69 hours, PSG/MESA ground truth: 0.60±0.60 hours; SLAMSS/MrOS: 0.53±0.66 hours, PSG/MrOS ground truth: 0.55±0.57 hours;). Deep sleep quality and quantity are vital metrics and early indicators for a number of diseases. Our method, which enables accurate deep sleep estimation from wearables-derived data, is therefore promising for a variety of clinical applications requiring long-term deep sleep monitoring.

Project description:BackgroundLongitudinal monitoring of vital signs provides a method for identifying changes to general health in an individual, particularly in older adults. The nocturnal sleep period provides a convenient opportunity to assess vital signs. Contactless technologies that can be embedded into the bedroom environment are unintrusive and burdenless and have the potential to enable seamless monitoring of vital signs. To realize this potential, these technologies need to be evaluated against gold standard measures and in relevant populations.ObjectiveWe aimed to evaluate the accuracy of heart rate and breathing rate measurements of 3 contactless technologies (2 undermattress trackers, Withings Sleep Analyzer [WSA] and Emfit QS [Emfit]; and a bedside radar, Somnofy) in a sleep laboratory environment and assess their potential to capture vital signs in a real-world setting.MethodsData were collected from 35 community-dwelling older adults aged between 65 and 83 (mean 70.8, SD 4.9) years (men: n=21, 60%) during a 1-night clinical polysomnography (PSG) test in a sleep laboratory, preceded by 7 to 14 days of data collection at home. Several of the participants (20/35, 57%) had health conditions, including type 2 diabetes, hypertension, obesity, and arthritis, and 49% (17) had moderate to severe sleep apnea, while 29% (n=10) had periodic leg movement disorder. The undermattress trackers provided estimates of both heart rate and breathing rate, while the bedside radar provided only the breathing rate. The accuracy of the heart rate and breathing rate estimated by the devices was compared with PSG electrocardiogram-derived heart rate (beats per minute) and respiratory inductance plethysmography thorax-derived breathing rate (cycles per minute), respectively. We also evaluated breathing disturbance indexes of snoring and the apnea-hypopnea index, available from the WSA.ResultsAll 3 contactless technologies provided acceptable accuracy in estimating heart rate (mean absolute error <2.12 beats per minute and mean absolute percentage error <5%) and breathing rate (mean absolute error ≤1.6 cycles per minute and mean absolute percentage error <12%) at 1-minute resolution. All 3 contactless technologies were able to capture changes in heart rate and breathing rate across the sleep period. The WSA snoring and breathing disturbance estimates were also accurate compared with PSG estimates (WSA snore: r2=0.76; P<.001; WSA apnea-hypopnea index: r2=0.59; P<.001).ConclusionsContactless technologies offer an unintrusive alternative to conventional wearable technologies for reliable monitoring of heart rate, breathing rate, and sleep apnea in community-dwelling older adults at scale. They enable the assessment of night-to-night variation in these vital signs, which may allow the identification of acute changes in health, and longitudinal monitoring, which may provide insight into health trajectories.International registered report identifier (irrid)RR2-10.3390/clockssleep6010010.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets