scholarly journals Dexmedetomidine-induced deep sedation mimics non-rapid eye movement stage 3 sleep: large-scale validation using machine learning

SLEEP ◽  
2020 ◽  
Author(s):  
Sowmya M Ramaswamy ◽  
Maud A S Weerink ◽  
Michel M R F Struys ◽  
Sunil B Nagaraj
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Eye Movement ◽  
Large Scale ◽  
Deep Sedation ◽  
Sleep Eeg ◽  
Rapid Eye Movement ◽  
Sleep Patterns ◽  
Natural Sleep ◽  
Eeg Recordings

Abstract Study Objectives Dexmedetomidine-induced electroencephalogram (EEG) patterns during deep sedation are comparable with natural sleep patterns. Using large-scale EEG recordings and machine learning techniques, we investigated whether dexmedetomidine-induced deep sedation indeed mimics natural sleep patterns. Methods We used EEG recordings from three sources in this study: 8,707 overnight sleep EEG and 30 dexmedetomidine clinical trial EEG. Dexmedetomidine-induced sedation levels were assessed using the Modified Observer’s Assessment of Alertness/Sedation (MOAA/S) score. We extracted 22 spectral features from each EEG recording using a multitaper spectral estimation method. Elastic-net regularization method was used for feature selection. We compared the performance of several machine learning algorithms (logistic regression, support vector machine, and random forest), trained on individual sleep stages, to predict different levels of the MOAA/S sedation state. Results The random forest algorithm trained on non-rapid eye movement stage 3 (N3) predicted dexmedetomidine-induced deep sedation (MOAA/S = 0) with area under the receiver operator characteristics curve >0.8 outperforming other machine learning models. Power in the delta band (0–4 Hz) was selected as an important feature for prediction in addition to power in theta (4–8 Hz) and beta (16–30 Hz) bands. Conclusions Using a large-scale EEG data-driven approach and machine learning framework, we show that dexmedetomidine-induced deep sedation state mimics N3 sleep EEG patterns. Clinical Trials Name—Pharmacodynamic Interaction of REMI and DMED (PIRAD), URL—https://clinicaltrials.gov/ct2/show/NCT03143972, and registration—NCT03143972.

146 Better Aerobic Fitness Is Associated with Distinct Sleep Characteristics in Adolescents

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A60-A60
Author(s):  
Ariel Neikrug ◽  
Shlomit Radom-Aizik ◽  
Ivy Chen ◽  
Annamarie Stehli ◽  
Kitty Lui ◽  
...  
Keyword(s):  
Eye Movement ◽  
Slow Wave ◽  
Aerobic Fitness ◽  
Nrem Sleep ◽  
Brain Maturation ◽  
Rapid Eye Movement ◽  
Sleep Spindle ◽  
Sleep Patterns ◽  
Peak Vo2 ◽  
Local Sleep

Abstract Introduction Aerobic fitness facilitates brain synaptic plasticity, which influences global and local sleep expression. While it is known that sleep patterns/behavior and non-rapid eye movement (NREM) sleep slow wave activity (SWA) tracks brain maturation, little is known about how aerobic fitness and sleep interact during development in youth. The aim of this pilot was to characterize relationships among aerobic fitness, measures of global/local sleep expression, and habitual sleep patterns in children and adolescents. We hypothesized that greater aerobic fitness would be associated with better sleep quality, indicated by increased SWA. Methods 20 adolescents (mean age=14.6±2.3 years old, range 11-17, 11 females) were evaluated for AF (peak VO2 assessed by ramp-type progressive cycle ergometry in the laboratory), habitual sleep duration and efficiency (continuous 7-14 day actigraphy with sleep diary), and topographic patterns of spectral power in slow wave, theta, and sleep spindle frequency ranges in non-rapid eye movement (NREM) sleep using overnight polysomnography with high-density electroencephalography (hdEEG, 128 channels). Results Significant relationships were observed between peak VO2 and habitual bedtime (r=-0.604, p=0.013) and wake-up time (r=-0.644, p=0.007), with greater fitness associated with an earlier sleep schedule (going to bed and waking up earlier). Peak VO2 was a significant predictor of slow oscillations (0.5-1Hz, p=0.018) and theta activity (4.5-7.5Hz, p=0.002) over anterior frontal and central derivations (p<0.001 and p=0.001, respectively) after adjusting for sex and pubertal development stage. Similar associations were detected for fast sleep spindle activity (13-16Hz, p=0.006), which was greater over temporo-parietal derivations. Conclusion Greater AF was associated with earlier habitual sleep times and with enhanced expression of developmentally-relevant sleep oscillations during NREM sleep. These data suggest that AF may 1) minimize the behavioral sleep delay commonly seen during adolescence, and 2) impact topographically-specific features of sleep physiology known to mechanistically support neuroplasticity and cognitive processes which are dependent on prefrontal cortex and hippocampal function in adolescents and adults. Support (if any) NCATS grant #UL1TR001414 & PERC Systems Biology Fund

High-throughput visual assessment of sleep stages in mice using machine learning

SLEEP ◽  
2021 ◽  
Author(s):  
Brian Geuther ◽  
Mandy Chen ◽  
Raymond J Galante ◽  
Owen Han ◽  
Jie Lian ◽  
...  
Keyword(s):  
Machine Learning ◽  
Eye Movement ◽  
High Throughput ◽  
Data Augmentation ◽  
Sleep Stage ◽  
Visual Assessment ◽  
Video Data ◽  
Sleep Stages ◽  
Rapid Eye Movement ◽  
Rapid Eye Movement Sleep

Abstract Study Objectives Sleep is an important biological process that is perturbed in numerous diseases, and assessment its substages currently requires implantation of electrodes to carry out electroencephalogram/electromyogram (EEG/EMG) analysis. Although accurate, this method comes at a high cost of invasive surgery and experts trained to score EEG/EMG data. Here, we leverage modern computer vision methods to directly classify sleep substages from video data. This bypasses the need for surgery and expert scoring, provides a path to high-throughput studies of sleep in mice. Methods We collected synchronized high-resolution video and EEG/EMG data in 16 male C57BL/6J mice. We extracted features from the video that are time and frequency-based and used the human expert-scored EEG/EMG data to train a visual classifier. We investigated several classifiers and data augmentation methods. Results Our visual sleep classifier proved to be highly accurate in classifying wake, non-rapid eye movement sleep (NREM), and rapid eye movement sleep (REM) states, and achieves an overall accuracy of 0.92 +/- 0.05 (mean +/- SD). We discover and genetically validate video features that correlate with breathing rates, and show low and high variability in NREM and REM sleep, respectively. Finally, we apply our methods to non-invasively detect that sleep stage disturbances induced by amphetamine administration. Conclusions We conclude that machine learning based visual classification of sleep is a viable alternative to EEG/EMG based scoring. Our results will enable non-invasive high-throughput sleep studies and will greatly reduce the barrier to screening mutant mice for abnormalities in sleep.

Chloral Hydrate and the Carbon Dioxide Chemoreceptor Response: A Study of Puppies and Infants

PEDIATRICS ◽  
1982 ◽  
Vol 70 (3) ◽  
pp. 447-450
Author(s):  
Martin H. Lees ◽  
George D. Olsen ◽  
Kip L. McGilliard ◽  
James D. Newcomb ◽  
Cecille O. Sunderland
Keyword(s):  
Carbon Dioxide ◽  
Tidal Volume ◽  
Eye Movement ◽  
Chloral Hydrate ◽  
Nrem Sleep ◽  
Co2 Production ◽  
O2 Consumption ◽  
Rapid Eye Movement ◽  
Natural Sleep ◽  
Co2 Elimination

CO2 chemoreceptor function was assessed during natural sleep and following the administration of 100 mg/kg of chloral hydrate to 26 puppies. With chloral hydrate-induced sleep, there were no significant changes in ventilation or in CO2 chemoreceptor response. The ventilation and CO2 chemoreceptor response of a group of infants in natural sleep were compared with those of a group receiving 50 mg/kg of chloral hydrate. Tidal volume, O2 consumption, and CO2 elimination were slightly higher in the group given chloral hydrate. There was no difference in the CO2 chemoreceptor response. The proportion of time spent in rapid eye movement (REM) and non-rapid eye movement (NREM) sleep in chloral hydrate-induced sleep was similar to that occurring in natural sleep. Use of chloral hydrate stabilizes O2 consumption and CO2 production, and it greatly facilitates the assessment of chemoreceptor function in infants. The CO2 chemoreceptor response appears not to be altered in puppies or infants.

Detecting Cognitive Distraction Using Random Forest by Considering Eye Movement Type

2018 ◽  
pp. 1587-1599
Author(s):  
Hiroaki Koma ◽  
Taku Harada ◽  
Akira Yoshizawa ◽  
Hirotoshi Iwasaki
Keyword(s):  
Machine Learning ◽  
Eye Movements ◽  
Random Forest ◽  
Decision Trees ◽  
Eye Movement ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Still Images ◽  
Cognitive Distraction ◽  
Movement Type

Detecting distracted states can be applied to various problems such as danger prevention when driving a car. A cognitive distracted state is one example of a distracted state. It is known that eye movements express cognitive distraction. Eye movements can be classified into several types. In this paper, the authors detect a cognitive distraction using classified eye movement types when applying the Random Forest machine learning algorithm, which uses decision trees. They show the effectiveness of considering eye movement types for detecting cognitive distraction when applying Random Forest. The authors use visual experiments with still images for the detection.

scholarly journals 3145 An Evaluation of Machine Learning and Traditional Statistical Methods for Discovery in Large-Scale Translational Data

2019 ◽  
Vol 3 (s1) ◽  
pp. 2-2
Author(s):  
Megan C Hollister ◽  
Jeffrey D. Blume
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Random Forest ◽  
Gene Expression Data ◽  
Large Scale ◽  
Second Generation ◽  
A Priori ◽  
Expression Data ◽  
P Values ◽  
Machine Learning Methods

OBJECTIVES/SPECIFIC AIMS: To examine and compare the claims in Bzdok, Altman, and Brzywinski under a broader set of conditions by using unbiased methods of comparison. To explore how to accurately use various machine learning and traditional statistical methods in large-scale translational research by estimating their accuracy statistics. Then we will identify the methods with the best performance characteristics. METHODS/STUDY POPULATION: We conducted a simulation study with a microarray of gene expression data. We maintained the original structure proposed by Bzdok, Altman, and Brzywinski. The structure for gene expression data includes a total of 40 genes from 20 people, in which 10 people are phenotype positive and 10 are phenotype negative. In order to find a statistical difference 25% of the genes were set to be dysregulated across phenotype. This dysregulation forced the positive and negative phenotypes to have different mean population expressions. Additional variance was included to simulate genetic variation across the population. We also allowed for within person correlation across genes, which was not done in the original simulations. The following methods were used to determine the number of dysregulated genes in simulated data set: unadjusted p-values, Benjamini-Hochberg adjusted p-values, Bonferroni adjusted p-values, random forest importance levels, neural net prediction weights, and second-generation p-values. RESULTS/ANTICIPATED RESULTS: Results vary depending on whether a pre-specified significance level is used or the top 10 ranked values are taken. When all methods are given the same prior information of 10 dysregulated genes, the Benjamini-Hochberg adjusted p-values and the second-generation p-values generally outperform all other methods. We were not able to reproduce or validate the finding that random forest importance levels via a machine learning algorithm outperform classical methods. Almost uniformly, the machine learning methods did not yield improved accuracy statistics and they depend heavily on the a priori chosen number of dysregulated genes. DISCUSSION/SIGNIFICANCE OF IMPACT: In this context, machine learning methods do not outperform standard methods. Because of this and their additional complexity, machine learning approaches would not be preferable. Of all the approaches the second-generation p-value appears to offer significant benefit for the cost of a priori defining a region of trivially null effect sizes. The choice of an analysis method for large-scale translational data is critical to the success of any statistical investigation, and our simulations clearly highlight the various tradeoffs among the available methods.

scholarly journals Development of a Large-Scale Functional Brain Network during Human Non-Rapid Eye Movement Sleep

2010 ◽  
Vol 30 (34) ◽  
pp. 11379-11387 ◽  
Author(s):  
V. I. Spoormaker ◽  
M. S. Schroter ◽  
P. M. Gleiser ◽  
K. C. Andrade ◽  
M. Dresler ◽  
...  
Keyword(s):  
Eye Movement ◽  
Large Scale ◽  
Brain Network ◽  
Rapid Eye Movement ◽  
Rapid Eye Movement Sleep ◽  
Functional Brain ◽  
Functional Brain Network

scholarly journals Targeted memory reactivation in human REM sleep elicits recurrent, temporally compressed reactivation

2021 ◽  
Author(s):  
Mahmoud E. A. Abdellahi ◽  
Anne C. M. Koopman ◽  
Matthias S. Treder ◽  
Penelope A. Lewis
Keyword(s):  
Machine Learning ◽  
Eye Movement ◽  
Performance Improvement ◽  
Rem Sleep ◽  
Strong Evidence ◽  
Nrem Sleep ◽  
Theta Activity ◽  
Rapid Eye Movement ◽  
Memory Reactivation ◽  
Machine Learning Classifiers

AbstractMemories are reactivated during non-rapid eye movement (NREM) sleep, but the question of whether equivalent reactivation also occurs in rapid eye movement (REM) sleep is hotly debated. To examine this, we used a technique called targeted memory reactivation (TMR) in which sounds are paired with learned material in wake, and then re-presented in subsequent sleep to trigger reactivation. We then used machine learning classifiers to identify TMR-induced reactivation in REM. The reactivation we measured was temporally compressed by approximately five times during REM compared to wakeful performance of the task, and often occurred twice after a single TMR cue. Reactivation strength positively predicted overnight performance improvement and was only apparent in trials with high theta activity. These findings provide strong evidence for memory reactivation in human REM sleep after TMR as well as an initial characterisation of this reactivation.

scholarly journals REM sleep: unique associations with behavior, corticosterone regulation and apoptotic pathways in chronic stress in mice

2018 ◽  
Author(s):  
Mathieu Nollet ◽  
Harriet Hicks ◽  
Andrew P. McCarthy ◽  
Huihai Wu ◽  
Carla S. Möller-Levet ◽  
...  
Keyword(s):  
Machine Learning ◽  
Eye Movement ◽  
Chronic Stress ◽  
Rem Sleep ◽  
Chronic Mild Stress ◽  
Specific Aspect ◽  
Mild Stress ◽  
Rapid Eye Movement ◽  
Rapid Eye Movement Sleep ◽  
Apoptotic Pathways

AbstractOne of sleep’s putative functions is mediation of adaptation to waking experiences. Chronic stress is a common waking experience, however, which specific aspect of sleep is most responsive, and how sleep changes relate to behavioral disturbances and molecular correlates remain unknown. We quantified sleep, physical, endocrine and behavioral variables and the brain and blood transcriptome in mice exposed to nine weeks of unpredictable chronic mild stress (UCMS). Comparing 46 phenotypical variables revealed that rapid-eye-movement sleep (REMS), corticosterone regulation and coat state were most responsive to UCMS. REMS theta oscillations were enhanced whereas delta oscillations in non-REMS were unaffected. Transcripts affected by UCMS in the prefrontal cortex, hippocampus, hypothalamus and blood were associated with inflammatory and immune responses. A machine learning approach controlling for unspecific UCMS effects identified transcriptomic predictors for specific phenotypes and their overlap. Transcriptomic predictor sets for the inter-individual variation in REMS continuity and theta activity shared many pathways with corticosterone regulation and in particular pathways implicated in apoptosis, including mitochondrial pathways. Predictor sets for REMS and anhedonia, one of the behavioral changes following UCMS, shared pathways involved in oxidative stress, cell proliferation and apoptosis. RNA predictor sets for non-NREMS parameters showed no overlap with other phenotypes. These novel data identify REMS as a core and early element of the response to chronic stress, and identify apoptotic pathways as a putative mechanism by which REMS mediates adaptation to stressful waking experiences.Significance StatementSleep is responsive to experiences during wakefulness and is altered in stress-related disorders. Whether sleep changes primarily concern rapid-eye-movement sleep (REMS) or non-REM sleep, and how they correlate with stress hormones, behavioral and transcriptomic responses remained unknown. We demonstrate using unpredictable chronic (9-weeks) mild stress that REMS is the most responsive of all the measured sleep characteristics, and correlates with deficiency in corticosterone regulation. An unbiased machine learning, controlling for unspecific effects of stress, revealed that REMS correlated with RNA predictor sets enriched in apoptosis including mitochondrial pathways. Several pathways were shared with predictors of corticosterone and behavioral responses. This unbiased approach point to apoptosis as a molecular mechanism by which REMS mediates adaptation to an ecologically relevant waking experience.

Constant light suppresses sleep and circadian rhythms in pigeons without consequent sleep rebound in darkness

1994 ◽  
Vol 267 (4) ◽  
pp. R945-R952 ◽  
Author(s):  
R. J. Berger ◽  
N. H. Phillips
Keyword(s):  
Circadian Rhythms ◽  
Eye Movement ◽  
Power Spectra ◽  
Behavioral Changes ◽  
Rapid Eye Movement ◽  
Rapid Eye Movement Sleep ◽  
Sleep Patterns ◽  
Free Running ◽  
Dim Light ◽  
Dd Transitions

Sleep patterns and circadian rhythms of body temperature, activity, body weight, and electroencephalographic (EEG) power spectra of pigeons were compared among three photic conditions: a 12:12-h light-dark cycle (LD), followed successively by constant bright (LL) and dim light (DD) periods. LL suppressed non-rapid-eye-movement and rapid eye movement sleep and circadian rhythms of the measured variables without producing increased drowsiness or other physiological or behavioral changes. Sleep patterns after LL-DD transitions also showed no evidence of prior sleep deprivation during LL. Sleep latency after LL-DD transitions was 93 min longer than after L-D transitions in LD. Total sleep and EEG slow wave activity during the first 24 h in DD did not differ from D in LD. Free-running circadian rhythms subsequently reappeared in DD after LL.

Sign in / Sign up

Export Citation Format

Share Document