Dataset Information

Deep Neural Network Sleep Scoring Using Combined Motion and Heart Rate Variability Data.

ABSTRACT: 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.

SUBMITTER: Haghayegh S

PROVIDER: S-EPMC7793092 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Neural Network Sleep Scoring Using Combined Motion and Heart Rate Variability Data.

Haghayegh Shahab S Khoshnevis Sepideh S Smolensky Michael H MH Diller Kenneth R KR Castriotta Richard J RJ

Sensors (Basel, Switzerland) 20201223 1

<i>Background:</i> 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). <i>M ...[more]

PMID: 33374527

Similar Datasets

Project description:BackgroundEstimating the depth of anaesthesia (DoA) is critical in modern anaesthetic practice. Multiple DoA monitors based on electroencephalograms (EEGs) have been widely used for DoA monitoring; however, these monitors may be inaccurate under certain conditions. In this work, we hypothesize that heart rate variability (HRV)-derived features based on a deep neural network can distinguish different anaesthesia states, providing a secondary tool for DoA assessment.MethodsA novel method of distinguishing different anaesthesia states was developed based on four HRV-derived features in the time and frequency domain combined with a deep neural network. Four features were extracted from an electrocardiogram, including the HRV high-frequency power, low-frequency power, high-to-low-frequency power ratio, and sample entropy. Next, these features were used as inputs for the deep neural network, which utilized the expert assessment of consciousness level as the reference output. Finally, the deep neural network was compared with the logistic regression, support vector machine, and decision tree models. The datasets of 23 anaesthesia patients were used to assess the proposed method.ResultsThe accuracies of the four models, in distinguishing the anaesthesia states, were 86.2% (logistic regression), 87.5% (support vector machine), 87.2% (decision tree), and 90.1% (deep neural network). The accuracy of deep neural network was higher than those of the logistic regression (p < 0.05), support vector machine (p < 0.05), and decision tree (p < 0.05) approaches. Our method outperformed the logistic regression, support vector machine, and decision tree methods.ConclusionsThe incorporation of four HRV-derived features in the time and frequency domain and a deep neural network could accurately distinguish between different anaesthesia states; however, this study is a pilot feasibility study. The proposed method-with other evaluation methods, such as EEG-is expected to assist anaesthesiologists in the accurate evaluation of the DoA.

Project description:The domestic dog (Canis familiaris) has been shown to both excel in recognising human emotions and produce emotion-related vocalisations and postures that humans can easily recognise. However, little is known about the effect of emotional experiences on subsequent sleep physiology, a set of phenomena heavily interrelated with emotions in the case of humans. The present paper examines heart rate (HR) and heart rate variability (HRV) during dogs' sleep, measures that are influenced by both positive and negative emotions in awake dogs. In Study I, descriptive HR and HRV data is provided on N = 12 dogs about the different sleep stages (wake, drowsiness, non-rapid eye movement (non-REM), REM; scoring based on electroencephalogram (EEG) data). We conclude that wakefulness is characterised by higher HR and lower HRV compared to all sleep stages. Furthermore, drowsiness is characterised by higher HR and lower HRV than non-REM and REM, but only if the electrocardiogram (ECG) samples are taken from the first occurrence of a given sleep stage, not when the longest periods of each sleep stage are analysed. Non-REM and REM sleep were not found to be different from each other in either HR or HRV parameters. In Study II, sleep HR and HRV measures are compared in N = 16 dogs after a positive versus negative social interaction (within-subject design). The positive social interaction consisted of petting and ball play, while the negative social interaction was a mixture of separation, threatening approach and still face test. Results are consistent with the two-dimensional emotion hypothesis in that following the intense positive interaction more elevated HR and decreased HRV is found compared to the mildly negative (lower intensity) interaction. However, although this trend can be observed in all sleep stages except for REM, the results only reach significance in the wake stage. In sum, the present findings suggest that HR and HRV are possible to measure during dogs' sleep, and can potentially be used to study the effect of emotions not only during but also after such interactions.

Dataset Information

Deep Neural Network Sleep Scoring Using Combined Motion and Heart Rate Variability Data.

Publications

Deep Neural Network Sleep Scoring Using Combined Motion and Heart Rate Variability Data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets