Deep Neural Network Sleep Scoring Using Combined Motion and Heart Rate Variability Data
| العنوان: | Deep Neural Network Sleep Scoring Using Combined Motion and Heart Rate Variability Data |
|---|---|
| المؤلفون: | Shahab Haghayegh, Richard J. Castriotta, Michael H. Smolensky, Kenneth R. Diller, Sepideh Khoshnevis |
| المصدر: | Sensors, Vol 21, Iss 25, p 25 (2021) Sensors Volume 21 Issue 1 Sensors (Basel, Switzerland) |
| بيانات النشر: | MDPI AG, 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Male, Long-Short-Term Memory (LSTM), Polysomnography, wrist actigraphy, lcsh:Chemical technology, 01 natural sciences, Biochemistry, Non-rapid eye movement sleep, Article, Analytical Chemistry, 03 medical and health sciences, 0302 clinical medicine, Heart Rate, Statistics, medicine, Humans, Heart rate variability, lcsh:TP1-1185, Electrical and Electronic Engineering, sleep, Instrumentation, Mathematics, medicine.diagnostic_test, time series classification, 010401 analytical chemistry, deep learning, Actigraphy, artificial intelligence, Convolutional Neural Network (CNN), Atomic and Molecular Physics, and Optics, 0104 chemical sciences, Female, Neural Networks, Computer, Sleep onset latency, Sleep (system call), Sleep onset, 030217 neurology & neurosurgery, Kappa |
| الوصف: | 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&ndash 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&ndash 34.3% higher than comparator IAs), and 58.7% Kappa agreement (16&ndash 23% higher than comparator IAs) in detecting sleep epochs. HA did not differ significantly from PSG in deriving sleep parameters&mdash 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. |
| وصف الملف: | application/pdf |
| اللغة: | English |
| تدمد: | 1424-8220 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8416e69a9702dc20c2ad219fcf65d49f https://www.mdpi.com/1424-8220/21/1/25 |
| حقوق: | OPEN |
| رقم الأكسشن: | edsair.doi.dedup.....8416e69a9702dc20c2ad219fcf65d49f |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 14248220 |
|---|