NL repository
menu
검색
Library
Browse
Communities & Collections
By Date
Authors
Titles
Subject
My Repository
My Account
Receive email updates
Edit Profile
DSpace at EWHA
의료원
의료원
Journal papers
View : 151 Download: 0
Imputing missing sleep data from wearables with neural networks in real-world settings
Title
Imputing missing sleep data from wearables with neural networks in real-world settings
Authors
Lee
;
Minki P.
;
Hoang
;
Kien
;
Park
;
Sungkyu
;
Song
;
YunMin
;
Joo
;
Eun Yeon
;
Chang
;
Won
;
Kim
;
Jee Hyun
;
Jae Kyoung
Ewha Authors
김지현
SCOPUS Author ID
김지현
Issue Date
2024
Journal Title
Sleep
ISSN
0161-8105
Citation
Sleep vol. 47, no. 1
Keywords
actigraphy
;
machine learning
;
missing data imputation
;
non-negative matrix factorization
;
sleep–wake cycle
;
wearable device
Publisher
Oxford University Press
Indexed
SCIE; SCOPUS
Document Type
Article
Abstract
Sleep is a critical component of health and well-being but collecting and analyzing accurate longitudinal sleep data can be challenging, especially outside of laboratory settings. We propose a simple neural network model titled SOMNI (Sleep data restOration using Machine learning and Non-negative matrix factorIzation [NMF]) for imputing missing rest-activity data from actigraphy, which can enable clinicians to better handle missing data and monitor sleep–wake cycles of individuals with highly irregular sleep–wake patterns. The model consists of two hidden layers and uses NMF to capture hidden longitudinal sleep–wake patterns of individuals with disturbed sleep–wake cycles. Based on this, we develop two approaches: the individual approach imputes missing data based on the data from only one participant, while the global approach imputes missing data based on the data across multiple participants. Our models are tested with shift and non-shift workers' data from three independent hospitals. Both approaches can accurately impute missing data up to 24 hours of long dataset (>50 days) even for shift workers with extremely irregular sleep–wake patterns (AUC > 0.86). On the other hand, for short dataset (~15 days), only the global model is accurate (AUC > 0.77). Our approach can be used to help clinicians monitor sleep–wake cycles of patients with sleep disorders outside of laboratory settings without relying on sleep diaries, ultimately improving sleep health outcomes. © The Author(s) 2023.
DOI
10.1093/sleep/zsad266
Appears in Collections:
의료원
>
의료원
>
Journal papers
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML
Show full item record
Find@EWHA
트윗하기
BROWSE
Communities & Collections
By Date
Authors
Titles
Subject