Exploring predictors of insomnia severity in shift workers using machine learning model

IntroductionInsomnia in shift workers has distinctive features due to circadian rhythm disruption caused by reversed or unstable sleep-wake cycle work schedules. While previous studies have primarily focused on a limited number of predictors for insomnia severity in shift workers, there is a need to...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyewon Yeo, Hyeyeon Jang, Nambeom Kim, Sehyun Jeon, Yunjee Hwang, Chang-Ki Kang, Seog Ju Kim
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Public Health
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpubh.2025.1494583/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850035272662646784
author Hyewon Yeo
Hyeyeon Jang
Nambeom Kim
Sehyun Jeon
Yunjee Hwang
Chang-Ki Kang
Seog Ju Kim
Seog Ju Kim
author_facet Hyewon Yeo
Hyeyeon Jang
Nambeom Kim
Sehyun Jeon
Yunjee Hwang
Chang-Ki Kang
Seog Ju Kim
Seog Ju Kim
author_sort Hyewon Yeo
collection DOAJ
description IntroductionInsomnia in shift workers has distinctive features due to circadian rhythm disruption caused by reversed or unstable sleep-wake cycle work schedules. While previous studies have primarily focused on a limited number of predictors for insomnia severity in shift workers, there is a need to further explore key predictors, and develop a data-driven prediction model for insomnia in shift workers. This study aims to identify potential predictors of insomnia severity in shift workers using a machine learning (ML) approach and evaluate the accuracy of the resulting prediction model.MethodsWe assessed the predictors of insomnia severity in large samples of individuals (4,572 shift workers and 2,093 non-shift workers). The general linear model with the least absolute shrinkage and selection operator (LASSO) was used to determine an ML-based prediction model. Additional analyses were conducted to assess the interaction effects depending on the shift work schedule.ResultsThe ML algorithms identified 41 key predictors from 281 variables: 1 demographic, 7 physical health, 13 job characteristics, and 20 mental health factors. Compared to the non-shift workers, the shift workers showed a stronger association between insomnia severity and five predicting variables: passiveness at work, authoritarian work atmosphere, easiness to wake up, family and interpersonal stress, and medication. The prediction model demonstrated good performance with high accuracy and specificity overall despite a limited F1 score (classification effectiveness) and recall (sensitivity). Specifically, a prediction model for shift workers showed better balance in F1 scores and recall compared to that for non-shift workers.DiscussionThis ML algorithm provides an effective method for identifying key factors that predict insomnia severity in shift workers. Our findings align with the traditional insomnia model while also reflecting the distinctive features of shift work such as workplace conditions. Although the potential for immediate clinical application is limited, this study can serve as guidance for future research in improving a prediction model for shift workers. Constructing comprehensive ML-based prediction models that include our key predictors could be a crucial approach for clinical purposes.
format Article
id doaj-art-fb20f2d8a9b04b2ca25b9cf048f1450a
institution DOAJ
issn 2296-2565
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Public Health
spelling doaj-art-fb20f2d8a9b04b2ca25b9cf048f1450a2025-08-20T02:57:32ZengFrontiers Media S.A.Frontiers in Public Health2296-25652025-03-011310.3389/fpubh.2025.14945831494583Exploring predictors of insomnia severity in shift workers using machine learning modelHyewon Yeo0Hyeyeon Jang1Nambeom Kim2Sehyun Jeon3Yunjee Hwang4Chang-Ki Kang5Seog Ju Kim6Seog Ju Kim7Samsung Medical Center, Sungkyunkwan University, Seoul, Republic of KoreaSamsung Medical Center, Sungkyunkwan University, Seoul, Republic of KoreaMedical Campus, Biomedical Engineering Research Center, Gachon University, Incheon, Republic of KoreaSamsung Medical Center, Sungkyunkwan University, Seoul, Republic of KoreaBrain and Cognitive Engineering, Korea University, Seoul, Republic of KoreaMedical Campus, Health Science, Radiological Science, Gachon University, Incheon, Republic of KoreaSamsung Medical Center, Sungkyunkwan University, Seoul, Republic of KoreaSchool of Medicine, Psychiatry, Sungkyunkwan University, Suwon, Republic of KoreaIntroductionInsomnia in shift workers has distinctive features due to circadian rhythm disruption caused by reversed or unstable sleep-wake cycle work schedules. While previous studies have primarily focused on a limited number of predictors for insomnia severity in shift workers, there is a need to further explore key predictors, and develop a data-driven prediction model for insomnia in shift workers. This study aims to identify potential predictors of insomnia severity in shift workers using a machine learning (ML) approach and evaluate the accuracy of the resulting prediction model.MethodsWe assessed the predictors of insomnia severity in large samples of individuals (4,572 shift workers and 2,093 non-shift workers). The general linear model with the least absolute shrinkage and selection operator (LASSO) was used to determine an ML-based prediction model. Additional analyses were conducted to assess the interaction effects depending on the shift work schedule.ResultsThe ML algorithms identified 41 key predictors from 281 variables: 1 demographic, 7 physical health, 13 job characteristics, and 20 mental health factors. Compared to the non-shift workers, the shift workers showed a stronger association between insomnia severity and five predicting variables: passiveness at work, authoritarian work atmosphere, easiness to wake up, family and interpersonal stress, and medication. The prediction model demonstrated good performance with high accuracy and specificity overall despite a limited F1 score (classification effectiveness) and recall (sensitivity). Specifically, a prediction model for shift workers showed better balance in F1 scores and recall compared to that for non-shift workers.DiscussionThis ML algorithm provides an effective method for identifying key factors that predict insomnia severity in shift workers. Our findings align with the traditional insomnia model while also reflecting the distinctive features of shift work such as workplace conditions. Although the potential for immediate clinical application is limited, this study can serve as guidance for future research in improving a prediction model for shift workers. Constructing comprehensive ML-based prediction models that include our key predictors could be a crucial approach for clinical purposes.https://www.frontiersin.org/articles/10.3389/fpubh.2025.1494583/fullshift workersleepinsomniamachine learningrisk prediction
spellingShingle Hyewon Yeo
Hyeyeon Jang
Nambeom Kim
Sehyun Jeon
Yunjee Hwang
Chang-Ki Kang
Seog Ju Kim
Seog Ju Kim
Exploring predictors of insomnia severity in shift workers using machine learning model
Frontiers in Public Health
shift worker
sleep
insomnia
machine learning
risk prediction
title Exploring predictors of insomnia severity in shift workers using machine learning model
title_full Exploring predictors of insomnia severity in shift workers using machine learning model
title_fullStr Exploring predictors of insomnia severity in shift workers using machine learning model
title_full_unstemmed Exploring predictors of insomnia severity in shift workers using machine learning model
title_short Exploring predictors of insomnia severity in shift workers using machine learning model
title_sort exploring predictors of insomnia severity in shift workers using machine learning model
topic shift worker
sleep
insomnia
machine learning
risk prediction
url https://www.frontiersin.org/articles/10.3389/fpubh.2025.1494583/full
work_keys_str_mv AT hyewonyeo exploringpredictorsofinsomniaseverityinshiftworkersusingmachinelearningmodel
AT hyeyeonjang exploringpredictorsofinsomniaseverityinshiftworkersusingmachinelearningmodel
AT nambeomkim exploringpredictorsofinsomniaseverityinshiftworkersusingmachinelearningmodel
AT sehyunjeon exploringpredictorsofinsomniaseverityinshiftworkersusingmachinelearningmodel
AT yunjeehwang exploringpredictorsofinsomniaseverityinshiftworkersusingmachinelearningmodel
AT changkikang exploringpredictorsofinsomniaseverityinshiftworkersusingmachinelearningmodel
AT seogjukim exploringpredictorsofinsomniaseverityinshiftworkersusingmachinelearningmodel
AT seogjukim exploringpredictorsofinsomniaseverityinshiftworkersusingmachinelearningmodel