Validation of sleep-based actigraphy machine learning models for prediction of preterm birth

Abstract Disruptive sleep is a well-established predictor of preterm birth. However, the exact relationship between sleep behavior and preterm birth outcomes remains unknown, in part because prior work has relied on self-reported sleep data. With the advent of smartwatches, it is possible to obtain...

Full description

Saved in:
Bibliographic Details
Main Authors: Benjamin C. Warner, Peinan Zhao, Erik D. Herzog, Antonina I. Frolova, Sarah K. England, Chenyang Lu
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:npj Women's Health
Online Access:https://doi.org/10.1038/s44294-025-00082-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849329318879035392
author Benjamin C. Warner
Peinan Zhao
Erik D. Herzog
Antonina I. Frolova
Sarah K. England
Chenyang Lu
author_facet Benjamin C. Warner
Peinan Zhao
Erik D. Herzog
Antonina I. Frolova
Sarah K. England
Chenyang Lu
author_sort Benjamin C. Warner
collection DOAJ
description Abstract Disruptive sleep is a well-established predictor of preterm birth. However, the exact relationship between sleep behavior and preterm birth outcomes remains unknown, in part because prior work has relied on self-reported sleep data. With the advent of smartwatches, it is possible to obtain more reliable and accurate sleep data, which can be utilized to evaluate the impact of specific sleep behaviors in concert with machine learning. We evaluate motion actigraphy data collected from a cohort of participants undergoing pregnancy, and train several machine learning models based on aggregate features engineered from this data. We then evaluate the relative impact from each of these actigraphy features, as well as features derived from questionnaires collected from participants. Our findings suggest that actigraphy data can predict preterm birth outcomes with a degree of effectiveness, and that variability in sleep patterns is a relatively fair predictor of preterm birth.
format Article
id doaj-art-ffdf7405e46c47c2a37814802be512a0
institution Kabale University
issn 2948-1716
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series npj Women's Health
spelling doaj-art-ffdf7405e46c47c2a37814802be512a02025-08-20T03:47:17ZengNature Portfolionpj Women's Health2948-17162025-06-013111310.1038/s44294-025-00082-yValidation of sleep-based actigraphy machine learning models for prediction of preterm birthBenjamin C. Warner0Peinan Zhao1Erik D. Herzog2Antonina I. Frolova3Sarah K. England4Chenyang Lu5AI for Health Institute, Washington University in St. LouisCenter for Reproductive Health Sciences, Department of Obstetrics & Gynecology, Washington University School of Medicine in St. LouisDepartment of Biology, Washington University in St. LouisCenter for Reproductive Health Sciences, Department of Obstetrics & Gynecology, Washington University School of Medicine in St. LouisAI for Health Institute, Washington University in St. LouisAI for Health Institute, Washington University in St. LouisAbstract Disruptive sleep is a well-established predictor of preterm birth. However, the exact relationship between sleep behavior and preterm birth outcomes remains unknown, in part because prior work has relied on self-reported sleep data. With the advent of smartwatches, it is possible to obtain more reliable and accurate sleep data, which can be utilized to evaluate the impact of specific sleep behaviors in concert with machine learning. We evaluate motion actigraphy data collected from a cohort of participants undergoing pregnancy, and train several machine learning models based on aggregate features engineered from this data. We then evaluate the relative impact from each of these actigraphy features, as well as features derived from questionnaires collected from participants. Our findings suggest that actigraphy data can predict preterm birth outcomes with a degree of effectiveness, and that variability in sleep patterns is a relatively fair predictor of preterm birth.https://doi.org/10.1038/s44294-025-00082-y
spellingShingle Benjamin C. Warner
Peinan Zhao
Erik D. Herzog
Antonina I. Frolova
Sarah K. England
Chenyang Lu
Validation of sleep-based actigraphy machine learning models for prediction of preterm birth
npj Women's Health
title Validation of sleep-based actigraphy machine learning models for prediction of preterm birth
title_full Validation of sleep-based actigraphy machine learning models for prediction of preterm birth
title_fullStr Validation of sleep-based actigraphy machine learning models for prediction of preterm birth
title_full_unstemmed Validation of sleep-based actigraphy machine learning models for prediction of preterm birth
title_short Validation of sleep-based actigraphy machine learning models for prediction of preterm birth
title_sort validation of sleep based actigraphy machine learning models for prediction of preterm birth
url https://doi.org/10.1038/s44294-025-00082-y
work_keys_str_mv AT benjamincwarner validationofsleepbasedactigraphymachinelearningmodelsforpredictionofpretermbirth
AT peinanzhao validationofsleepbasedactigraphymachinelearningmodelsforpredictionofpretermbirth
AT erikdherzog validationofsleepbasedactigraphymachinelearningmodelsforpredictionofpretermbirth
AT antoninaifrolova validationofsleepbasedactigraphymachinelearningmodelsforpredictionofpretermbirth
AT sarahkengland validationofsleepbasedactigraphymachinelearningmodelsforpredictionofpretermbirth
AT chenyanglu validationofsleepbasedactigraphymachinelearningmodelsforpredictionofpretermbirth