Recent trends of infant motor activity estimation using wearable sensors: A scoping review
5 affiliations
- 1Department of Biomedical Engineering, University of Massachusetts Lowell, Lowell, Massachusetts, United States of America
- 2Division of Physical Therapy, Human Performance, School of Medicine, West Virginia University, Morgantown, West Virginia, United States of America
- 3Department of Physical Therapy and Kinesiology, Zuckerberg College of Health Sciences, University of Massachusetts, Lowell, Massachusetts, United States of America
- 4Miner School of Computer and Information Sciences, University of Massachusetts, Lowell, Massachusetts, United States of America
- 5Solomont School of Nursing, University of Massachusetts, Lowell, Massachusetts, United States of America
Abstract
Wearable sensors may enable objective monitoring of infant motor activity, posture, and movement in laboratory, clinic, and home contexts. However, evidence for the validity, generalizability, and implementation readiness of wearable-derived infant motor measures remains heterogeneous. This scoping review synthesized technical features, validation evidence, and clinical applications of wearable sensors monitoring infant motor activity, posture, or movement during awake periods in the first year of life. PRISMA-ScR guidelines were followed, and the protocol was prospectively registered on Open Science Framework. Searches for peer-reviewed articles on wearable-based monitoring of infant activity published between 2019 and 2024 were identified through searches of PubMed, CINAHL, IEEE Xplore, and the ACM Digital Library. A total of 41 studies were selected and classified using Keadle's five-phase validation framework, distinguishing technical validation (Phases I–III) from applied implementation (Phase IV). Fifteen studies (36.6%) included typically developing infants, 22 (53.7%) included infants with or at-risk for developmental disabilities, and 4 (9.8%) were unspecified. Fifteen studies (36.6%) focused on technical validation; 26 (63.4%) implemented sensors in applied contexts. Triaxial accelerometers (n = 15) and IMUs (n = 24) were most common, with sampling frequencies from 1–150 Hz. Posture classification accuracy was 95.8%–98.2% in studies directly comparing posture and movement, whereas fine-grained movement classification was near 81%–84%. Reference-standard correspondence was generally strong for accumulated posture duration (r = 0.80–0.99) but more variable for movement and clinical measures (r = 0.61–0.98). Application studies quantified physical activity, movement coordination and complexity, and intervention responsiveness, with over half collecting home-based data. Wearable sensors have evolved from proof-of-concept systems to family-centered digital health tools supporting developmental monitoring and physical activity promotion. When paired with caregiver feedback and infant-centered design, these technologies may support families, complement clinic-based assessment, and extend developmental support access. Future research should prioritize standardized reporting, affordability, and open-source analytic pipelines to advance equitable implementation. Author summary: Infant movement provides important information about early health and development, but it is difficult to measure continuously during everyday life. Wearable sensors offer a way to monitor infant activity and posture outside the clinic, including in the home. In this review, we examined 41 studies published between 2019 and 2024 that used wearable sensors to measure movement during the first year of life. We found that accelerometers and other motion-sensing devices could often identify infant posture and gross activities with high accuracy. Researchers also used these technologies to study physical activity, movement coordination, developmental differences, and responses to intervention. More than half of the applied studies collected data in home settings, showing growing interest in real-world use. However, differences in devices, methods, reporting, affordability, and data analysis continue to limit comparison and widespread adoption. Wearable sensors may eventually help families and healthcare professionals monitor development over longer periods and complement clinic-based assessments, but more consistent, accessible, and infant-centered approaches are needed.
Related
- Dual-stream attention and feature fusion for human activity recognition via wearable sensors
- The future of wearable sweat sensors in intensive care units: Toward a new era of noninvasive, continuous real-time monitoring
- Identifying unique gait phenotypes across neuromotor conditions using wearable inertial sensors and topological data analysis
- Adaptive personalization for wearable non-invasive continuous glucose sensors.
- A wearable device dataset for mental health assessment using laser Doppler flowmetry and fluorescence spectroscopy sensors
BibTeX
@article{devito2026recent,
title = {{Recent trends of infant motor activity estimation using wearable sensors: A scoping review}},
author = {Alexa DeVito and Ketaki Inamdar and Margaret E. O'Neil and Yidong Zhu and Mohammad Arif Ul Alam and Ainat Koren},
journal = {PLOS Digital Health},
year = {2026},
month = nov,
doi = {10.1371/journal.pdig.0001809},
url = {https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001809},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Recent trends of infant motor activity estimation using wearable sensors: A scoping review
AU - Alexa DeVito
AU - Ketaki Inamdar
AU - Margaret E. O'Neil
AU - Yidong Zhu
AU - Mohammad Arif Ul Alam
AU - Ainat Koren
PY - 2026
DA - 2026/11/06
JO - PLOS Digital Health
DO - 10.1371/journal.pdig.0001809
UR - https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001809
AB - Wearable sensors may enable objective monitoring of infant motor activity, posture, and movement in laboratory, clinic, and home contexts. However, evidence for the validity, generalizability, and implementation readiness of wearable-derived infant motor measures remains heterogeneous. This scoping review synthesized technical features, validation evidence, and clinical applications of wearable sensors monitoring infant motor activity, posture, or movement during awake periods in the first year of life. PRISMA-ScR guidelines were followed, and the protocol was prospectively registered on Open Science Framework. Searches for peer-reviewed articles on wearable-based monitoring of infant activity published between 2019 and 2024 were identified through searches of PubMed, CINAHL, IEEE Xplore, and the ACM Digital Library. A total of 41 studies were selected and classified using Keadle's five-phase validation framework, distinguishing technical validation (Phases I–III) from applied implementation (Phase IV). Fifteen studies (36.6%) included typically developing infants, 22 (53.7%) included infants with or at-risk for developmental disabilities, and 4 (9.8%) were unspecified. Fifteen studies (36.6%) focused on technical validation; 26 (63.4%) implemented sensors in applied contexts. Triaxial accelerometers (n = 15) and IMUs (n = 24) were most common, with sampling frequencies from 1–150 Hz. Posture classification accuracy was 95.8%–98.2% in studies directly comparing posture and movement, whereas fine-grained movement classification was near 81%–84%. Reference-standard correspondence was generally strong for accumulated posture duration (r = 0.80–0.99) but more variable for movement and clinical measures (r = 0.61–0.98). Application studies quantified physical activity, movement coordination and complexity, and intervention responsiveness, with over half collecting home-based data. Wearable sensors have evolved from proof-of-concept systems to family-centered digital health tools supporting developmental monitoring and physical activity promotion. When paired with caregiver feedback and infant-centered design, these technologies may support families, complement clinic-based assessment, and extend developmental support access. Future research should prioritize standardized reporting, affordability, and open-source analytic pipelines to advance equitable implementation. Author summary: Infant movement provides important information about early health and development, but it is difficult to measure continuously during everyday life. Wearable sensors offer a way to monitor infant activity and posture outside the clinic, including in the home. In this review, we examined 41 studies published between 2019 and 2024 that used wearable sensors to measure movement during the first year of life. We found that accelerometers and other motion-sensing devices could often identify infant posture and gross activities with high accuracy. Researchers also used these technologies to study physical activity, movement coordination, developmental differences, and responses to intervention. More than half of the applied studies collected data in home settings, showing growing interest in real-world use. However, differences in devices, methods, reporting, affordability, and data analysis continue to limit comparison and widespread adoption. Wearable sensors may eventually help families and healthcare professionals monitor development over longer periods and complement clinic-based assessments, but more consistent, accessible, and infant-centered approaches are needed.
SN - 2767-3170
ER -