Recent trends of infant motor activity estimation using wearable sensors: A scoping review

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.