JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Gross motor performance of infants with an at-home wearable measurement and the Alberta Infant Motor Scale: A concurrent validity study

  • 0BABA Center, Pediatric Research Center, New Children's Hospital, Helsinki University Hospital, Helsinki, Finland.
Developmental Medicine and Child Neurology +

|

February 17, 2026

|

February 17, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

At-home wearable sensors accurately assess infant gross motor skills, showing strong correlation with the Alberta Infant Motor Scale (AIMS). This technology offers a scalable, objective alternative for monitoring infant development in various settings.

Area Of Science

  • Pediatric motor development assessment
  • Wearable technology in healthcare
  • Infant gross motor performance evaluation

Background

  • The Alberta Infant Motor Scale (AIMS) is a standard tool for assessing infant motor development.
  • Current assessment methods can be resource-intensive and require specialized clinical settings.
  • There is a need for scalable, objective, and accessible methods for monitoring infant motor skills.

Purpose Of The Study

  • To evaluate the concurrent validity of a novel at-home wearable measurement system against the AIMS.
  • To assess the reliability of wearable technology in capturing infants' gross motor performance.

Main Methods

  • An observational study utilized the Motor Assessment of Infants with a JUmpsuit (MAIJU) wearable device for 67 at-home measurements in 42 infants (aged 4-18 months).
  • Data included a normative cohort and a clinical cohort from a neurodevelopmental follow-up clinic.
  • Correlations were drawn between the expert-assessed AIMS score and the MAIJU-derived BABA Infant Motor Score (BIMS), alongside machine learning predictions.

Main Results

  • A very strong correlation (Spearman's rho = 0.97, p < 10^-40) was found between the BIMS and AIMS scores.
  • High agreement (Cohen's kappa = 0.81) was observed in detecting low-performing infants using centile-based cut-offs between AIMS and BIMS.
  • Machine learning-based AIMS predictions from wearable data showed comparable performance (rho = 0.96, p < 10^-37) to direct BIMS score utilization.

Conclusions

  • Scalable, at-home wearable measurements demonstrate high comparability to the established AIMS assessment for infant motor performance.
  • The MAIJU system provides an objective, quantitative, and expert-independent method for motor assessment.
  • This technology shows significant promise for widespread application in distributed healthcare and clinical trials for infant monitoring.