Related Experiment Video
Updated: Jul 2, 2026

09:24
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
Published on: May 17, 2024
Body position classification using wearable sensors in infants with cerebral palsy
Kari S Kretch1, Florencia A Enriques1, John M Franchak2
1University of Southern California, 1540 Alcazar St., Los Angeles, CA 90089, United States.
Infant Behavior & Development
|June 30, 2026
Summary
Wearable sensors and machine learning accurately classify body position in infants with cerebral palsy (CP). This technology can measure real-world motor behavior and learning opportunities for infants with CP.
Area of Science:
- Biomedical Engineering
- Developmental Pediatrics
- Machine Learning in Healthcare
Background:
- Infants with cerebral palsy (CP) face motor impairments that can affect learning opportunities.
- Measuring real-world motor behavior in infants with CP is crucial for understanding developmental challenges.
- Existing machine learning models for body position classification in typical development (TD) infants need validation for CP populations.
Purpose of the Study:
- To assess the validity of using machine learning and wearable sensors for classifying body position in infants with CP.
- To determine the most accurate machine learning model configuration for body position classification in infants with CP.
- To explore the potential of sensor data for quantifying motor behavior and learning opportunities in infants with CP.
Main Methods:
- Ten infants with CP and 19 infants with typical development (TD) wore four inertial sensors on their legs.
- Video recordings of 90 minutes per session were manually scored for five body positions: supine, prone, sitting, standing, and held.
- Random forest classifiers were trained using sensor-derived motion features, with varying dataset sizes and group compositions (CP, TD, CP and TD).
Main Results:
- Machine learning models trained on larger datasets including CP infant data showed highest accuracy.
- Final models achieved comparable performance for CP (86% accuracy) and TD infants (89% accuracy).
- Classifications demonstrated individual differences (ICCs = 0.682–0.999) and correlated with motor skill assessments.
Conclusions:
- Wearable sensors and machine learning provide a valid method for accurately classifying real-world body position in infants with CP.
- This technology can quantify motor behavior and learning opportunities, aiding in the assessment and support of infants with CP.
- The findings support the use of these tools to better understand and address the motor challenges faced by infants with CP.
