Learning Developmental Age from 3D Infant Kinetics Using Adaptive Graph Neural Networks
This provides a quantitative and interpretable method for early detection of neurodevelopmental issues in infants, though it is incremental as it builds on existing graph neural network techniques.
The paper tackled the problem of neurodevelopmental assessment in infants by introducing Kinetic Age (KA), a data-driven metric that predicts an infant's age from movement patterns, achieving improvement over traditional machine learning baselines.
Reliable methods for the neurodevelopmental assessment of infants are essential for early detection of problems that may need prompt interventions. Spontaneous motor activity, or 'kinetics', is shown to provide a powerful surrogate measure of upcoming neurodevelopment. However, its assessment is by and large qualitative and subjective, focusing on visually identified, age-specific gestures. In this work, we introduce Kinetic Age (KA), a novel data-driven metric that quantifies neurodevelopmental maturity by predicting an infant's age based on their movement patterns. KA offers an interpretable and generalizable proxy for motor development. Our method leverages 3D video recordings of infants, processed with pose estimation to extract spatio-temporal series of anatomical landmarks, which are released as a new openly available dataset. These data are modeled using adaptive graph convolutional networks, able to capture the spatio-temporal dependencies in infant movements. We also show that our data-driven approach achieves improvement over traditional machine learning baselines based on manually engineered features.