Discriminative models of spontaneous kicking movement patterns for term and preterm infants: A pilot study

Abstract

In this paper, we discuss machine learning methods for classifying gross kicking activity for the term and preterm infants. We examine different combinations of sensors to determine the relative importance of each sensor to gross activity detection. In addition, we discuss methods to correlate infant age to the amount of time an infant performs unilateral vs bilateral kicking and time an infant is at rest. For preterm infants, we examine this same relationship using birth age and adjusted age. From this comparison, we aim to determine which age is a better predictor for movement breakdown. For gross activity recognition, it was determined that a sensor placed on the thigh was less important to overall recognition than a sensor placed on the foot or shin. In addition, a sensor placed on the foot tended to be the most accurate on its own while the thigh sensor tended to be the least accurate. For the relationship between infant age and movement breakdown, it was determined that the amount of time spent at rest increases as age increases. Furthermore, the amount of time spent performing bilateral kicking decreases at a more rapid rate than unilateral kicking as age increases. Finally, we examine how this relationship changes over time for infants observed over multiple months.