Abstract
The inherent challenges in recruiting human subjects, particularly infants, often hinder the acquisition of sufficiently large datasets for health research, thereby limiting the applicability of conventional machine-learning (ML) approaches. In this study, we analyze full-day motion recordings from two groups: typically developing infants (N = 12) and infants at risk for developmental disabilities (N = 24), further divided into those with good (N = 10) and poor (N = 9) developmental outcomes at 24 months. The goal is to differentiate at-risk (AR) infants from those with typical development (TD) and predict outcomes for the at-risk category using wearable data. Due to its limited size, previous studies on this dataset, employing statistical and machine learning methods, raise reliability concerns. To address this, we introduce a novel algorithmic approach to extract meaningful patterns, referred to as Motifs, from the raw signals. The abundance of Motifs serves as highly informative indicators, enabling effective differentiation between the groups. Evaluation on this limited-size dataset demonstrates the effectiveness of Motifs in distinguishing AR from TD infants and predicting future outcomes for the at-risk category.