Spatial Statistical Machine Learning Models to Assess Health Vulnerabilities in Children

Abstract

Background: The health and development of children during their first year of school is known to impact their social, emotional, and academic capabilities throughout and beyond early education. Physical health, motor development, social and emotional well-being, learning styles, language and communication, cognitive skills, and general knowledge are all considered to be important aspects of a child’s health and development. It is important for many organisations and governmental agencies to continually improve their understanding of the factors which determine or influence health vulnerabilities among children. This article studies the relationships between health vulnerabilities and educational factors among children in Queensland, Australia. In Queensland, the percentage of children who are developmentally vulnerable in at least one domain in 2018 was around 26%, and the overall percentage of attendance at preschool was around 75.4% These are the lowest rates among all states and territories of Australia. There is also substantial geographic variation in rates across the state. Methods: Spatial statistical machine learning models are reviewed and compared in the context of a study of geographic variation in the association between health vulnerabilities and attendance at preschool among children in Queensland, Australia. A new spatial random forest (SRF) model is suggested that can explain more of the spatial variation in data than other approaches.Results: In the case study, spatial models were shown to provide a better fit compared to models that ignored the spatial variation in the data. The SRF model was shown to be the only model which can explain all of the spatial variation in each of the health vulnerabilities considered in the case study. The spatial analysis revealed that the attendance at preschool factor has a strong influence on the physical health domain vulnerability and emotional maturity vulnerability among children in their first year of school. Conclusion: This study confirmed that it is important to take into account the spatial nature of data when fitting statistical machine learning models. A new spatial random forest model was introduced and was shown to explain more of the spatial variation and provide a better model fit in the case study of health vulnerabilities among children in Queensland. At small-area population level (statistical area level 2 (SA2)), increased attendance at preschool was strongly associated with reduced physical and emotional health vulnerabilities among children in their first year of school.