Causal Effect of Parent-Child Relationship on Oppositional Defiant Disorder Symptoms Based on Machine Learning Approach

Abstract

Abstract Oppositional defiant disorder (ODD) is one of the most common disorders in children and is highly susceptible to further internalizing and externalizing problems. Research has addressed the multilevel family factors associated with the development of ODD, whereas it is necessary to further investigate the causal relationship between these factors and ODD for effective intervention. Due to the close association to ODD, we investigated the causal effect of parent-child relationship (PCR) on ODD symptoms using the machine learning based Causal Forest (CF) model with observed factual data in this study. Based on the PCR improvement in two consecutive years, 423 longitudinal children were divided into improved and control groups. The ODD symptoms in the second year was set as the dependent variable. Additionally, several factors based on the multilevel family model and the baseline ODD in the first year were included as covariates. The CF model showed PCR had a significant causal effect on ODD symptoms in the samples, which means the improvement of PCR could effectively alleviate the ODD symptoms. Furthermore, the causality exhibited heterogeneity. The causal effect was greater in those children with higher baseline ODD, worse family atmosphere, lower emotion regulation abilities in themselves or their parents. Conversely, the parenting style played a positive role on the causality which suggested the importance of parenting training in ODD families. This study would be helpful in forming personalized family-oriented intervention strategies for ODDs.