Grant: Project Grant

Mental health problems are a pressing concern facing children today. Research shows that evidence-based psychotherapies for children's mental health problems are only moderately effective, and as many as 50% of children will fail to respond to treatment or will drop out of treatment. There is thus significant room for improvement. One way to improve outcomes for children and their families is to understand how psychotherapy works for children and to make personalized adjustments to optimize their effectiveness. The proposed research will investigate the biobehavioral regulation of negative emotion as a mechanism of children's response to psychotherapy for anxiety, depression, and behaviour problems. We will apply machine learning models to characterize how emotion regulation varies throughout the course of treatment. The research brings together an interdisciplinary research team of highly qualified researchers and knowledge users with expertise in child psychopathology, clinical research, machine learning, and knowledge translation. The proposed research is of utmost importance to the health sector, and particularly to children with lived experience and mental health agencies who serve these children and their families. The application of machine learning to mental health research is an innovative and leading-edge approach that stands to directly inform ways to tailor and personalize child psychotherapies. This is a necessary first step towards patient-oriented care pathways that tailor combinations of interventions to patient mental health needs to lead to a stronger (i.e., more effective and efficient) mental healthcare system.