Evidence for Smartwatch-Derived Cardiac Measurements as Biomarkers of Therapeutic Response in Children With Disruptive Behavior Disorder

Objective Disruptive behaviors are thought to involve dysregulation in the autonomic nervous system (ANS), but a consistent relationship between autonomic measurements and behavioral severity and/or treatment response has not been established in pediatric populations. Digital health technologies (e.g. wearables) serve as a scalable and accessible means to derive biomarkers of therapeutic response reflective of dysregulation in the ANS. This study examined whether smartwatch-derived heart rate (HR) and heart rate variability (HRV) metrics change over the course of Parent–Child Interaction Therapy (PCIT) and whether these changes relate to behavioral improvement. Method Continuous smartwatch data were collected from children aged 3–7 years (N = 50) enrolled in a 12-session PCIT trial, of whom 36 met wear-time criteria and were included in the final analysis. Weekly Eyberg Child Behavior Inventory (ECBI) assessments were the primary clinical outcome. Linear and quadratic mixed models were used to assess changes in HR measurements and their relationship to ECBI scores. Stimulant and non-stimulant medication use for comorbid ADHD as well as sociodemographic covariates were included in each model. Results The results demonstrated that throughout treatment, there was a significant decrease in both resting HR and average HR (p < 0.001) with number of sessions, as well as an increase in HRV (p = 0.04). Resting HR and average HR both demonstrated a quadratic relationship with ECBI Intensity T Scores (p = 0.01 and p=0.01, respectively), meaning that moderate HR was associated with lower levels of disruptive behavior. Conclusion These results demonstrate changes over time in autonomic variables and support the potential value of cardiac measurements in the comprehensive monitoring of patients undergoing treatment for disruptive behaviors. The use of commercial wearable devices provides scalable and ecologically valid results, which may prove to be useful in the future treatment of pediatric disruptive behaviors. Clinical trial registration information Monitoring of Sleep and Behavior of Children 3-7 Years Old Receiving Parent-Child Interaction Therapy With the Help of Artificial Intelligence; https://clinicaltrials.gov/study/NCT05077722 Diversity & Inclusion Statement We worked to ensure sex and gender balance in the recruitment of human participants.