Ecological Momentary Assessment of Emotional Dysregulation and Outbursts among Youth with ADHD: A Feasibility Study of a Biomarker-Driven Predictive Algorithm in the Special Education Pre-K and Early Childhood Classroom Settings

Ripudaman Singh ^1* Janav Panchal ¹ Sami Ali ¹ Beth Krone ² Isaac J Wert ² Mark Owens ³ Mark Stein ⁴ Maulik V Shah ¹

• ¹ MaxisHealth LLC, Edison, United States
• ² Icahn School of Medicine at Mount Sinai, New York, New York, United States
• ³ Department of Child and Adolescent Psychiatry, School of Medicine, New York University, New York, New York, United States
• ⁴ University of Washington, Seattle, Washington, United States

BACKGROUND: Attention Deficit Hyperactivity Disorder (ADHD) among children younger than 6 years is quite impairing, nearly half these youth with ADHD experience school exclusion from mainstream preschool classes due to related emotional and behavioral outbursts. While a range of behavior rating scales and subjective measures are used to assess these youth, objective methods of assessment and prediction derived from technology have potential to improve therapeutic and academic interventions outcomes for these youths. We hypothesized that biometric sensors would provide objective, highly sensitive and specific information regarding the physiological status of children prior to an impulsive outburst and could be feasibly implemented using a wearable device in the special education classroom. METHODS: We recruited two whole classrooms (N=5 youth in the pre-K class and N=5 youth from the first grade) of a specialized therapeutic day-school for youth with ADHD and other psychiatric and developmental disorders to examine feasibility of obtaining continuous physiological data associated with behavioral and emotional outbursts through smartwatch use.Children wore a sensor watch during their daily classroom activities for two weeks and trained observers collected data using behavioral logs. Using ecological momentary assessment methodology, to examine correlations between objective sensor data and observer observation. Data collected from parents regarding prior night's sleep was also examined. RESULTS: All participants completed the study. With a few tolerability or palatability issues. Associations were found between physiological and behavioral/ questionnaire data. The methodology holds promise for reliably measuring behavioral and emotional outbursts in young children. CONCLUSIONS: This is the first study to use a bio-marker device in-vivo among severely dysregulated pre-school aged youth throughout a full school day. This study established the feasibility of utilizing sensor derived physiological data as an objective biomarker of ADHD within the special education therapeutic classroom. Further research with larger samples is required to build a more robust and personalized AI predictive model.