Date of Completion

2024

Document Type

Honors College Thesis

Department

Psychological Sciences

Thesis Type

Honors College

First Advisor

Dr. Ellen McGinnis

Second Advisor

Dr. Sayamwong Hammack

Keywords

digital phenotyping, child mental health, biomarkers, mental health, wearable sensors, KID Study

Abstract

Mental health disorders are prevalent in children, and early identification is critical to early intervention. Children who are too young to reliably report on their own mental states (children ages 4-8) are typically assessed via parent reports of their emotional and behavioral problems. Parent reports, however, are biased due to unobservable symptoms, and parental mental health literacy. With the advancement of physiological sensors, the prospect of digital phenotyping emerges as a potential avenue for supplementing parent reports with objective measures. The idea of measuring a child's behavior and inferring their physiological or mental state is not a new concept, though digital phenotyping may be a promising method for doing this reliably, efficiently, and cost effectively. This study examines child heart rate and motion to provide insight into a child's disorder status. Results suggest that motion alone may act as an accurate predictor of ADHD disorder status, but not heart rate alone. However, it is the asynchrony of motion and heart rate that together may act as a unique identifier of diagnoses including ADHD, internalizing disorders, and their Comorbidity. Multi-modal sensor data merits further study as digital phenotypes of mental health disorders in young children.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.

Download

Share

COinS