ChAMP Background

What is ChAMP?

Background: Internalizing disorders, such as anxiety and depression, in pre-school aged children are common and often go undiagnosed into adulthood. Delayed intervention can increase risk for interpersonal impairments, substance abuse, and increased risk for suicide, thus, early identification is crucial. However, early subjective assessment of anxiety and depression present challenges as self-reports are not reliable in children younger than 8 years, and parental-reports often exhibit bias and poor sensitivity. Previously, we have presented an objective assessment demonstrating good accuracy (75%-81%) in identifying early childhood anxiety and depression which uses physiology (motion and audio) measured via wearable sensors during brief mood induction tasks. However, these methods required specialized equipment and expertise in data and sensor engineering to administer and analyze.

Method: To improve ecological validity, we have developed the ChAMP System, which includes an Android mobile application for collecting movement and audio data during mood induction tasks, a waist belt for attaching the phone to participants, and an open-source data analysis platform for extracting digital biomarkers and discovering digital phenotypes. As proof of principle, we present data collected using the ChAMP System from 50 children ages 5-8, with and without anxiety or depressive disorders.

Results: Results indicate that several movement and audio-derived features significantly differ between diagnostic status groups and correlate with symptom severity. We provide a route for other researchers to request usage of the ChAMP System, lowering the barrier to entry for those interested in exploring digital phenotyping of childhood mental health but who may not have the background in signal processing or data science.

Conclusions: We aim to continue to build this scalable platform to aid in early identification of anxiety and depressive disorders in young children by crowd-sourcing validation efforts and making it accessible to researchers across domains and locations.

Foundational Research supporting the development of ChAMP

Primary Articles

• McGinnis EW, Copeland W, Shanahan L, Egger HL. Parental perception of mental health needs in young children [published online ahead of print, 2021 Oct 15]. Child Adolesc Ment Health. 2021;10.1111/camh.12515. doi:10.1111/camh.12515

• McGinnis RS, McGinnis EW. Advancing Digital Medicine with Wearables in the Wild. Sensors (Basel). 2022;22(12):4576. Published 2022 Jun 17. doi:10.3390/s22124576

• McGinnis EW, Scism J, Hruschak J, et al. Digital Phenotype for Childhood Internalizing Disorders: Less Positive Play and Promise for a Brief Assessment Battery. IEEE J Biomed Health Inform. 2021;25(8):3176-3184. doi:10.1109/JBHI.2021.3053846

• McGinnis EW, McGinnis RS, Hruschak J, et al. Wearable sensors detect childhood internalizing disorders during mood induction task. PLoS One. 2018;13(4):e0195598. Published 2018 Apr 25. doi:10.1371/journal.pone.0195598

• McGinnis RS, McGinnis EW, Hruschak J, et al. Rapid detection of internalizing diagnosis in young children enabled by wearable sensors and machine learning. PLoS One. 2019;14(1):e0210267. Published 2019 Jan 16. doi:10.1371/journal.pone.0210267

• McGinnis RS, McGinnis EW, Hruschak J, et al. Rapid Anxiety and Depression Diagnosis in Young Children Enabled by Wearable Sensors and Machine Learning. Annu Int Conf IEEE Eng Med Biol Soc. 2018;2018:3983-3986. doi:10.1109/EMBC.2018.8513327

• McGinnis EW, McGinnis RS, Muzik M, et al. Movements Indicate Threat Response Phases in Children at Risk for Anxiety. IEEE J Biomed Health Inform. 2017;21(5):1460-1465. doi:10.1109/JBHI.2016.2603159

• McGinnis EW, Anderau SP, Hruschak J, et al. Giving Voice to Vulnerable Children: Machine Learning Analysis of Speech Detects Anxiety and Depression in Early Childhood. IEEE J Biomed Health Inform. 2019;23(6):2294-2301. doi:10.1109/JBHI.2019.2913590

• Loftness BC, Halvorson-Phelan J, O’Leary A, Cheney N, McGinnis EW, McGinnis RS. UVM KID Study: Identifying Multimodal Features and Optimizing Wearable Instrumentation to Detect Child Anxiety. Annu Int Conf IEEE Eng Med Biol Soc. 2022;2022:1141-1144. doi:10.1109/EMBC48229.2022.9871090

• McGinnis, Ellen; McGinnis, Ryan; Hruschak, Jessica; Bilek, Emily; Ip, Ka; Morelen, Diana; Lawler, Jamie; Fitzgerald, Kate; Rosenblum, Katherine; and Musik, Maria. 2018. Wearable Sensors Outperform Behavioral Coding as Valid Marker of Childhood Anxiety and Depression. PlosOne. Vol.13(4). https://doi.org/10.1371/journal.pone.0195598

• Torous J, Kiang MV, Lorme J, Onnela JP. New Tools for New Research in Psychiatry: A Scalable and Customizable Platform to Empower Data Driven Smartphone Research. JMIR Ment Health. 2016;3(2):e16. Published 2016 May 5. doi:10.2196/mental.5165

Request Usage of the ChAMP System

To request download access for the ChAMP mobile application, please fill out this form or scan this QR code.