Use of Mobile and Wearable Artificial Intelligence in Child and Adolescent Psychiatry: Scoping Review

Abstract

Background Mental health disorders are a leading cause of medical disabilities across an individual’s lifespan. This burden is particularly substantial in children and adolescents because of challenges in diagnosis and the lack of precision medicine approaches. However, the widespread adoption of wearable devices (eg, smart watches) that are conducive for artificial intelligence applications to remotely diagnose and manage psychiatric disorders in children and adolescents is promising. Objective This study aims to conduct a scoping review to study, characterize, and identify areas of innovations with wearable devices that can augment current in-person physician assessments to individualize diagnosis and management of psychiatric disorders in child and adolescent psychiatry. Methods This scoping review used information from the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A comprehensive search of several databases from 2011 to June 25, 2021, limited to the English language and excluding animal studies, was conducted. The databases included Ovid MEDLINE and Epub ahead of print, in-process and other nonindexed citations, and daily; Ovid Embase; Ovid Cochrane Central Register of Controlled Trials; Ovid Cochrane Database of Systematic Reviews; Web of Science; and Scopus. Results The initial search yielded 344 articles, from which 19 (5.5%) articles were left on the final source list for this scoping review. Articles were divided into three main groups as follows: studies with the main focus on autism spectrum disorder, attention-deficit/hyperactivity disorder, and internalizing disorders such as anxiety disorders. Most of the studies used either cardio-fitness chest straps with electrocardiogram sensors or wrist-worn biosensors, such as watches by Fitbit. Both allowed passive data collection of the physiological signals. Conclusions Our scoping review found a large heterogeneity of methods and findings in artificial intelligence studies in child psychiatry. Overall, the largest gap identified in this scoping review is the lack of randomized controlled trials, as most studies available were pilot studies and feasibility trials.

Optimizing Multitask Assignment of Internet of Things Devices by Reinforcement Learning in Mobile Crowdsensing Scenes

“…e MTA strategy must consider optimal resource allocation while ensuring system response time and data quality. As environmental data grow exponentially, MTA is sure to replace the conventional single-task assignment methods in large-scale complex scenarios [1,2]. Hence, an efficient and reasonable MTA method has certain research value and practical significance [3].…”

Wearable Artificial Intelligence for Anxiety and Depression: Scoping Review

“…Recently, there have been rapid ongoing developments in artificial intelligence (AI) technology and wearable technology for health care and clinical use, offering numerous advantages for individualizing diagnoses and the treatment management of psychiatric disorders, including anxiety and depression [10][11][12]. Wearable technology includes electronic devices that users can wear near the body (eg, smartwatches, smart glasses, and smart bracelets), on the body (eg, electrocardiogram electrodes), and in the body (eg, implantable smart patches) and electronic textiles (eg, smart clothes).…”

Machine learning in biosignals processing for mental health: A narrative review

“…About this topic, Perna et al (2018) describe how wearable biosensors and the analysis of electronic medical records can access massive quantities of data and become important instruments for applying precision medicine to psychiatry, especially with the support of supervised and unsupervised ML models (Perna et al, 2018). Welch et al (2022) work is instead focused on how ML enables to assess of psychiatric disorders in young people through wearable devices. The review finds ECG 2019): a ML model was designed to determine the effectiveness of the combined use of accelerometers and SC sensors to detect generalized tonic-clonic seizures, relying on the E4 wristbands (Empatica) for the detection of motion and SC.…”

“…The milestones research studies in Affective Computing. SC was additionally considered in the experiments involving Empatica E4) alongside information about movement, are considered in studies aiming to individualize diagnosis and the treatment of several psychiatric disorders (i.e., ADHD, learning disability, and autism spectrum, bipolar, and internalizing disorders;Welch et al, 2022).An exemplifying application of a wearable device to epilepsy can be found inRegalia et al (…”