JMIR Publications

ABSTRACT

Background:

As the demand for youth mental health care continues to rise, managing wait times and reducing treatment delays are key challenges to delivering timely and quality care. Clinical staging is a heuristic model for youth mental health that can stratify care allocation according to an individual’s risk of illness progression. The application of staging has been traditionally limited to trained clinicians, yet if digital technologies could be leveraged to apply clinical staging, then this could increase the scalability and utility of this model in services.

Objective:

The aim of this study is to validate a digital algorithm to accurately differentiate young people at lower and higher risk of developing mental disorders.

Methods:

The cohort comprised 131 young people, aged between 16 to 25 years, who presented to youth mental health services in Australia for the first time between November 2018 to March 2021. Clinical stages (either stage 1a or stage 1b+) were allocated independently by expert psychiatrists and compared to the digital algorithm based on a multidimensional self-report questionnaire.

Results:

Of the 131 participants, the mean (SD) age was 20.3 (2.4) years and 94 (71.8%) were female. Ninety-one percent of clinical stage ratings were concordant between the digital algorithm and the expert ratings with a substantial interrater agreement (κ=0.67, P<.001). The algorithm demonstrated 90.8% (95% CI 85.6 – 95.2%, P=0.03) accuracy, 80.0% sensitivity, 92.8% specificity, and F1-score of 72.7%. Of the agreement, 16 young people were allocated to stage 1a, while 103 were assigned to stage 1b+. Among the 12 discordant cases, the digital algorithm allocated a lower stage (stage 1a) to eight participants with lower levels of depressive mood (P<.001) and anxiety symptoms (P<.001) compared to the experts.

Conclusions:

This novel digital algorithm is sufficiently robust to be used as an adjunctive decision support tool to stratify care and assist with demand management in youth mental health services. This work could transform care pathways and expedite care allocation for those in early stages of common anxiety and depressive disorders. Between 11% and 27% of young people presenting for care may be suitable for low intensity online or brief interventions, creating additional clinical capacity to be directed towards those who are in stage 1b+ for further assessment and intervention.