Measurement-Based Mental Health Care for Adolescents in Africa: Protocol for a Computerized Adaptive Test

Adolescent mental health care is constrained not only by limited treatment capacity but also by the absence of precise and efficient tools to identify and triage those in need. Measurement-based mental health care relies on standardized assessments to guide identification, treatment selection, and ongoing monitoring of mental disorders. However, conventional assessments present a trade-off: diagnostic interviews lack feasibility at scale, while brief screening tools result in misclassification and suboptimal allocation of limited mental health resources. Computerized adaptive testing addresses this trade-off by dynamically tailoring assessments to individuals, maximizing measurement precision while minimizing assessment burden. Despite these advances, no adaptive assessment for adolescent mental health has been developed or calibrated using African data.

The AfriCAT study aims to develop and internally validate a precision computerized adaptive assessment of adolescent depression and anxiety using nationally representative Kenyan data, with the longer-term goal of supporting measurement-based mental health care across diverse African contexts.

AfriCAT is a mixed methods study integrating psychometric modeling, adaptive simulation, modular clinical decision support networks, participatory workshops, discrete choice experiments (DCEs), and stakeholder interviews. Diagnostic Interview Schedule for Children, version 5 (DISC-5) modules assessing major depressive disorder, generalized anxiety disorder, social phobia, and posttraumatic stress disorder among adolescents aged 10 to 17 years from the Kenya National Adolescent Mental Health Survey (N=5155) will form the item bank. Adaptive engines will be developed using a bifactor multidimensional item response theory framework and a modular neural architecture. Simulation-based internal validation will evaluate precision, efficiency, and diagnostic classification relative to DISC-5 diagnoses. Participatory workshops in Kenya and South Africa, DCEs to quantify adolescent preferences, and stakeholder interviews will inform refinement of adolescent- and provider-facing prototypes.

Ethical approval has been obtained from the Human Research Ethics Committee (Medical) at the University of the Witwatersrand and the Aga Khan University Institutional Scientific and Ethics Review Committee. Data preparation and model development are underway. Participatory workshops and DCEs are ongoing. Simulation-based validation and prototype refinement will follow.

AfriCAT aims to develop the first adaptive mental health assessment calibrated using nationally representative African adolescent data. By integrating precision psychometrics with participatory co-design, the study seeks to enable more accurate triage and support scalable, measurement-based adolescent mental health care in resource-constrained settings.