JMIR Publications

ABSTRACT

Background:

Adolescents living with HIV are disproportionally affected by depression which in turn worsens their adherence to HIV antiretrovirals (ART), increases viral load, and doubles their risk of mortality. Because most adolescents living with HIV live in low- and middle-income countries (LMIC), few receive depression treatment due to a lack of mental health services and specialists in low-resource settings. Chatbot technology, used increasingly in health service delivery, could be a promising avenue for delivering low-intensity mental health care to adolescents living with HIV in resource-constrained settings.

Objective:

The goal of our study is to develop and pilot test for feasibility and acceptability a prototype, optimized conversational agent (chatbot) to provide mental health education, self-help skills, and care linkage for adolescents living with HIV.

Methods:

The development of the chatbot comprises three phases conducted over 2 years. In the first phase (year 1), we will conduct formative research to understand the views, opinions, and preferences of up to N=48 adolescents aged 11-19 (6 focus groups of up to N=8 adolescents living with HIV per group), their caregivers (N=5 in-depth interviews), and HIV program personnel (N=5 in-depth interviews) regarding depression among adolescents living with HIV. We will also investigate the perceived acceptability of a mental health chatbot, including barriers and facilitators to accessing and using a chatbot for depression care by adolescents living with HIV. In the second phase (year 1), we will iteratively program a chatbot with successive versions (0.1, 0.2, 0.3), meeting regularly with a Youth Advisory Board comprised of adolescents living with HIV who will guide and inform the chatbot development and content to arrive at a prototype version (version 1.0) for pilot testing. In the third phase (year 2), we will pilot test for feasibility and acceptability the prototype chatbot among N=50 adolescents living with HIV naïve to its development. Data will be collected on the acceptability of the chatbot-delivered education and self-help strategies, depression knowledge changes, and intention to seek care linkage.

Results:

By the completion of study phases 1 and 2, we expect our chatbot to incorporate key needs and preferences gathered from focus groups and interviews for managing mental health among adolescents living with HIV. By the completion of study phase 3, we will have assessed the feasibility and acceptability of the prototype chatbot. The study commenced in January 2023, and study phase 3 is planned to begin by March 2024. Final results are expected by January 2025.

Conclusions:

The study will produce a prototype mental health chatbot developed with and for adolescents living with HIV that will be ready for efficacy testing in a subsequent, larger study. Clinical Trial: N/A – This study is not an RCT.