Self-Care from Anywhere: Evaluating the usability of an AI-powered HIV toolkit among adolescent girls and young women and healthcare providers in South Africa
Read the full pre-print publication here
Background HIV remains a major public health challenge in South Africa, with gaps in early diagnosis and linkage to care driving onward transmission. Adolescent girls and young women face barriers to timely care, including stigma, privacy concerns, and limited clinic access, while healthcare providers work in resource-constrained settings with high client volumes. We evaluated the Self-Care from Anywhere (SCFA) toolkit, an AI-enabled intervention comprising an AI Companion for AGYW and a provider-facing Clinical Portal to support HIV prevention, testing, and linkage to care. The AI Companion is designed to complement and extend human-delivered services, particularly in resource constrained settings, rather than replace in-person counselling.
Methods We conducted an exploratory study to assess the usability, feasibility, and acceptability of the SCFA toolkit in Gauteng Province (November 2024-May 2025). AGYW engaged with the AI Companion, and a subset completed a simulated HIV self-testing activity with AI-delivered counselling. Pre and post-intervention surveys, including the System Usability Scale (SUS), were administered. Usability testing of the Clinical Portal involved healthcare providers using the toolkit without formal training to capture first impressions. A subset of AGYW and healthcare providers participated in separate focus group discussions or in-depth interviews. Quantitative data were analysed using descriptive statistics, and qualitative data were analysed thematically.
Results A total of 97 AGYW were enrolled; 75.3% had completed high school and 91.8% were unemployed or full time students. Most participants (85.6%) self-reported HIV-negative status, and 63.9% reported sexual activity in the past 12 months. The AI Companion demonstrated high usability (mean SUS 87.7, SD 12.7) and was perceived as acceptable and useful, particularly for its personalisation and confidentiality features. Healthcare providers had a mean age of 34 years (SD 6.5), with about half serving as HIV testing and screening counsellors. Most providers rated the Clinical Portal’s ease of use, comprehension, and client support as positive to very positive, though 23% expressed concerns regarding workflow efficiency and their ability to manage additional client volume. Providers also highlighted the Clinical Portal’s value for case management.
Conclusion AI-powered digital health tools, such as the SCFA toolkit, show potential to enhance user engagement and support care delivery, with high usability and acceptability demonstrated among AGYW and healthcare providers. Continued user-centred refinement is essential to ensure these tools remain responsive to the evolving needs and care contexts of diverse user groups.
