African Forced Displacement Studies (Broader than Conflict Portal - | 15 May 2001
AI in Mental Health Support Platforms for Refugees in Kenya: Engagement and Outcomes
K, a, m, a, u, K, i, h, a, r, a, ,, W, a, m, b, u, i, M, u, t, i, t, h, i, ,, N, y, a, m, u, N, g, u, n, j, i, r, i
Abstract
AI-assisted mental health support platforms have shown promise in addressing psychological distress among refugees, particularly in resource-limited settings such as Kenya. A comprehensive search strategy was employed across multiple databases, including PubMed and Scopus, focusing on studies published between and . Studies were selected based on predefined inclusion criteria to ensure a diverse sample. Engagement levels varied significantly among the platforms reviewed, with an average engagement rate of 47% over three months post-installation, indicating that user retention is crucial for effective mental health support delivery. AI-supported mental health apps have the potential to improve psychological outcomes in refugees by providing accessible and affordable therapy options. However, further research is needed to optimise platform design and user experience. Developers should focus on enhancing app usability and incorporating culturally sensitive content to increase engagement and effectiveness. Model estimation used $\hat{\theta}=argmin<em>{\theta}\sum</em>i\ell(y<em>i,f</em>\theta(x<em>i))+\lambda\lVert\theta\rVert</em>2^2$, with performance evaluated using out-of-sample error.