Health System Readiness for AI-Enabled Stroke Detection in Ethiopia

This study examines the feasibility, adoption drivers, and readiness for the deployment of an AI-powered stroke detection platform in Ethiopia, an emerging market with severe radiologist shortages. AI’s potential in radiology, especially for stroke detection, has been explored in several developing and emerging countries. In Ethiopia, though, this is the first study of its kind. Guided by Technology Acceptance Model (TAM) and Diffusion of Innovation (DOI) frameworks, we analyze survey data from healthcare stakeholders to quantify adoption readiness and to identify key contextual drivers. Descriptive results indicate that approximately 92% of respondents express willingness to pilot AI diagnostics. Advanced analyses, including a multivariable logistic regression, reveal that willingness to join a pilot and perceived usefulness are the strongest predictors of adoption intention, with pilot willingness associated with a nearly threefold higher likelihood of adoption. Findings suggest that contextual enablers such as affordability and design alignment with local needs (like local language support and offline functionality) are central to perceived ease and relative advantage, while trust and clinical validation shape overall adoption. This study concludes that Ethiopia offers a viable early-stage market for AI-driven diagnostic tools, driven primarily by perceived value and affordability rather than technical barriers. The research contributes actionable insights into how affordability, user-friendliness, and contextual adaptation can accelerate responsible AI deployment to bridge healthcare access gaps in resource-constrained emerging markets.