AI Diagnostics in Resource-Constrained Healthcare: A Methodological Approach for Malawi's Context

AI diagnostics have shown potential in resource-constrained healthcare settings, particularly for disease diagnosis. A mixed-methods design was employed, incorporating surveys (N=100), interviews (n=25), and case studies (N=10) among healthcare providers and patients to understand current diagnostic practices and AI feasibility. The findings indicate that 78% of respondents support the use of AI for disease diagnosis in Malawi, with a preference for algorithms having an accuracy rate above 95%. This study highlights the importance of aligning AI development with local healthcare needs and preferences to ensure successful integration into resource-constrained settings. Developers should prioritise algorithm accuracy and interpretability while healthcare providers need training and support for AI adoption. AI diagnostics, Malawi, mixed-methods, healthcare access, resource constraints