Journal of E-Governance and Digital Transformation in Africa (Technology | 13 August 2012
AI-Aided Diagnostics in Malawi's Resource-Constrained Healthcare Settings
C, h, a, n, z, u, M, a, l, i, p, o
Abstract
AI-aided diagnostics have shown promise in resource-limited healthcare settings by enhancing accuracy and efficiency of disease diagnosis. A cross-sectional study was conducted using machine learning models trained on a dataset of clinical records from Malawian healthcare facilities. The study aimed to assess model accuracy through precision and recall metrics. The AI models achieved an overall accuracy rate of 85% in diagnosing common diseases, with higher precision for malaria cases (90%) compared to tuberculosis (75%). AI-aided diagnostics can significantly improve disease diagnosis outcomes in resource-constrained settings. Further research should focus on model validation across different geographic regions and the integration of AI into existing healthcare workflows. AI, Diagnostics, Malawi, Precision, Recall 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.