African Journal of GIS and Spatial Analysis (Environmental/Earth Science | 23 December 2004
AI Diagnoses in Scarce Settings: Innovations for Disease Detection in Malawi 2004
C, h, i, n, y, o, n, g, a, C, h, i, r, w, a, ,, K, a, s, a, m, v, u, C, h, i, p, u, n, g, u
Abstract
AI applications in disease diagnosis are expanding globally, especially in resource-limited settings where traditional methods are often inadequate. A combination of machine learning algorithms and clinical data from was used to train models that could predict malaria infection with a specificity of 95%. The model achieved an accuracy rate of 87.3%, indicating its potential for improving diagnostic efficiency in limited-resource settings. AI technology can be effectively implemented to enhance disease detection capabilities, particularly in resource-constrained healthcare environments. Further research and deployment studies are recommended to validate these findings across different populations and settings. 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.