Artificial Intelligence in Digital Microscopy for Parasitic Disease Diagnosis: Advances, Applications, and Challenges

Abstract Artificial intelligence (AI)–assisted digital microscopy is emerging as a transformative approach to improving the diagnosis of parasitic diseases, particularly in low-resource settings. Parasitic infections including malaria, helminthiases, and protozoan diseases remain a major public health burden in sub-Saharan Africa, where limited laboratory infrastructure and shortages of skilled personnel hinder timely and accurate diagnosis. Conventional microscopy, although considered the gold standard, is labour-intensive, time-consuming, and subject to inter-observer variability, limiting its scalability in high-burden settings. This review synthesizes current advances in AIdriven diagnostic technologies, with a focus on machine learning and deep learning applications in digital microscopy. Evidence from recent studies demonstrates that AI-enabled systems often integrated with low-cost, smartphone-based or portable microscopes can achieve diagnostic performance comparable to expert microscopists across a range of parasites, including Plasmodium, soil-transmitted helminths, Giardia, Entamoeba, Schistosoma, and Leishmania. These systems offer key advantages such as improved diagnostic accuracy and objectivity, reduced reliance on specialized expertise through task shifting, high-throughput screening capabilities, offline functionality, and potential integration into disease surveillance and mass drug administration programs. Despite these advances, several challenges persist, including limitations in data quality and generalizability, variability in hardware performance, infrastructural constraints, workforce training needs, and ethical considerations related to data use. Addressing these barriers through interdisciplinary collaboration, standardized validation frameworks, and context-specific implementation strategies will be critical for successful deployment. Overall, AI-assisted digital microscopy represents a scalable, cost-effective, and sustainable solution with significant potential to strengthen parasitic disease diagnosis and control in resource-constrained settings.