SVM Model-Based Digital System for Malaria Screening and Parasite Monitoring

Malaria continues to pose a persistent health challenge, necessitating innovative approaches for effective resolution. In this context, we present a novel digital methodology employing Support Vector Machines (SVM) for malaria screening and diagnosis, with the aim of augmenting diagnostic capabilities to address this pressing issue. Traditional methods of malaria diagnosis are characterized by slowness and reliance on specialized expertise. The SVM-based model we propose addresses this limitation by efficiently processing extensive malaria datasets, providing healthcare practitioners with a valuable tool for analysing crucial data. Notably, it excels in the classification of intricate blood smear images, automating the identification of parasites and distinguishing infected cells from their healthy counterparts. Our evaluation of the model demonstrates promising results. Particularly, the model showcases proficiency in distinguishing between four types of malaria parasites (pm, pv, po, and pf) with a commendable 72% accuracy rate. This level of accuracy holds significant potential for enhancing malaria diagnostics, particularly in the context of resource constraints. The user-friendly nature of our SVM model pioneers’ precise malaria diagnosis, effectively merging technological advancements with healthcare efforts in the ongoing battle against this ailment. By empowering healthcare professionals, our model contributes meaningfully to the global campaign against malaria.