A Hybrid Artificial Intelligence and Data Envelopment Analysis Model for Effective Malaria Diagnosis
Muhammad Yusuf Muhammad, Adeyemi Abel Ajibesin · 2025
Malaria is a life-threatening disease affecting millions globally, with a particularly severe impact in tropical and sub-Saharan Africa, where millions of deaths have been recorded over the decades. Traditional clinical methods for diagnosing malaria, such as microscopic examination of blood smears, rapid diagnostic tests (RDTs), and advanced techniques like polymerase chain reaction (PCR), flow cytometry, and fluorescent microscopy, have yielded significant results; however, they often lack accuracy. Limitations such as complexity, time consumption, reliance on human expertise, and inapplicability in field settings highlight the need for a computer-assisted approach to address these challenges. This research proposes an artificial intelligence solution utilizing a machine learning framework, specifically leveraging the capabilities of Convolutional Neural Networks (CNNs) for enhanced diagnostic accuracy. Additionally, it introduces the application of Data Envelopment Analysis (DEA) to evaluate and optimize the efficiency of the proposed AI model in diagnosing malaria.