Artificial Intelligence in Parasitology: Advancing Malaria Diagnosis, Treatment, and Control

Abstract

Parasitology remains essential for understanding parasites and the diseases they cause, with malaria persisting as a significant global health challenge. Traditional diagnostic methods, such as microscopy and rapid diagnostic tests (RDTs), face limitations, including misdiagnosis, prolonged turnaround time, and difficulty in detecting low-level infections, despite progress achieved through international control strategies. Furthermore, global issues such as drug resistance and climate change pose significant threats to these gains.

Artificial Intelligence (AI), particularly machine learning (ML) and deep learning (DL), is revolutionizing parasitology, especially in malaria diagnosis. AI-driven models, including Convolutional Neural Networks (CNNs), have demonstrated high diagnostic accuracy, reaching 98.4% in blood smear image classification (1). These tools provide faster, more sensitive, and accessible diagnostics, particularly in resource-limited environments. AI also supports drug discovery, predicts therapeutic efficacy based on resistance markers, facilitates personalized treatment, and enables early outbreak prediction by integrating meteorological and demographic data. In research, AI accelerates the identification of vaccine targets and the discovery of therapeutic molecules, significantly reducing development timelines.

While AI presents clear benefits in diagnostic precision, individualized therapy, and disease surveillance, challenges such as limited data availability, infrastructural barriers, and ethical considerations persist. Addressing these barriers through targeted investment, ethical frameworks, and cross-disciplinary collaboration is crucial for harnessing the full potential of AI in managing parasitic diseases, such as malaria, and advancing the field of parasitology.