Artificial Intelligence for Neglected Tropical Diseases: Enhancing Diagnosis, Drug Discovery and Public Health Surveillance

Neglected tropical diseases (NTDs) continue to affect the high risk populations in low income countries, where diagnosis are delayed, have been limited therapeutics options and poor surveillance systems remain major barriers to control. Artificial Intelligence becomes an emerging and promising tool to address these gaps by improving the detection of diseases, accelerating drug discovery, and helping in drug repurposing and strengthening in outbreak prediction. This review summarizes the recent applications of Machine Learning, Deep Learning and Explainable AI in NTD management, with importance in Leishmaniasis, Schistosopmiasis, Chagas Disease and Human African Trypanosomaisis. AI based models shown value in biomarker discovery, microscopic image analysis, clinical symptom interpretation and epidemiological forecasting using multimodal datasets including genomic, imaging, environmental and clinical information. Concurrently, AI has demonstrated potential in target identification, virtual screening, physicochemical property prediction and formulation development as a result reducing its time, cost and experimental burden in drug development. Though its has advantages, major challenges are there which includes data scarcity, model interpretability, external validation and equitable deployment in endemic regions. Overall AI offers a powerful framework for improving diagnosis, therapy discovery and public health surveillance in NTDs. With continuing collaboration with clinicians, data scientists and public health researcher it will be essential to translate these advances into practical and scalable solutions for affected populations.