Abstract: Artificial intelligence (AI) plays a crucial role in the surveillance for, parasitic diseases, especially in the surveillance and early warning of schistosomiasis, malaria, and echinococcosis, the priority parasitic diseases in China. AI technologies, such as deep learning and multimodal data fusion, have enabled the automatic pathogen identification, spatiotemporal dynamic modeling, vector-host tracing, and risk prediction, significantly improving surveillance accuracy, timeliness, and intelligence. However, the in-deepth application of AI still faces significant challenges, including limited model generalization due to data quality and standardization deficiency, reduced robustness in open-environment surveillance, ethical concerns such as privacy problems and algorithmic bias, restricted technology deployment by inadequate primary healthcare resources and low surveillance effectiveness for rare parasitic diseases due to small-sample learning. To address these problems, it is necessary to strengthen interdisciplinary collaboration to improve data standardization, facilitate the development of interpretable AI, establish adaptive models with ethical frameworks, and improve grassroot-level adaptability of surveillance systems. This paper summarizes the current applications of AI and related challenges in the surveillance and early warning of priority parasitic diseases to provide reference for the appropriate application and future development of AI in this field.