THE USE OF MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE IN MODERN PARASITOLOGY

Currently, a direction that uses new methods based on machine learning and artificial intelligence principles may become relevant in modern parasitology. The use of advanced computing along with traditional parasitological techniques makes it possible to increase the accuracy and effectiveness of parasitological research and create predictive models for preventive measures. Many studies in parasitological science are related to the issues of visual identification of parasitic objects, as well as new forms of building predictive models for the formation of natural and synanthropic foci. Model-building is one of the most important stages in predicting risks of parasitic infection dissemination in local areas. Neural network-based image analysis makes it possible to automatically identify parasitic organisms with quick and accurate identification of their species and development stages in the studied samples. The combination of artificial intelligence and epizootology led to predictive modeling which helps to make further predictions of dangerous outbreaks of parasitic diseases. Based on the data provided, such as natural factors, behavioral characteristics of vectors, and their behavior, artificial intelligence can provide an objective picture of temporal and spatial dissemination of parasitic invasions.