Artificial Intelligence Techniques for Predictive Modeling of Vector-Borne Diseases and its Pathogens: A Systematic Review

Vector-borne diseases (VBDs) have a significant impact on human and animal health. VBD has been emerging or re-emerging in a variety of geographic regions, raising alarming new disease threats and economic losses. As a result, techniques based on Artificial Intelligence have been utilized to anticipate vector-borne diseases. Specifically, this study examines the various techniques used in previous studies, including individual and ensemble methods, parameters or variables, dataset types, and performance measures. We examined four databases for scholarly articles published from 2010 to 2021 that discussed prediction models for vector-borne illnesses. The results indicated that increasing air travel and uncontrolled mosquito vector populations were mostly responsible for the population's decline in health. We reviewed a count of 159 studies on the aedes mosquito, the anopheles' mosquito, the culex mosquito, the triatome bug, the lice, the ticks, the fleas, and the blackflies etc. Our research conducted numerous investigations and summarizes the automated learning techniques utilised in VBD predictive modelling in this article. There is a need for more evidence to ensure that machine and deep learning models can be included in regular diagnostic care. Studies on VBD prediction models should be included to aid practitioners and patients in making medical decisions.

Automated summary

Vector-borne diseases have a significant impact on human and animal health. Artificial intelligence techniques have been used to predict these diseases, and the increase in air travel and uncontrolled mosquito vector populations are major factors contributing to the decline in population health.