Deep Learning Approaches for Predicting Vector-Borne Disease Risks: A Case Study

Abstract

Insects such as mosquitoes, ticks, tsetse flies, and flies are the vectors. They spread most of the global vector-borne diseases. They are dangerous to health because they are highly sensitive to environmental changes and are toxic. Every year, effective disease control activities are implemented through interventions and innovations in pest control. However, traditional methods are costly, slow, and spatially limited. As the role of IT is broadly increasing, AI-driven methods can provide real-time, risk-free surveillance that is more efficient in disease control. The Sustainable Development Goals (SDGs) are key targets for global healthcare reform. Using AI, most models are capable of predicting the disease and can suggest forecasting from the available data, including expert knowledge. These systems use environmental factors (latitude, elevation, and precipitation) and can optimize disease forecasting in various regions of the Earth. This approach may revolutionize vector tracking and disease management. This study used an available online dataset to predict vector-borne diseases from existing data using a Deep Learning Model. This study identified diseases such as Dengue, Malaria, which are also propagated by mosquitoes.