Optimizing Tabular Vector-Borne Disease Surveillance with Machine Learning Classification Techniques

Vector-borne diseases (VBDs) represent a critical global health challenge due to the rising incidence and potential for serious outcomes. This study aims to enhance VBD surveillance by leveraging machine learning classification techniques to identify and predict vector-borne diseases based on symptomatology. Using a comprehensive dataset sourced from Kaggle, multiple classification algorithms, including Support Vector Machines, K-Nearest Neighbors, Logistic Regression, Decision Tree, Random Forest, and Multi-Layer Perceptron, were applied and evaluated. The results demonstrate that the Multi-Layer Perceptron model achieved the highest accuracy, underscoring its effectiveness in disease classification. The findings of this study support the advancement of public health initiatives, enabling proactive disease management through optimized VBD prediction and classification.