Leveraging AHP and transfer learning in machine learning for improved prediction of infectious disease outbreaks

Abstract

Infectious diseases significantly impact both public health and economic stability, underscoring the critical need for precise outbreak predictions to effictively mitigate their impact. This study applies advanced machine learning techniques to forecast outbreaks of Dengue, Chikungunya, and Zika, utilizing a comprehensive dataset comprising climate and socioeconomic data. Spanning the years 2007 to 2017, the dataset includes 1716 instances characterized by 27 distinct features. The researchers adopt the Analytic Hierarchy Process (AHP) for feature selection and integrated transfer learning to boost the accuracy of the study's predictions. The researchers' approach involves the deployment of several machine learning algorithms, including Random Forest, XGBoost, Gradient Boosting, and an ensemble of these methods. The result reveals that the ensemble model is particularly effective, achieving the highest accuracy rate of 96.80% and an AUC of 0.9197 for predicting Zika outbreaks. Furthermore, it exhibts consistent performance across various metrics. Notably, in the context of Chikungunya, this model achieves an optimal balance between precision and recall, with an accuracy of 93.31%, a precision of 57%, and a recall of 63%, highlighting its reliability for effective outbreak prediction.