A Novel Ensemble Approach for Dengue Fever Prediction

Abstract

Prediction of diseases at the right time and accurately is crucial for improving patients' health conditions and reducing costs of healthcare services. Therefore, machine learning approaches have recently become very popular in predicting diseases in patients. Dengue fever, which is a highly spreading mosquito-born disease caused by the virus, still poses a significant threat to human health in the world. In this paper, a novel dengue prediction approach using the novel Light Gradient Boosting Machine (LightGBM), which is a high-performing decision tree-based ensemble learning method, is introduced. Clinical symptoms, lab tests, and demographic information are considered as features to predict whether a patient has been infected with dengue fever. Experimental results prove that proposed LightGBM model yields better accuracy, precision, recall, and F1-score than traditional machine learning algorithms.