A robust and non-parametric model for prediction of dengue incidence

TL;DR

This paper introduces a non-parametric Gaussian Process model for dengue prediction that effectively captures sudden incidence changes, outperforming existing methods in accuracy for disease surveillance.

Contribution

It presents a novel, flexible Gaussian Process regression approach for dengue prediction, improving robustness and accuracy over traditional models.

Findings

GP model outperforms existing methods in accuracy

Captures steep and sudden incidence changes effectively

Provides a robust tool for health authorities' planning

Abstract

Disease surveillance is essential not only for the prior detection of outbreaks but also for monitoring trends of the disease in the long run. In this paper, we aim to build a tactical model for the surveillance of dengue, in particular. Most existing models for dengue prediction exploit its known relationships between climate and socio-demographic factors with the incidence counts, however they are not flexible enough to capture the steep and sudden rise and fall of the incidence counts. This has been the motivation for the methodology used in our paper. We build a non-parametric, flexible, Gaussian Process (GP) regression model that relies on past dengue incidence counts and climate covariates, and show that the GP model performs accurately, in comparison with the other existing methodologies, thus proving to be a good tactical and robust model for health authorities to plan their course of action.