An integrated recurrent neural network and regression model with spatial and climatic couplings for vector-borne disease dynamics

TL;DR

This paper presents an integrated neural network and regression model that incorporates climate and spatial data to improve the prediction of vector-borne disease outbreaks, demonstrated on leishmaniasis data from Sri Lanka.

Contribution

The study introduces a novel combined neural network and regression approach that accounts for climate, seasonality, and neighboring regions in disease modeling.

Findings

Outperformed ARIMA models in predicting disease outbreaks.

Model effectively incorporated climate and spatial influences.

Ablation study supported the model's design choices.

Abstract

We developed an integrated recurrent neural network and nonlinear regression spatio-temporal model for vector-borne disease evolution. We take into account climate data and seasonality as external factors that correlate with disease transmitting insects (e.g. flies), also spill-over infections from neighboring regions surrounding a region of interest. The climate data is encoded to the model through a quadratic embedding scheme motivated by recommendation systems. The neighboring regions' influence is modeled by a long short-term memory neural network. The integrated model is trained by stochastic gradient descent and tested on leish-maniasis data in Sri Lanka from 2013-2018 where infection outbreaks occurred. Our model outperformed ARIMA models across a number of regions with high infections, and an associated ablation study renders support to our modeling hypothesis and ideas.