An integrated recurrent neural network and regression model with spatial and climatic couplings for vector-borne disease dynamics
This work addresses disease prediction for public health applications, but appears incremental as it combines existing techniques (RNNs, regression, embeddings) in a domain-specific way.
The researchers tackled the problem of predicting vector-borne disease outbreaks by developing an integrated model combining recurrent neural networks and nonlinear regression with spatial and climatic couplings. Their model outperformed ARIMA models on leishmaniasis data from Sri Lanka (2013-2018), particularly in high-infection regions.
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.