Enhancing fine-grained intra-urban dengue forecasting by integrating spatial interactions of human movements between urban regions

Abstract

Background As a mosquito-borne infectious disease, dengue fever (DF) has spread through tropical and subtropical regions worldwide in recent decades. Dengue forecasting is essential for enhancing the effectiveness of preventive measures. Current studies have been primarily conducted at national, sub-national, and city levels, while an intra-urban dengue forecasting at a fine spatial resolution still remains a challenging feat. As viruses spread rapidly because of a highly dynamic population flow, integrating spatial interactions of human movements between regions would be potentially beneficial for intra-urban dengue forecasting. Methodology In this study, a new framework for enhancing intra-urban dengue forecasting was developed by integrating the spatial interactions between urban regions. First, a graph-embedding technique called Node2Vec was employed to learn the embeddings (in the form of an N-dimensional real-valued vector) of the regions from their population flow network. As strongly interacting regions would have more similar embeddings, the embeddings can serve as “interaction features.” Then, the interaction features were combined with those commonly used features (e.g., temperature, rainfall, and population) to enhance the supervised learning–based dengue forecasting models at a fine-grained intra-urban scale. Results The performance of forecasting models (i.e., SVM, LASSO, and ANN) integrated with and without interaction features was tested and compared on township-level dengue forecasting in Guangzhou, the most threatened sub-tropical city in China. Results showed that models using both common and interaction features can achieve better performance than that using common features alone. Conclusions The proposed approach for incorporating spatial interactions of human movements using graph-embedding technique is effective, which can help enhance fine-grained intra-urban dengue forecasting.

Deep learning models for forecasting dengue fever based on climate data in Vietnam

“…These conditions are advantageous to the spread of DF. Hence, including these meteorological factors into prediction models has the potential to improve prediction accuracy as demonstrated in previous works [8,14,23,24].…”

“…A diverse range of forecast techniques has been applied to the prediction of DF from weather data both in Vietnam and internationally, such as those used in Kuala Lumpur, Malaysia [14]; Guangzhou, China [12]; Guadeloupe, France [15]; and Thailand [16]. These techniques include, but are not limited to, Poisson regression models [17,18], hierarchical Bayesian models [19], autoregressive integrated moving average (ARIMA) and seasonal ARIMA models [15,20,21], support vector regression (SVR) [22,23], least absolute shrinkage and selection operator (LASSO) regression [22,24], artificial neural networks (ANNs) [24], back-propagation neural networks (BPNNs), gradient boosting machine (GBM) [23], generalized additive models (GAMs) [16,23], and long short-term memory (LSTM) models [14,23]. The models listed all included temperature and rainfall as variables; other variables included humidity [8,14], air pressure and water pressure [23], wind speed [14], altitude, urban land cover [19], enhanced vegetation index [14], and data from nearby regions in the form of population flow [23] or spatial autoregression of DF risk [19].…”

Predicting infectious disease for biopreparedness and response: A systematic review of machine learning and deep learning approaches

“…The popular ML techniques most widely used in the field of ID prediction include tree-based approaches [ [20] , [21] , [22] ] and Support Vector Machines (SVM) [ [23] , [24] , [25] ] due to their ease of implementation and interpretability. On the other hand, DL techniques, such as feed-forward neural networks (FNN) [ 26 , 27 ] and recurrent neural networks (RNN) [ 28 , 29 ], are popular for their ability to integrate large and complex data into their predictions.…”

Dengue Fever: From Extreme Climates to Outbreak Prediction

“…Based on these factors, a wide range of Machine Learning (ML) models have been employed to predict DF incidence rates/cases or outbreaks for many different areas e.g., Queensland in Australia [11], Guangzhou in China [8], Singapore [6], Honduras [6], Brazil [24], Bangkok in Thailand [18], Selangor in Malaysia [25], and Vietnam [13]. These models range from traditional to recent deep learning methods, e.g., Seasonal Autoregressive Integrated Moving Averaged (SARIMA) [11], Poisson regression [26], Support Vector Regression (SVR) [8], Gradient Boosting Machine (GBM) [7], [8], Generalized Additive Models (GAMs) [8], Generalized Linear Mixed Models (GLMMs) [13], Artificial Neural Networks (ANNs) [9], Back-propagation neural network (BPNNs) [7], Long-short term memory (LSTM) [7], Convolution Neural Networks (CNNs) [10], and Transfomer [10]. Inputs for these models also vary but climate data (e.g., rainfall and temperature) are frequently studied subjects [2].…”