Data-driven methods for dengue prediction and surveillance using real-world and Big Data: A systematic review

Background Traditionally, dengue surveillance is based on case reporting to a central health agency. However, the delay between a case and its notification can limit the system responsiveness. Machine learning methods have been developed to reduce the reporting delays and to predict outbreaks, based on non-traditional and non-clinical data sources. The aim of this systematic review was to identify studies that used real-world data, Big Data and/or machine learning methods to monitor and predict dengue-related outcomes. Methodology/Principal findings We performed a search in PubMed, Scopus, Web of Science and grey literature between January 1, 2000 and August 31, 2020. The review (ID: CRD42020172472) focused on data-driven studies. Reviews, randomized control trials and descriptive studies were not included. Among the 119 studies included, 67% were published between 2016 and 2020, and 39% used at least one novel data stream. The aim of the included studies was to predict a dengue-related outcome (55%), assess the validity of data sources for dengue surveillance (23%), or both (22%). Most studies (60%) used a machine learning approach. Studies on dengue prediction compared different prediction models, or identified significant predictors among several covariates in a model. The most significant predictors were rainfall (43%), temperature (41%), and humidity (25%). The two models with the highest performances were Neural Networks and Decision Trees (52%), followed by Support Vector Machine (17%). We cannot rule out a selection bias in our study because of our two main limitations: we did not include preprints and could not obtain the opinion of other international experts. Conclusions/Significance Combining real-world data and Big Data with machine learning methods is a promising approach to improve dengue prediction and monitoring. Future studies should focus on how to better integrate all available data sources and methods to improve the response and dengue management by stakeholders.

Advanced Early Dengue Prediction and Exploration Service (AEDES)

This paper presents Project AEDES, a big data early warning, and surveillance system for dengue. The project utilizes Google Search Trends to detect public interest and panics related to dengue. Using Google Search Trends, precipitation, and temperature readings from climate data, the system nowcasts probable dengue cases and dengue-related deaths. The system utilizes FAPAR, NDVI, and NDWI readings from remote sensing to detect likely mosquito hotspots to prioritize interventions. We discuss the origin and development of the project and recent developments. We also discuss the current state of development and directions for further work.

Predicting the Dengue Epidemic in Guangzhou, China by Meteorological Parameter Methods

This study was aimed to determine dengue season, and further establish a prediction model by meteorological methods. The dengue and meteorological data were collected from Guangdong Meteorological Bureau and Guangdong Provincial Center for Disease Prevention and Control, respectively. We created a sliding accumulated temperature method to accurately calculate the beginning and ending day of dengue season. Probabilistic Forecast model was derived under comprehensive consideration of various weather processes including typhoon, rainstorm, and so on. We found: 1) The dengue fever season enters when effective accumulated temperature of a continuing 45 days (T45) ≥0 °C, and it finishes when effective accumulated temperature of a continuing 6 days (T6) <0 °C. 2) A Probabilistic Forecast Model for dengue epidemic was established with good forecast effects, which were verified by the actual incidence of dengue in Guangzhou. The Probabilistic Forecast Model provides markedly improved forecasting techniques for dengue prediction.