Autor(es):
Ceia-Hasse, Ana ; Sousa, Carla A. ; Gouveia, Bruna R. ; Capinha, César
Data: 2023
Identificador Persistente: http://hdl.handle.net/10362/164974
Origem: Repositório Institucional da UNL
Assunto(s): Dengue; Forecast; Machine learning; Mosquito; Time series classification; RA0421 Public health. Hygiene. Preventive Medicine; QA75 Electronic computers. Computer science; Ecology, Evolution, Behavior and Systematics; Ecology; Modelling and Simulation; Ecological Modelling; Computer Science Applications; Computational Theory and Mathematics; Applied Mathematics; Infectious Diseases; SDG 3 - Good Health and Well-being; SDG 9 - Industry, Innovation, and Infrastructure
Descrição
Funding Information: We thank the personnel of the Regional Health Direction of the Autonomous Region of Madeira (Direção Regional da Saúde) involved in egg collection and analysis and the Portuguese Institute for Sea and Atmosphere (Instituto Português do Mar e da Atmosfera), namely Dr. Victor Prior, for providing the weather data. ACH, CAS and CC were supported by Portuguese National Funds through Fundação para a Ciência e a Tecnologia (ACH and CAS: PTDC/SAU-PUB/30089/2017 and GHTM-UID/Multi/04413/2013; CC: CEECIND/02037/2017, UIDB/00295/2020 and UIDP/00295/2020). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Funding Information: We thank the personnel of the Regional Health Direction of the Autonomous Region of Madeira (Direção Regional da Saúde) involved in egg collection and analysis and the Portuguese Institute for Sea and Atmosphere (Instituto Português do Mar e da Atmosfera), namely Dr. Victor Prior, for providing the weather data. ACH, CAS and CC were supported by Portuguese National Funds through Fundação para a Ciência e a Tecnologia (ACH and CAS: PTDC/SAU-PUB/30089/2017 and GHTM-UID/Multi/04413/2013; CC: CEECIND/02037/2017, UIDB/00295/2020 and UIDP/00295/2020). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Publisher Copyright: © 2023 The Authors
Arboviral diseases such as dengue, Zika, chikungunya or yellow fever are a worldwide concern. The abundance of vector species plays a key role in the emergence of outbreaks of these diseases, so forecasting these numbers is fundamental in preventive risk assessment. Here we describe and demonstrate a novel approach that uses state-of-the-art deep learning algorithms to forecast disease vector abundances. Unlike classical statistical and machine learning methods, deep learning models use time series data directly as predictors and identify the features that are most relevant from a predictive perspective. We demonstrate for the first time the application of this approach to predict short-term temporal trends in the number of Aedes aegypti mosquito eggs across Madeira Island for the period 2013 to 2019. Specifically, we apply the deep learning models to predict whether, in the following week, the number of Ae. aegypti eggs will remain unchanged, or whether it will increase or decrease, considering different percentages of change. We obtained high predictive performance for all years considered (mean AUC = 0.92 ± 0.05 SD). Our approach performed better than classical machine learning methods. We also found that the preceding numbers of eggs is a highly informative predictor of future trends. Linking our approach to disease transmission or importation models will contribute to operational, early warning systems of arboviral disease risk.
