Machine-learning forecasting for Dengue epidemics - Comparing LSTM, Random Forest and Lasso regression
Mussumeci, E.; Coelho, F. C.
Show abstract
Effective management of seasonal diseases such as dengue fever depends on timely deployment of control measures prior to the high transmission season. As the epidemic season fluctuates from year to year, the availability of accurate forecasts of incidence can be decisive in attaining control of such diseases. Obtaining such forecasts from classical time series models has proven a difficult task. Here we propose and compare machine learning models incorporating feature selection,such as LASSO and Random Forest regression with LSTM a deep recurrent neural network, to forecast weekly dengue incidence in 790 cities in Brazil. We use multivariate time-series as predictors and also utilize time series from similar cities to capture the spatial component of disease transmission. Among the compared models, the LSTM recurrent neural network model displayed the smallest predictive errors in predicting incidence of dengue out of sample, in cities of different sizes.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Dengue forecasting and outbreak detection in Brazil using LSTM: integrating human mobility and climate factors 98%
- Integrating Kolmogorov-Arnold Networks with Ordinary Differential Equations for Efficient, Interpretable and Robust Deep Learning: A Case Study in the Epidemiology of Infectious Diseases 93%
- Within-host models unravelling the dynamics of dengue reinfections 92%
Similar papers in this journal
- Interdependence between confirmed and discarded cases of dengue, chikungunya and Zika viruses in Brazil: A multivariate time-series analysis 95%
- Interdependence between confirmed and discarded cases of dengue, chikungunya and Zika viruses in Brazil: A multivariate time-series analysis 95%
- Climate drivers of malaria at its southern fringe in the Americas 93%
Similar papers in this journal
- Predicting dengue importation into Europe, using machine learning and model-agnostic methods. 95%
- A Recursive Bifurcation Model for Predicting the Peak of COVID-19 Virus Spread in United States and Germany 92%
- Forecasting virus outbreaks with social media data via neural ordinary differential equations 92%
Similar papers in this journal
- Predicting Dengue Incidence Leveraging Internet-Based Data Sources. A Case Study in 20 cities in Brazil 96%
- An investigation of spatial-temporal patterns and predictions of the COVID-19 pandemic in Colombia, 2020-2021 93%
- Severity Index for Suspected Arbovirus (SISA): machine learning for accurate prediction of hospitalization in subjects suspected of arboviral infection 93%
Similar papers in this journal
- Measuring the impact of nonpharmaceutical interventions on the SARS-CoV-2 pandemic at a city level: An agent-based computational modeling study of the City of Natal 92%
- Spatio-temporal modelling of COVID-19 infection and associated risk factors in Dakar, Senegal 92%
- Determining the effects of preseasonal climate factors toward dengue early warning system in Bangladesh 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.