Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia.
The robust estimate and forecast capability of random forests (RF) has been widely recognized, however this ensemble machine learning method has not been widely used in mosquito-borne disease forecasting. In this study, two sets of RF models were developed at the national (pooled department-level da...
Published in: | PLOS Neglected Tropical Diseases |
---|---|
Main Authors: | , , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Public Library of Science (PLoS)
2020
|
Subjects: | |
Online Access: | https://doi.org/10.1371/journal.pntd.0008056 https://doaj.org/article/412874192dff4fc89038d07e0a621075 |
id |
ftdoajarticles:oai:doaj.org/article:412874192dff4fc89038d07e0a621075 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:412874192dff4fc89038d07e0a621075 2023-05-15T15:12:49+02:00 Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. Naizhuo Zhao Katia Charland Mabel Carabali Elaine O Nsoesie Mathieu Maheu-Giroux Erin Rees Mengru Yuan Cesar Garcia Balaguera Gloria Jaramillo Ramirez Kate Zinszer 2020-09-01T00:00:00Z https://doi.org/10.1371/journal.pntd.0008056 https://doaj.org/article/412874192dff4fc89038d07e0a621075 EN eng Public Library of Science (PLoS) https://doi.org/10.1371/journal.pntd.0008056 https://doaj.org/toc/1935-2727 https://doaj.org/toc/1935-2735 1935-2727 1935-2735 doi:10.1371/journal.pntd.0008056 https://doaj.org/article/412874192dff4fc89038d07e0a621075 PLoS Neglected Tropical Diseases, Vol 14, Iss 9, p e0008056 (2020) Arctic medicine. Tropical medicine RC955-962 Public aspects of medicine RA1-1270 article 2020 ftdoajarticles https://doi.org/10.1371/journal.pntd.0008056 2022-12-31T07:51:21Z The robust estimate and forecast capability of random forests (RF) has been widely recognized, however this ensemble machine learning method has not been widely used in mosquito-borne disease forecasting. In this study, two sets of RF models were developed at the national (pooled department-level data) and department level in Colombia to predict weekly dengue cases for 12-weeks ahead. A pooled national model based on artificial neural networks (ANN) was also developed and used as a comparator to the RF models. The various predictors included historic dengue cases, satellite-derived estimates for vegetation, precipitation, and air temperature, as well as population counts, income inequality, and education. Our RF model trained on the pooled national data was more accurate for department-specific weekly dengue cases estimation compared to a local model trained only on the department's data. Additionally, the forecast errors of the national RF model were smaller to those of the national pooled ANN model and were increased with the forecast horizon increasing from one-week-ahead (mean absolute error, MAE: 9.32) to 12-weeks ahead (MAE: 24.56). There was considerable variation in the relative importance of predictors dependent on forecast horizon. The environmental and meteorological predictors were relatively important for short-term dengue forecast horizons while socio-demographic predictors were relevant for longer-term forecast horizons. This study demonstrates the potential of RF in dengue forecasting with a feasible approach of using a national pooled model to forecast at finer spatial scales. Furthermore, including sociodemographic predictors is likely to be helpful in capturing longer-term dengue trends. Article in Journal/Newspaper Arctic Directory of Open Access Journals: DOAJ Articles Arctic PLOS Neglected Tropical Diseases 14 9 e0008056 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Arctic medicine. Tropical medicine RC955-962 Public aspects of medicine RA1-1270 |
spellingShingle |
Arctic medicine. Tropical medicine RC955-962 Public aspects of medicine RA1-1270 Naizhuo Zhao Katia Charland Mabel Carabali Elaine O Nsoesie Mathieu Maheu-Giroux Erin Rees Mengru Yuan Cesar Garcia Balaguera Gloria Jaramillo Ramirez Kate Zinszer Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. |
topic_facet |
Arctic medicine. Tropical medicine RC955-962 Public aspects of medicine RA1-1270 |
description |
The robust estimate and forecast capability of random forests (RF) has been widely recognized, however this ensemble machine learning method has not been widely used in mosquito-borne disease forecasting. In this study, two sets of RF models were developed at the national (pooled department-level data) and department level in Colombia to predict weekly dengue cases for 12-weeks ahead. A pooled national model based on artificial neural networks (ANN) was also developed and used as a comparator to the RF models. The various predictors included historic dengue cases, satellite-derived estimates for vegetation, precipitation, and air temperature, as well as population counts, income inequality, and education. Our RF model trained on the pooled national data was more accurate for department-specific weekly dengue cases estimation compared to a local model trained only on the department's data. Additionally, the forecast errors of the national RF model were smaller to those of the national pooled ANN model and were increased with the forecast horizon increasing from one-week-ahead (mean absolute error, MAE: 9.32) to 12-weeks ahead (MAE: 24.56). There was considerable variation in the relative importance of predictors dependent on forecast horizon. The environmental and meteorological predictors were relatively important for short-term dengue forecast horizons while socio-demographic predictors were relevant for longer-term forecast horizons. This study demonstrates the potential of RF in dengue forecasting with a feasible approach of using a national pooled model to forecast at finer spatial scales. Furthermore, including sociodemographic predictors is likely to be helpful in capturing longer-term dengue trends. |
format |
Article in Journal/Newspaper |
author |
Naizhuo Zhao Katia Charland Mabel Carabali Elaine O Nsoesie Mathieu Maheu-Giroux Erin Rees Mengru Yuan Cesar Garcia Balaguera Gloria Jaramillo Ramirez Kate Zinszer |
author_facet |
Naizhuo Zhao Katia Charland Mabel Carabali Elaine O Nsoesie Mathieu Maheu-Giroux Erin Rees Mengru Yuan Cesar Garcia Balaguera Gloria Jaramillo Ramirez Kate Zinszer |
author_sort |
Naizhuo Zhao |
title |
Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. |
title_short |
Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. |
title_full |
Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. |
title_fullStr |
Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. |
title_full_unstemmed |
Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. |
title_sort |
machine learning and dengue forecasting: comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in colombia. |
publisher |
Public Library of Science (PLoS) |
publishDate |
2020 |
url |
https://doi.org/10.1371/journal.pntd.0008056 https://doaj.org/article/412874192dff4fc89038d07e0a621075 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
PLoS Neglected Tropical Diseases, Vol 14, Iss 9, p e0008056 (2020) |
op_relation |
https://doi.org/10.1371/journal.pntd.0008056 https://doaj.org/toc/1935-2727 https://doaj.org/toc/1935-2735 1935-2727 1935-2735 doi:10.1371/journal.pntd.0008056 https://doaj.org/article/412874192dff4fc89038d07e0a621075 |
op_doi |
https://doi.org/10.1371/journal.pntd.0008056 |
container_title |
PLOS Neglected Tropical Diseases |
container_volume |
14 |
container_issue |
9 |
container_start_page |
e0008056 |
_version_ |
1766343458044248064 |