TY - JOUR
T1 - Prediction of dengue outbreak in Selangor Malaysia using machine learning techniques
AU - Salim, Nurul Azam Mohd
AU - Wah, Yap Bee
AU - Reeves, Caitlynn
AU - Smith, Madison
AU - Yaacob, Wan Fairos Wan
AU - Mudin, Rose Nani
AU - Dapari, Rahmat
AU - Sapri, Nik Nur Fatin Fatihah
AU - Haque, Ubydul
N1 - Funding Information:
The authors would like to thank Universiti Teknologi MARA (UiTM) and Ministry of Higher Education Malaysia for the funding of this research under the FRGS Grant (FRGS/1/2016/STG06/UITM02/2). UH was supported by the Research Council of Norway (Grant # 281077).
Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12
Y1 - 2021/12
N2 - Dengue fever is a mosquito-borne disease that affects nearly 3.9 billion people globally. Dengue remains endemic in Malaysia since its outbreak in the 1980’s, with its highest concentration of cases in the state of Selangor. Predictors of dengue fever outbreaks could provide timely information for health officials to implement preventative actions. In this study, five districts in Selangor, Malaysia, that demonstrated the highest incidence of dengue fever from 2013 to 2017 were evaluated for the best machine learning model to predict Dengue outbreaks. Climate variables such as temperature, wind speed, humidity and rainfall were used in each model. Based on results, the SVM (linear kernel) exhibited the best prediction performance (Accuracy = 70%, Sensitivity = 14%, Specificity = 95%, Precision = 56%). However, the sensitivity for SVM (linear) for the testing sample increased up to 63.54% compared to 14.4% for imbalanced data (original data). The week-of-the-year was the most important predictor in the SVM model. This study exemplifies that machine learning has respectable potential for the prediction of dengue outbreaks. Future research should consider boosting, or using, nature inspired algorithms to develop a dengue prediction model.
AB - Dengue fever is a mosquito-borne disease that affects nearly 3.9 billion people globally. Dengue remains endemic in Malaysia since its outbreak in the 1980’s, with its highest concentration of cases in the state of Selangor. Predictors of dengue fever outbreaks could provide timely information for health officials to implement preventative actions. In this study, five districts in Selangor, Malaysia, that demonstrated the highest incidence of dengue fever from 2013 to 2017 were evaluated for the best machine learning model to predict Dengue outbreaks. Climate variables such as temperature, wind speed, humidity and rainfall were used in each model. Based on results, the SVM (linear kernel) exhibited the best prediction performance (Accuracy = 70%, Sensitivity = 14%, Specificity = 95%, Precision = 56%). However, the sensitivity for SVM (linear) for the testing sample increased up to 63.54% compared to 14.4% for imbalanced data (original data). The week-of-the-year was the most important predictor in the SVM model. This study exemplifies that machine learning has respectable potential for the prediction of dengue outbreaks. Future research should consider boosting, or using, nature inspired algorithms to develop a dengue prediction model.
UR - http://www.scopus.com/inward/record.url?scp=85099412834&partnerID=8YFLogxK
U2 - 10.1038/s41598-020-79193-2
DO - 10.1038/s41598-020-79193-2
M3 - Article
C2 - 33441678
AN - SCOPUS:85099412834
SN - 2045-2322
VL - 11
JO - Scientific Reports
JF - Scientific Reports
IS - 1
M1 - 939
ER -