TY - JOUR
T1 - Machine learning approaches for dengue prediction : a review of algorithms and applications
AU - Hussain, Zafer
AU - Khan, Imran Ahmed
AU - Arsalan, Mudassar Hassan
PY - 2023
Y1 - 2023
N2 - Dengue disease positions a significant global public health challenge, warranting attention from local health authorities and the international community. The escalating number of reported cases necessitates early detection to mitigate the risk of disease transmission. This review paper examines the application of various machine learning (ML) algorithms in predicting the spread of Dengue within communities. Our investigation encompasses a range of ML techniques, including Self-Organizing Maps, Decision Trees, Support Vector Machines, neural networks, fuzzy systems, and evolutionary algorithms and classifiers. Leveraging ML computation, these techniques demonstrate high levels of predictive accuracy, offering valuable insights for dengue prediction. Effective control measures and timely assessment of cases using ML can significantly reduce dengue risk. To implement the proposed policy, geographic variables and local statistical data should be incorporated within the ML framework. Collaboration between health scientists and data scientists in employing ML approaches can lead to the development of innovative methods for diagnosis, treatment, emergency management, and prediction of Dengue. Ultimately, these techniques may inform policy development and contribute to disease eradication efforts.
AB - Dengue disease positions a significant global public health challenge, warranting attention from local health authorities and the international community. The escalating number of reported cases necessitates early detection to mitigate the risk of disease transmission. This review paper examines the application of various machine learning (ML) algorithms in predicting the spread of Dengue within communities. Our investigation encompasses a range of ML techniques, including Self-Organizing Maps, Decision Trees, Support Vector Machines, neural networks, fuzzy systems, and evolutionary algorithms and classifiers. Leveraging ML computation, these techniques demonstrate high levels of predictive accuracy, offering valuable insights for dengue prediction. Effective control measures and timely assessment of cases using ML can significantly reduce dengue risk. To implement the proposed policy, geographic variables and local statistical data should be incorporated within the ML framework. Collaboration between health scientists and data scientists in employing ML approaches can lead to the development of innovative methods for diagnosis, treatment, emergency management, and prediction of Dengue. Ultimately, these techniques may inform policy development and contribute to disease eradication efforts.
UR - https://hdl.handle.net/1959.7/uws:72243
UR - http://pu.edu.pk/images/journal/geography/pdf/2_V78_No1_2023.pdf
M3 - Article
SN - 0369-9331
VL - 78
SP - 15
EP - 36
JO - Pakistan Geographical Review
JF - Pakistan Geographical Review
IS - 1
ER -