Dengue is fast emerging pandemic-prone viral disease in many parts of the world. Dengue flourishes in urban areas, suburbs, and the countryside, but also affects more affluent neighborhoods in tropical and subtropical countries. Dengue is a mosquito-borne viral infection causing a severe flu-like illness and sometimes causing a potentially deadly complication called severe dengue. It is a major public health problem in India. Accurate and timely forecasts of dengue incidence in India are still lacking. In this chapter, the state-of-the-art machine learning algorithms are used to develop an accurate predictive model of dengue. Several machine learning algorithms are used as candidate models to predict dengue incidence. Performance and goodness of fit of the models were assessed, and it is found that the optimized SVR gives minimal RMSE 0.25. The classifiers are applied, and experiment results show that the extreme boost and random forest gives 93.65% accuracy.
TopIntroduction
Dengue fever, also called as break bone fever is a disease rooted from dengue virus which is transmitted by Aedes mosquito. There are four kind of dengue infection such as DHF1, DHF2, DHF3 and DHF4. The symptoms of dengue include low blood pressure, headache, joint pain, rashes, and low levels of blood platelets count which leads to critical dengue hemorrhagic fever. The major issue in dengue fever is that there is no particular antibiotic or medicine exists to care for it. Dengue fever takes place in form of cycles and which is exist inside the body of a patient for one or two weeks. This leads to bleeding, abdominal pain and dengue hemorrhagic fever
Mainly Aedes mosquito brings a virus in its saliva when it gnaws a healthy person. These viruses go into persons’ body and mixed with body fluids of a healthy person. When dengue virus is blended with the white blood vessels, it begins reproducing inside the white blood cells (WBC) and thus starts the dengue virus cycle. If there is severe infection, the length of virus cycle is extended and thus has an effect on bone marrow and liver leading to less blood circulation in blood vessels and blood pressure turn out to be so low that is not able to supply adequate blood to all of the organs in a body. The main task of platelets is blood clotting which is affected because of dengue virus. Virus reduces platelets which causes increased risk of bleeding.
The primary aim of this chapter is dengue disease prediction in administrative region. The predictive analytics covers several statistical methods in data analytics and machine learning. It explores the present and past facts to make predictions about future or unknown events. In this chapter, a number of machine learning algorithms including the Support Vector Regression (SVR) algorithm, Step-down Linear Regression(SLR) model, Gradient Boosted Regression Tree (GBRT) algorithm, Negative Binomial Regression (NBM) model, Least Absolute Shrinkage and Selection Operator (LASSO) linear regression model and Generalized Additive Model (GAM)are utilized as candidate models to predict dengue incidence. Evaluation of performance and goodness of fit of the models were donewith the help of root-mean-square error (RMSE) and R-squared measures
The chief contributions of this chapter paper are:
- 1.
To perform thorough review on data analysis on dengue diseases.
- 2.
Comparative analysis of various machine learning algorithms on dengue dataset in an administrative region.
- 3.
Make out the best performance algorithm for prediction of diseases through methodical investigation.
The remaining section of this chapter is organized as follows. Section 2 discusses about the literature review of dengue disease analysis. Section 3 briefs about methodology of dengue disease prediction. The experiment results are done and analyzed the performance of various predictive analytics approaches are done in section 4. Section 5 concluded the chapter.
TopLiterature Review
In a study conducted by Long et al (2010) for dengue outbreaks, they identified the number of attributes to be used in determining outbreaks rather than using only case counts. They used multiple attribute value based on Apriori concept. The results were encouraging when they identified more than one attributes showing similar graph in vector-borne diseases outbreaks. Their proposed methods also outperform in term of detection rate, false positive rate and overall performance.
The mRNA expression levels of genes involved in dengue virus innate immune responses were measured using quantitative real time PCR (qPCR). A novel application of the support vector machines (SVM) algorithm was used to analyse the expression pattern of 12 genes in peripheral blood mononuclear cells (PBMCs) of 28 dengue patients (13 DHF and 15 DF) during acute viral infection. The SVM model was trained using gene expression data of these genes and achieved the highest accuracy of ∼85% with leave-one-out cross-validation. This work was the first report of application of the SVM method to gene expression data from DF and DHF patients to better understand the role of the genes in DENV infection pathway. The results suggested the important role of seven genes in classifying DF and DHF patients: TLR3, MDA5, IRF3, IFN-α, CLEC5A, and the two most important MYD88 and TLR7 (Gomes et al, 2010).