Mathematical modelling and a systems science approach to describe the role of cytokines in the evolution of severe dengue

Jayasundara, Pavithra; Perera, S. S. N.; Malavige, Gathsaurie Neelika; Jayasinghe, Saroj

doi:10.1186/s12918-017-0415-3

Cited by 6 publications

(5 citation statements)

References 43 publications

(79 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study is an attempt to develop a decision model to predict the severity level of dengue patients and is an improved extension of the models in (Jayasundara, et al, 2017) and (Premaratne, et al, 2017). Three variations are carried out.…”

Section: Resultsmentioning

confidence: 99%

“…The fuzzy membership functions are developed according to the previous studies (Jayasundara, et al, 2017) and (Premaratne, et al, 2017). The membership functions for platelet, dengue NS1 antigen, lymphocyte and dengue IgG antibody levels are given in equations (7), (8), (9) and (10) Decision Tree Output IID3 algorithm based decision trees are implemented for 96 and 108 hours from onset of illness for the parameters in Model A and Model B.…”

Section: Model Developmentmentioning

confidence: 99%

“…where ( ), 10 ( ) are the membership values of TNF-α and IL-10 respectively and both are concentrated by 1.1 as in (Jayasundara, et al, 2017). H1 produces the Hamacher product between TNF-α and IL-10.…”

Section: Hours From Onset Of Illnessmentioning

confidence: 99%

See 2 more Smart Citations

Developing a Decision Support Testing Algorithm to Detect Severity Level of Dengue

Jayasundara

Perera

Rathnayaka

2017

ESJ

View full text Add to dashboard Cite

Dengue is a vector borne disease that has become a global threat. In order to reduce the mortality rate early detection of dengue severity level is crucial. This study is an extension of the decision models developed individually for inflammatory mediators and immune parameters. The objective of this study is to improve the individual models by considering their combined effect and to improve the decision making at 96 hours from onset of illness. In order to combine these, three approaches are attempted including, combining together the individual full models on inflammatory mediators and immune parameters, combining the immune parameters based model with decision tree informed cytokines and implementing a decision tree informed model with immune parameters and inflammatory mediators. The decision tree algorithm that is used in model development is Improved ID3 algorithm. The decision tree based model is a two-step decision system with the initial decision being made using the parameters TNF-α, IL-10, dengue NS1 antigen and dengue IgG antibody and, the operator values above 0.4413, are then subjected to the second test including platelet and Platelet Activating Factor. The decision tree based model performed well with an accuracy of 76.19% and 82.3% of DHF patients were correctly classified. Sensitivity analysis indicated the model to be robust.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Model Developmentmentioning

confidence: 99%

See 1 more Smart Citation

Developing a Decision Support Testing Algorithm to Detect Severity Level of Dengue

Jayasundara

Perera

Rathnayaka

2017

ESJ

View full text Add to dashboard Cite

show abstract

“…To forecast dengue outbreak in southern China, researchers apply GAM [32], SVR as well as variations of regression modeling [33], and the factor-detector modeling module of the ArgGIS software [34]. Researchers in Sri Lanka adopt fuzzy system with trapezoidal membership function to predict the developing from classic dengue fever to the severe level using clinical evidences as input data [35].…”

Section: Related Workmentioning

confidence: 99%

Computational Intelligence and Statistical Learning Performances on Predicting Dengue Incidence using Remote Sensing Data

Kerdprasop¹,

Kerdprasop²

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Dengue is a viral infection disease transmitted to people through the bite of specific mosquito species living in a tropical zone. According to the World Health Organization, dengue has been listed among the top-ten diseases for 2019 as it makes 3.9 billion people in 128 countries be at risk of infection. One major cause of substantial dengue widespread is the globally warm climate that accelerates rapid growth of mosquito vectors. In this research, we aim to build data-driven models to predict dengue cases using satellite index data to represent temperature, humidity, and greenness over the surface area of Bangkok, which is our target area of dengue prediction because of its high infection cases. Oceanic Niño Index is also used as a predictor variable to represent climate variability. The modeling methods employ seven algorithms from two broad schemes of the machine learning field. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are algorithms from the subfield of computational intelligence, whereas multiple linear regression (MLR), generalized linear model (GLM), support vector regression (SVR), classification and regression tree (CART), and chi-squared automatic interaction detection (CHAID) are from the statistical learning subfield. Performances of these algorithms are evaluated on the same set of out-of-sample data. The results are that ANFIS is the best model for predicting dengue outbreak in the capital city of Thailand.

show abstract

“…This leads to development of pleural effusion, ascites and shock [13]. A mathematical model had been developed to predict development of DHF looking at a combination of cytokines [14].…”

Section: Pathogenesismentioning

confidence: 99%

Management of dengue infection: improving morbidity

Wickramasinghe

2020

Cey. J. Med. Sci.

View full text Add to dashboard Cite

Article informationTotal number of Words 4100Author has no conflicts of interest to declare AbstractDengue is a vector borne disease, prevalent in the tropics in epidemic proportions. In recent years it has become one of the highest mortality causing communicable diseases in the tropics. Its pathophysiology is not completely understood. In the absence of a definitive treatment modality, supportive care is the most important tool. Having a better understanding of the haematological and biochemical changes is of paramount importance in order to provide effective supportive care to achieve speedy recovery with minimum morbidity and mortality. Although several candidate vaccines have been produced most are still undergoing phase III clinical trials.This article intends to discuss identified and postulated pathophysiological modalities in dengue infection and possible therapeutic/management options that could be adopted to reduce dengue morbidity and mortality.

show abstract

Mathematical modelling and a systems science approach to describe the role of cytokines in the evolution of severe dengue

Cited by 6 publications

References 43 publications

Developing a Decision Support Testing Algorithm to Detect Severity Level of Dengue

Developing a Decision Support Testing Algorithm to Detect Severity Level of Dengue

Computational Intelligence and Statistical Learning Performances on Predicting Dengue Incidence using Remote Sensing Data

Management of dengue infection: improving morbidity

Contact Info

Product

Resources

About