Performance evaluation of the neural network diagnostic system for the re-emerging arboviral infection -dengue
International Journal of Latest Trends in Engineering and Technology · 2017
The prevalence of emerging infectious diseases in humans has increased within the recent past and also threatens to increase in the near future.Dengue, a Flavivirus and Chikungunya, an Alphavirus, transmitted by Aedes mosquitoes, [1] are a cause of great concern to public health in India, especially in delta regions.Because of a number of factors, including urbanization, globalization of travel, and lack of efficient chemical pesticide-based vector control interventions, these infections have re-emerged as a significant international community health problem.Chikungunya fever resembles Dengue fever, and is characterized by severe, sometimes persistent, joint pain (arthritis), as well as fever and rash [2].Diagnosis of Dengue starts with a clinical suspicion, prompted by the recognition of a collection of presenting symptoms and signs.In the early acute febrile phase of illness, Dengue patients often present with a history of sudden onset fever, which is often accompanied by nausea, aches and pains.As, the clinical manifestations of Chikungunya fever resemble those of Dengue fever it has to be distinguished from Dengue fever.[3] Co-occurrence of both fevers has been observed in Tamil Nadu state of India thus highlighting the importance of strong clinical suspicion and efficient laboratory support.It has been postulated that many cases of Dengue virus infection are misdiagnosed and that the incidence of CHIKV infection is much higher than reported [4].Therefore, the present study was undertaken to diagnose Chikungunya infection in clinically suspected Dengue patients and the vice-versa.Most of the research studies done on Dengue, involves weather parameters, considering the significance of weather variables in spreading DF.However, it is difficult to find a research that is using the same Dengue data to do the classification, but there are researches related with this technique that is using different Dengue data to choose the best method for knowledge acquisition for Dengue dataset.In medical decision making, a variety of neural networks are used for decision accuracy.A neural network with enough elements (called neurons) can classify any data with arbitrary accuracy.They are particularly well suited for complex decision boundary problems over many variables.Therefore we choose neural networks as a good candidate for solving the Arboviral disease classification problem which contains the numerical data such as our dataset.Considering all the above research studies, first, we perform a standard presentation of results that promote and facilitate future comparisons to recognize important trends and patterns which, in turn, will inform the development of opinion and medical practice and patients affected by