Abstract:
Dengue Haemorrhagic Fever is a mosquito-borne disease caused by the arthropod genus mosquito which is found in the tropics and sub-tropics region of the world; transmitting the dengue virus otherwise called serotypes which is a member of the RNA virus group and Flaviviridae virus family from one host to another. Hence, it is categorized as an endemic ailment due to its mode of transmission. Conversely, the symptoms begin to manifest in host after three to fourteen days after infection. Some of its symptoms might include loss of appetite, headache, high fever, metallic taste, vomiting, rash and joint pains just to name a few. This dengue infection has caused millions of death worldwide yearly due to lack of early diagnosis of the ailment. In recent past, several systems have been developed to diagnose this endemic disease, but they generated a lot of false negative during testing and were unable to detect Dengue Haemorrhagic Fever and its overlapping symptoms. Hence, in this paper, we proposed and simulated a model to predict Dengue Haemorrhagic Fever using a machine learning technique called Bayesian Belief Network. The model was designed using Bayes Server and tested with data collected from Dengue Haemorrhagic Fever medical repository. The model had a 99.84% prediction accuracy.
|