A Survey on Using Immunopathogenesis to Predict Nipah Virus using Machine Learning Techniques

Viral disease can occur through direct contact with immunopathogenesis. The consecutive reappearance of the Nipah virus is one of the human-zoonotic viruses relevant to the Hendra virus (HeV) which spreads due to the impact of pteropus bats/flying foxes or unprotected pets and causes a serious attack and encephalitis. First, the NiV was reported in Malaysia in 1998. Subsequently, lung disease was recently discovered in the Kerala district. According to WHO statistics, the identification of zoonotic disease, one of the main challenges and cause of numerous outbreaks, coincide with the season of the sap harvest, that is, from winter to spring. The huge family of Henipavirus extends new species of deadly disease called Nipah by the novel Paramyxovirus pathogen. The goal of this work is to predict and diagnose virus by knowing the effectiveness of machine learning as soon as possible due to lethality. In current medical care, PCR or serology works effectively to diagnose the virulent, in which the body is rapidly transformed through the blood immunity cells, which it infects with asymptomatic symptoms. This document aims to summarize the machine learning technique, which is one of the main areas in the field of data analysis, although it plays a more important role in many real-time applications; the healthcare sector analyses the multiple machine learning algorithms for disease prediction and/or solution analysis. The minor inconvenience of the healthcare sector may take some time to clarify the test result. From a medical point of view, there are no syringes and there are no validated drugs available against the Nipah virus. So far, the result reaches a high mortality. Here, the summary of Nipah reports to stimulate researchers to observe the disease in the first phase with high precision and also tracks the drugs associated with Nipah. Machine learning algorithms are very essential in the medical society to isolate the virus of suspicious and emergency cases using ML predictor.