Predictive dynamics: Modeling for virological surveillance and clinical management of dengue

Abstract

Dengue fever is a flu-like illness spread by the bite of an infected mosquito and is fast emerging as a major public health concern. Timely and cost-effective diagnosis would reduce the mortality rates besides providing better grounds for clinical management and disease surveillance. Identifying the clinical features for early diagnosis of dengue would be useful in reducing the virus transmission in a community. In addition to the clinical features, obtaining the influential laboratory attributes and their range would aid in quick identification of disease severity in the suspected individuals. In this chapter a new alternating decision tree methodology which generates more accurate and simplified decision tree structures with simplified classification rules is discussed. This approach helps one to obtain the influential clinical and laboratory features which would aid in identifying the suspected dengue individuals and assess the severity of infection in them.