Skip to Main Content
Identification of the influential clinical symptoms and laboratory features that help in the diagnosis of dengue fever (DF) in early phase of the illness would aid in designing effective public health management and virological surveillance strategies. Keeping this as our main objective, we develop in this paper a new computational intelligence-based methodology that predicts the diagnosis in real time, minimizing the number of false positives and false negatives. Our methodology consists of three major components: 1) a novel missing value imputation procedure that can be applied on any dataset consisting of categorical (nominal) and/or numeric (real or integer); 2) a wrapper-based feature selection method with genetic search for extracting a subset of most influential symptoms that can diagnose the illness; and 3) an alternating decision tree method that employs boosting for generating highly accurate decision rules. The predictive models developed using our methodology are found to be more accurate than the state-of-the-art methodologies used in the diagnosis of the DF.