An Approach to Develop Expert Systems in Medical Diagnosis Using Machine Learning Algorithms (Asthma) and a Performance Study

Abstract

Machine Intelligence plays a crucial role in the design of expert systems in medical diagnosis. In India, most people suffer from some sort of disease like asthma, diabetics, cancer, and many more. We consider the disease asthma for diagnosis. The diagnosis of asthma can be done in two ways 1) through questionnaire and 2) through clinical data. We considered both approaches to design the expert system for the diagnosis of asthma. We have chosen some machine learning algorithms such as the Context-sensitive auto-associative memory neural network model[1] (CSAMM), Backpropagation model, C4.5 algorithm, Bayesian Network, Particle Swarm Optimization [7]. We present a performance study on these algorithms in terms of accuracy and some outstanding characteristics