The modeling of body's immune system using Bayesian Networks

In this paper, the urinary infection, that is a common symptom of the decline of the immune system, is discussed based on the well-known algorithms in machine learning, such as Bayesian networks in both Markov and tree structures. A large scale sampling has been executed to evaluate the performance of Bayesian network algorithm. A number of 4052 samples wereobtained from the database of the Takestan Department of Health, a center affiliated to Qazvin University of Medical Sciences. According to the goals of the study and using the expert opinion of the laboratory and urologist, 15 variables were selected. The database included both urine analysis and culture tests. The results indicated 99.7% accuracy of the diagnosis for the training data, (75% of total data), and 99.8% accuracy of the diagnosis for testing data (25% of total data). Based on the Bayesian network model, the important covariates influencing the Urinary infection have been proved to be the increase of bacteria and the decrease of white blood cells in different age groups. The results of this study can be used in the context of machine learning and intelligent systems for rapid diagnosis of the disease and the treatment of people suspected of suffering from it.