Diagnosis of brucellosis disease using data mining: A case study on patients of a hospital in Tehran

Brucellosis is a common zoonotic infection of humans from livestock. This bacterial infection is acquired from infected animals and their products. The pathogen of this disease is a genus of bacilli called Brucella, and no effective vaccine has been discovered yet for the prevention of human brucellosis.

The present study is mainly conducted to diagnose brucellosis accurately and timely, using Data Mining techniques. Based on the knowledge discovered with Data Mining and opinions of specialist physicians, this study aims to propose instructions for diagnosing brucellosis.

The dataset used in this study contains 340 samples and is extracted from the files of patients at Tehran Imam Khomeini Hospital from the years 2010-2020. Attributes of this dataset have been determined based on domain expert opinions, namely specialist physicians. After initial analysis and data pre-processing, various Data Mining techniques have been employed to diagnose brucellosis, including neural networks, Bayesian networks, and decision trees.

According to the recorded data, 270 people (approximately 79% of samples) had brucellosis. Some clinical symptoms were more prominent among infected patients, including fever, arthritis, tremor, decreased appetite, and nightly perspiration. Among all employed Data Mining techniques in this study, the decision tree with C5.0 pruning algorithm possessed the highest accuracy in diagnosing patients with brucellosis (approximately 99% accuracy). Based on the obtained final model, the most important factors for diagnosing brucellosis are the Wright test, Coombs Wright test, blood culture test, and living place.

According to the results of this study, brucellosis can be diagnosed with a high accuracy using Data Mining techniques. Furthermore, the most significant factors for diagnosing brucellosis disease can be identified by Data Mining. Among all investigated techniques in this study, the decision tree with C5.0 pruning algorithm has the most accuracy in diagnosing brucellosis. Given the decision tree created by the C5.0 algorithm and the opinions of specialist physicians, some instructions are proposed based on a decision-making framework to classify referents into patient and non-patient groups. These instructions can accelerate the diagnosis, reduce therapeutic costs, and decrease treatment period.