The Diagnosis of Brucellosis in Rafsanjan City Using Deep Auto-Encoder Neural Networks

Introduction: Brucellosis is considered as one of the most important common infectious diseases between humans and animals. Considering the endemic nature of brucellosis and the existence of numerous reports of human and animal cases of brucellosis in Iran, the incidence of human brucellosis in Rafsanjan city was determined in the last 3 years (2016–2018). The main objective of this study was to find an automated consistent and intelligent method with low sensitivity based on a neural network which is capable of accurate detection of brucellosis disease. Methods: In this descriptive analytic study, cases of human brucellosis in Rafsanjan, south of Iran, were analyzed based on sex, age, pregnancy, history of contact with livestock and the use of non-pasteurized dairy products, Right Laboratory parameters and 2ME during 3 years (2016–2018). Data were split into two subsets of train (80%) and test (20%). The artificial neural network approach of the deep auto-encoder was used to train each subset. Results: The deep auto-encoder method achieves 94.61% sensitivity, 90.84% accuracy and 50% specificity in the diagnosis of brucellosis over the experimental data sets. The experimental results also showed the excellent performance of the proposed artificial neural network. Conclusion: The deep artificial neural network model can be used as an efficient and intelligent method to detect the human cases of brucellosis. However, further studies are required to design other models of artificial neural networks based on deep learning to detect other infectious diseases.