Application of artificial neural network model in studying the mechanism of disease relapse event in patients with tuberculosis

Background & Aims: Today, due to progressing technology and improving the standard of living of humans, the study of diseases has become more complex. This complexity has led to using new methods, such as the model of artificial neural networks (ANNs), to study many chronic diseases, especially tuberculosis (TB). The present study aimed to investigate the mechanism of disease relapse events by applying a multilayer perceptron artificial neural network (MLP-ANN) model among TB patients. Materials & Methods: This retrospective cohort study examined information of 4,564 TB patients treated in Masih Daneshvari Hospital, Tehran, Iran, from 2005 to 2015. TB disease relapse was considered as a study event, and the relapse mechanism was investigated using an MLP-ANN model consisting of three layers. Results: Based on an MLP-ANN model comprising three layers, the power to accurately predict disease relapse in TB patients was 96%. Also, variables of family size, adverse effects of exposure to cigarette smoke, patient age, and education as very effective factors, and marital status, history of drug use, imprisonment, pulmonary TB, diabetes, and AIDS as effective factors were identified in predicting the mechanism of TB disease relapse. Conclusion: Using an ANN model in the study of TB relapse due to its flexibility and high predictive accuracy can clarify any ambiguous aspects of this disease.