Search

Background & Aims: There are variables whose influence on the risk of tuberculosis (TB) recurrence change over time. Therefore, this study aimed to assess the time-dependent effects of these variables on the hazard of TB recurrence. Materials & Methods: In this historical cohort study, data were collected from 4,564 TB patients who were referred to the TB research center of Dr. Masih Daneshvari Hospital, Tehran, from 2005 to 2015, in order to evaluate factors affecting the hazard of TB recurrence in terms of time dependency or time constancy. Data were analyzed in STATA 14 software using a statistical test based on Schoenfeld residuals, the time-dependent effects method, and the time-varying effects model (considering time function as f (t) = t). Results: The results showed that only the impact of the variables of drug adverse effects and passive smoker were inconstant over time and had time-dependent effects, and they also influenced the hazard of TB recurrence. Also, the effect of the two mentioned variables on the hazard of TB recurrence displayed a decreasing and increasing trend with time, respectively. Conclusion: Using the time-varying effects model in the study of the hazard of TB recurrence allows evaluating the time-dependent effects of the studied variables and also can differentiate them from the time-independent variables.

Background & Aims: Diagnosis and treatment of patients with multidrug-resistant tuberculosis (MDR-TB) are very important. Hence, it is necessary to predict and diagnose these patients based on individual, demographic and clinical characteristics before starting treatment. This study aimed to predict MDR-TB in TB patients using the perceptron artificial neural networks (ANNs) model. Materials & Methods: This retrospective cohort study was conducted on 1,050 TB patients who have been treated in Masih Daneshvari Hospital, Tehran, Iran from 2005 to 2015. Data on personal and demographic information, as well as medical data such as drug therapy, final outcome of treatment, and the diagnosis of MDR-TB, were collected from the patients' medical records. Results: The results of this study indicated that the predictive power of MDR-TB for both training and testing groups was 85% and 80%, respectively. Also, the variables of marital status, education, drug use, being imprisoned, extrapulmonary TB, history of comorbidities, AIDS, patients' age, and family size were identified as very effective factors. However, variables of residence, smoking history, contact with a TB person, pulmonary TB, drug side effects, nationality, and diabetes were found as effective factors in predicting the development of MDR-TB. Conclusion: Application of the perceptron ANNs model in the study of MDR-TB is able to create new horizons in the diagnosis of these patients due to high predictive accuracy.

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.