Showing 2 results for Bayesian Network
S Heidari, A Kavousi, V Rezaei Tabar,
Volume 14, Issue 2 (9-2018)
Abstract
Background and Objectives: Breast cancer is the most common cancer in Iran. It can be prevented by rapid diagnosis of the disease. Thus, it is necessary to determine the causal relationships between variables related to breast cancer. Bayesian network is a data mining tool that shows the causal relationship between different variables. In this paper, a Bayesian network was applied to find causal relationships between breast cancer variables using a genetic algorithm in a graphical model.
Methods: in this applied study, data were collected from 900 breast cancer patients in Kerman Province from 1999 to 2008. For data analysis, we used a probabilistic graphical model representing the causal relationship between variables.
Results: The results showed that surgery was the most important treatment for breast cancer. Based on the conditional and marginal probabilities, the women who underwent surgery had higher hopes of living longer. Moreover, 81% of the patients who did not undergo surgery only received chemotherapy or radiotherapy were less likely to have long lives.
Conclusion: People aged 40-65 years are more likely to have breast cancer. Moreover, the variables of age, surgery, chemotherapy, and radiotherapy had a direct effect on the status of the patients and there were direct edges from these variables to the status of the patients.
F Feizmanesh, Aa Safaei,
Volume 14, Issue 3 (12-2018)
Abstract
Background and Objectives: Pulmonary embolism is a potentially fatal and prevalent event that has led to a gradual increase in the number of hospitalizations in recent years. For this reason, it is one of the most challenging diseases for physicians. The main purpose of this paper was to report a research project to compare different data mining algorithms to select the most accurate model for predicting pulmonary embolism in hospitalized patients. This model would provide the knowledge needed by the medical staff fir better decision making.
Methods: In this research, we designed a prediction model using different methods of machine learning that would best predict the probability of pulmonary embolism in patients at risk. Among data mining algorithms, Bayesian network, decisions tree (J48), logistic regression (LR), and sequential minimal optimization (SMO) were used. The data used in the study included risk factors and past history of patients admitted to the Lung Department of Shariati Hospital, Tehran, Iran.
Results: The results showed that the accuracy and specificity of all prediction models were satisfactory. The Bayesian model had the highest sensitivity in predicting pulmonary embolism.
Conclusion: Although the results showed a little difference in the performance of prediction models, the Bayesian model is a more appropriate tool to predict the occurrence of pulmonary embolism in hospitalized patients in this type of data. It can be considered a supportive approach along medical decisions to improve disease prediction.
