Background: Breast cancer is one of the most common cancers with a high mortality rate among women. Prognosis and early diagnosis of breast cancer among women society reduce considerable rate of their mortality. Nowadays, due to this illness, try to be setting up intelligent systems, which can predict and early diagnose this cancer, and reduce mortality of women society.
Methods: Overall, 208 samples were collected from 2014 to 2015 from two oncologist offices and Javadalaemeh Clinic in Kerman, southeastern Iran. Data source was medical records of patients, then 64 data mining models in MATLAB and WEKA software were used, eventually these measured precision and accuracy of data mining models.
Results: Among 64 data mining models, Bayes-Net model had 95.67% of accuracy and 95.70% of precision; therefore, was introduced as the best model for prognosis and diagnosis of breast cancer.
Conclusion: Intelligent and reliable data mining models are proposed. Hence, these models are recommended as a useful tool for breast cancer prediction as well as medical decision-making.
Keywords: Breast cancer; Data mining models; Diagnosis; Ductal and lobular.