Abstract
Breast cancer is the most common invasive cancer and the second leading cause of cancer death in women. and regrettably, this rate is increasing every year. One of the aspects of all cancers, including breast cancer, is the recurrence of the disease, which causes painful consequences to the patients. Moreover, the practical application of data mining in the field of breast cancer can help to provide some necessary information and knowledge required by physicians for accurate prediction of breast cancer recurrence and better decision-making. The main objective of this study is to compare different data mining algorithms to select the most accurate model for predicting breast cancer recurrence. This study is cross-sectional and data gathering of this research performed from June 2018 to June 2019 from the official statistics of Ministry of Health and Medical Education and the Iran Cancer Research Center for patients with breast cancer who had been followed for a minimum of 5 years from February 2014 to April 2019, including 5471 independent records. After initial pre-processing in dataset and variables, seven new and conventional data mining algorithms have been applied that each one represents one kind of data mining approach. Results show that the C5.0 algorithm possibly could be a helpful tool for the prediction of breast cancer recurrence at the stage of distant recurrence and nonrecurrence, especially in the first to third years. also, LN involvement rate, Her2 value, Tumor size, free or closed tumor margin were found to be the most important features in our dataset to predict breast cancer recurrence.
Highlights
Cancer refers to any one of a large number of diseases characterized by the development of abnormal cells that divide uncontrollably due to genetic mutation in DNA and can infiltrate and destroy normal body tissue
Seven data mining algorithms based on the accuracy, Sensitivity, Specificity, F-measure, area under the ROC curve of the models, etc. are compared
The results indicate that all of the seven methods exceptions for multilayer perceptron (MLP), Bayesian, and Learning Vector Quantization (LVQ) can predict the recurrence of breast cancer, and it is realized that despite adding the new methods to the model, the C5.0 and KPCA-Support Vector Machines (SVM) is the best approximation method
Summary
Cancer refers to any one of a large number (over 100 diverse diseases) of diseases characterized by the development of abnormal cells that divide uncontrollably due to genetic mutation in DNA and can infiltrate and destroy normal body tissue. What is similar among all is the deficiency in the regulating mechanisms of the cells’ natural growth, proliferation, and death. The cancerous cells can invade the tissues nearby and spread to other parts of the body eventually and is the second-leading cause of death in the world [1, 2].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
