Background: In recent years the growing trend of colon cancer has revealed that we need some safe and new methods to detect and control this disease. Data mining is one of these methods, one of its most important applications is the discovery of hidden patterns between data in a large database. In this study, we explore and discover unknown patterns in a real colon cancer data set.
Methods: In this study, the information of 400 colorectal cancer patients, with 42 cfeature has been studied.This information was collected through the Colorectal Research Center, Shiraz University of Medical Sciences, between 2008 and 2016. After performing the data set preprocessing, the hidden relationships between the features of this data are discovered through the Fp-Growth algorithm.
Results: Ater using this algorithm and discovering the relationship between some of the features, some rules have been developed. Based on the suggestion of the specialist and the importance of the features, the rules have been studied in seven groups.
Conclusion: The results of the review of the laws indicate that the pathologic stage and the age of the patient had a significant effect on the survival rate of the patients.
Also, the percentage of men and women with rectal cancer is greater than that of the clone, and the sex does not affect the survival of the patient.
Other findings from the review of this data can be the lack of a meaningful relationship between the patient's pathologic stage and the demographic information.
Rights and permissions | |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |