XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Using Data Mining Methods (SVM and Bagging) to Survival Prediction in Patients with Colon Cancer in the Radiotherapy Section of Namazai Hospital. irje. 2018; 1111
URL: http://irje.tums.ac.ir/article-1-5802-en.html
Abstract:   (1291 Views)
Background and Objectives: Colon cancer is the second most common cancer in the world and fourth most common cancer in both sexes in IRAN, whose % 8.12 of all cancers in the covers. Predict the outcome of cancer and basic clinical data about it is very important. Then according to high rates of colon cancer and the benefits of data mining to predict survival, the aim of this study was to survey two widely used machine learning algorithms; Bagging and Support Vector Machines (SVM) to predict the outcome of colon cancer patients.
Methods: The population of this study was 567 patients with 1-4 stage of colon cancer in Namazi radiotherapy center in Shiraz in 2006-2011. Three hundred thirty eight patients were alive and 229 patients were dead. We used of Support Vector Machines (SVM) and Bagging methods in order to survival predicting patients with colon cancer. We analyzed our data with Weka Software (Ver.3.6.10).
Results: About 57% of patients were men. More than 45% of patients were in range of 50-70 years old. The maximum and minimum of tumors’ location was related to rectum and left colon with 51% and 9% respectively. The treatment in more than 80% of patients was initially surgical, then chemotherapy or radiotherapy. The performance of two algorithms was determined with confusion matrix. Accuracy, specificity and sensitivity of SVM were 84.4, 80, and 87.5, and in Bagging were 83.2, 75 and 88 percent, respectively.
Conclusion: The results showed both algorithms have a high performance in survival prediction of Patients with colon cancer but Support Vector Machines has a more accuracy.
     
Type of Study: Research | Subject: General
Received: 2017/11/12 | Accepted: 2017/11/12 | Published: 2017/11/12

Add your comments about this article : Your username or Email:
Write the security code in the box

© 2017 All Rights Reserved | Iranian Journal of Epidemiology

Designed & Developed by : Yektaweb