Conference proceedings article
Breast cancer surgery survivability prediction using Bayesian network and support vector machines


Research Areas
Currently no objects available

Publication Details
Author list: Aljawad D., Alqahtani E., Al-Kuhaili G., Qamhan N., Alghamdi N., Alrashed S., Alhiyafi J., Olatunji S.
Publisher: Institute of Electrical and Electronics Engineers Inc.
Publication year: 2017
Journal name in source: 2017 International Conference on Informatics, Health and Technology, ICIHT 2017
Title of series: Informatics, Health & Technology (ICIHT)
ISBN: 9781467387651
Web of Science ID: 000403395000001
PubMed ID:
Scopus ID: 85019194840


Predicting the survival status of patients who will undergo breast cancer surgery is highly important, where it indicates whether conducting a surgery is the best solution for the presented medical case or not. Since this is a case of life or death, the need to explore better prediction techniques to ensure accurate survival status prediction cannot be overemphasized. In this paper we evaluate the performance of support vector machine (SVM) and Bayesian network (BN) in predicting the survival state of breast cancer patients after having a surgery. The experiments on both techniques have been carried out using Weka software package. Empirical results from simulations showed that support vector machine outperformed Bayesian network in this task, where support vector machine achieved better accuracy of 74.44% while Bayesian network had its best accuracy of 67.56%.


Projects
Currently no objects available

Keywords
support vector machine

Documents
Currently no objects available

Last updated on 2019-30-10 at 13:28