A hybrid multi-stage learning technique based on brain storming optimization algorithm for breast cancer recurrence prediction

被引:16
作者
Alwohaibi, Maram [1 ,2 ,3 ]
Alzaqebah, Malek [1 ,2 ]
Alotaibi, Noura M. [1 ,2 ]
Alzahrani, Abeer M. [1 ,2 ]
Zouch, Mariem [1 ,2 ]
机构
[1] Imam Abdulrahman Bin Faisal Univ, Coll Sci, Dept Math, POB 1982, Dammam, Saudi Arabia
[2] Imam Abdulrahman Bin Faisal Univ, Basic & Appl Sci Res Ctr, POB 1982, Dammam, Saudi Arabia
[3] Imam Abdulrahman Bin Faisal Univ, Coll Sci, Dept Math, Dammam, Saudi Arabia
关键词
Data mining; Breast cancer recurrence; Machine learning; Brain storming optimization; Feature selection methods; FEATURE-SELECTION;
D O I
10.1016/j.jksuci.2021.05.004
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Breast cancer disease is considered to be the second leading reason for death among women. Unfortunately, even if the treatment of cancer started soon after diagnosis, the cancer cells may remain in the body, and cancer may recur. Various Machine Learning (ML) methods to predict breast cancer recurrence were applied recently, and the ML methods' performance needs to be examined to determine the proper method for prediction. Usually, the datasets contain many features which may sometimes mislead the prediction process; as some features may lead to confusion or inaccurate prediction. Thus, in this study, two breast cancer recurrence datasets were statistically analyzed and further refined by Brain Storming Optimization algorithm (BSO). The proposed multi-stages technique consists of three main stages; first, the statistical feature selection methods (SFM) which statistically select the discrimi-native features based on importance ranking and features correlations and statistical hypothesis testing, to be passed to the second stage. The features are ranked based on their correlation with the class vari-able. The second stage namely the multi classifier (MC), which evaluates each method based on three classifiers and produces a combination of features performed by two SFM and three classifiers. In the third stage, the best combination of the selected features was recognized by the BSO algorithm to search for an optimal solution that produces the highest accuracy. In addition, the BSO algorithm has been mod-ified to deal with the feature selection problem. The performance of the proposed technique was evalu-ated by stratified 10-fold cross-validation. As a result, the multi-stage learning technique showed to be effective in ranking the features and improved the classification accuracy for breast cancer recurrence.(c) 2021 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
引用
收藏
页码:5192 / 5203
页数:12
相关论文
共 53 条
[1]  
Aalaei S, 2016, IRAN J BASIC MED SCI, V19, P476
[2]   Predicting Breast Cancer Recurrence Using Machine Learning Techniques: A Systematic Review [J].
Abreu, Pedro Henriques ;
Santos, Miriam Seoane ;
Abreu, Miguel Henriques ;
Andrade, Bruno ;
Silva, Daniel Castro .
ACM COMPUTING SURVEYS, 2016, 49 (03)
[3]  
Aggarwa C.C., 2014, DATA MIN KNOWL DISC
[4]   Support vector machines combined with feature selection for breast cancer diagnosis [J].
Akay, Mehmet Fatih .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (02) :3240-3247
[5]  
Alwohaibi M., 2019, EARTHDOC C P, V2019, P1, DOI [10.3997/2214-4609.201902193, DOI 10.3997/2214-4609.201902193]
[6]  
Alzaqebah M., 2020, Int. J. Electr. Comput. Eng. (IJECE), V10, P3672, DOI 10.11591/ijece.v10i4.pp3672-3684
[7]   Hybrid Brain Storm Optimization algorithm and Late Acceptance Hill Climbing to solve the Flexible Job-Shop Scheduling Problem [J].
Alzaqebah, Malek ;
Jawarneh, Sana ;
Alwohaibi, Maram ;
Alsmadi, Mutasem K. ;
Almarashdeh, Ibrahim ;
Mohammad, Rami Mustafa A. .
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2022, 34 (06) :2926-2937
[8]  
[Anonymous], SIAM NEWS
[9]  
[Anonymous], 2011, Data Mining: Concepts, Models, Methods, and Algorithms
[10]  
[Anonymous], 2018, WHO PRESS RELEASE