BCD-WERT: a novel approach for breast cancer detection using whale optimization based efficient features and extremely randomized tree algorithm

• Published in: PeerJ. Computer science Vol. 7; p. e390
• Main Authors: Abbas, Shafaq, Jalil, Zunera, Javed, Abdul Rehman, Batool, Iqra, Khan, Mohammad Zubair, Noorwali, Abdulfattah, Gadekallu, Thippa Reddy, Akbar, Aqsa
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 12.03.2021; PeerJ, Inc; PeerJ Inc
• Subjects: Accuracy; Algorithms; Artificial intelligence; Bioinformatics; Breast cancer; Cancer; Care and treatment; Cetacea; Classification; Data mining; Datasets; Decision trees; Diabetes; Diagnosis; Disease; Feature extraction; Feature selection; Human-Computer Interaction; Literature reviews; Machine learning; Mobile and Ubiquitous Computing; Optimization; Optimization techniques; Performance evaluation; Support vector machine; Support vector machines; Tumors; Whale optimization algorithm; Wisconsin; Taiwan; United States > US; Breast cancer; Support vector machine; Whale optimization algorithm; Machine learning
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/peerj-cs.390

Breast cancer is one of the leading causes of death in the current age. It often results in subpar living conditions for a patient as they have to go through expensive and painful treatments to fight this cancer. One in eight women all over the world is affected by this disease. Almost half a million women annually do not survive this fight and die from this disease. Machine learning algorithms have proven to outperform all existing solutions for the prediction of breast cancer using models built on the previously available data. In this paper, a novel approach named BCD-WERT is proposed that utilizes the Extremely Randomized Tree and Whale Optimization Algorithm (WOA) for efficient feature selection and classification. WOA reduces the dimensionality of the dataset and extracts the relevant features for accurate classification. Experimental results on state-of-the-art comprehensive dataset demonstrated improved performance in comparison with eight other machine learning algorithms: Support Vector Machine (SVM), Random Forest, Kernel Support Vector Machine, Decision Tree, Logistic Regression, Stochastic Gradient Descent, Gaussian Naive Bayes and k-Nearest Neighbor. BCD-WERT outperformed all with the highest accuracy rate of 99.30% followed by SVM achieving 98.60% accuracy. Experimental results also reveal the effectiveness of feature selection techniques in improving prediction accuracy.