Machine Learning Model for Breast Cancer Data Analysis Using Triplet Feature Selection Algorithm

Abstract

The machine learning techniques can be used for clinical investigations in breast cancer diagnosis. The researchers investigated various machine learning algorithms, such as Support Vector Machine, Naïve Bayes, Logistic Regression (LR), Random Forest, Decision Tree and K Nearest Neighbor to diagnose the disease. Early detection of breast cancer cells from the features is essential. Feature selection is the process of reducing the input features to improve the performance of the model. This research aims to increase the accuracy, sensitivity, specificity and to reduce the False Positive Rate (FPR) and False Negative Rate (FNR) by feature selection. The proposed feature selection technique is comprised of two phases: feature grouping and feature selection. In the first phase, feature grouping uses the Pearson correlation techniques to identify the correlation among the features and group the features based on high-, medium- and low- level ranking. In the second phase, Triplet Feature Selection (TFS) method has been proposed to avoid collinearity among the features. In this, the features are selected based on the correlation differences in each subset when satisfying the race condition. Finally, select the features in the triplet group and apply LR classification technique to diagnose the disease. The proposed classifier achieved an accuracy (95.4%), FPR (1%), FNR (4%), sensitivity (97%) and specificity (96%) to detect the benign and malign ones. The effects of TFS feature selection with LR classifier were used and the performance of the proposed framework was compared with the existing feature selection methods and classifiers.

KEYWORDS:

• Accuracy
• Benign
• Correlation
• Logistic regression
• Malignant
• Triplet feature selection

Additional information

Notes on contributors

Dhivya P.

P Dhivya is currently pursuing her PhD in information and communication engineering in the area of big data analytics from Anna University, Chennai. She completed ME in computer science and engineering from SNS College of Technology, Coimbatore. She has seven years of teaching experience in engineering colleges and currently working as assistant professor in the Department of Computer Science and Engineering at Bannari Amman Institute of Technology, affiliated to Anna University, Chennai. Her research interest includes machine learning and mobile ad hoc networks. She published over 10 articles in refereed international journals which were indexed in Scopus and Google Scholar, one book publication titled “Computer Organization and Architecture” and 12 papers in national and international conferences. She has filed two national level patents.

Bazilabanu A.

A BazilaBanu is professor in the Department of Computer Science and Engineering at Bannari Amman Institute of Technology, India. She received her PhD degree in information and communication engineering from Anna University, India in 2015 and is guiding PhD scholars. She holds 16 years of professional experience in academic and softwares Industry. She is an advisory board member for International Association of Data Science, Asia Pacific University of Technology and Innovation, Kualalumpur, Malaysia. She has published 14 articles in national and international journals. She is an active reviewer and Guest Editor for international journals and technical committee member for international conferences organized by Malaysia and Thailand universities. Her research interest includes big data and data analytics. She has filed three National level patents and received grants from AICTE for Margdarshan scheme and National Commission for Women. E-mail: [email protected]

Thirumalaikolundusubramanian Ponniah

Ponniah Thirumalaikolundusubramanian is an emeritus professor, Department of Medicine, Trichy SRM Medical College Hospital and Research Centre, Irungalur, Trichy, India. He completed MBBS in 1971 and an alumnus of Tirunelveli Medical College, Madurai University and MD in general medicine from Madurai Medical College, Madurai in 1979. He completed post graduate diploma in counseling and guidance from Madurai Kamaraj University, Madurai in 1985 and received post graduate diploma in medico legal systems in 2003 from Symbiosis International University, Pune. He received special training in various aspects of health science research, medical education and health care. He worked as a faculty and handled both UG and PG students in various government medical colleges and elevated to the post of director, professor and head of Institute of Internal Medicine, Madras Medical College, Chennai and retired in 2007 from Govt services. He received different awards from Association of Physicians of India, Indian Medical Association, The Tamil Nadu Dr MGR Medical University, Madras Medical College. His areas of interests are community health education, health science Research, infections, toxicology, ethical and legal aspects of healthcare. He has published 200 articles/reports/communications in PubMed (USA) indexed journals and another 40 articles in Indian medical journals as well as presented over 300 papers at national/regional/international conferences. E-mail: [email protected]