A cost-sensitive logistic regression model for breast cancer detection

ABSTRACT

The diagnosis of breast cancer (BC) with a machine-learning model is a classification problem where the model involves training a model to identify the class of a given observation. However, real-world Wisconsin’s BC diagnostic dataset, which is widely employed to implement a model for BC detection, consists imbalanced class. The benign class outnumbers the malignant class. The implementation of a model for BC detection with an imbalanced dataset leads to biased classification towards the majority class leading to lower accuracy and precision of malignant class. Thus, this research proposes a cost-sensitive logistic regression model for BC detection. During the training phase, benign and malignant class is weighted to influence the classification bias toward begin class. The study compared the model with standard logistic regression. The experimental result appears to prove that the proposed model outperforms as compared to standard logistic regression. The model has receiver characteristic curve area value AUC = 99.99.

KEYWORDS:

• Logistic regression
• BC detection
• imbalanced classification
• costs-sensitive model
• BC prediction
• random forest algorithm
• machine learning
• SVM

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Sushma S J

Dr Sushma S J is working as Associate Professor, Department of ECE, GSSS Institute of Engineering and Technology for women, Mysuru. She has got 21 years of teaching experience. She has obtained Bachelor of Engineering from Manglore University in the year 2001. In 2007. She obtained Master of Technology and Ph.D from Visveswaraya Technological University, Belagavi, India. She has published 40+ papers in national conferences 16+ in international conference and 50+ in international journal. Her area of interests includes Image Processing, Computational Intelligence, machine learning, data science and Computer Networks.

Prasanna Kumar S C

Dr Prasanna Kumar S C is working as Professor, Department of Instrumentation Technology, RV college of Engineering, Bangalore. He has got 25 years of teaching, 01 year of industry and 15 years of research experience. He did his Bachelor of Engineering and master of Engineering from Mysore University. He was awarded PhD in the year 2009 from Avinashlingham University, Tamilnadu. He has published over 25 papers in national and international conferences and around 70+ papers in the international journals. He has received academic excellence award for the years 2008 and 2009 3.

Tsehay Admassu Assegie

Tsehay Admassu Assegie, is working as Assistant professor Department of Computer Science, Injibara University, Ethiopia. He has to his credits 100+ publications in various conferences and journals. His area of interest are Machine learning, Deep learning, Image processing.