Multiclass Classification of Breast Cancer using Machine learning techniques
Abstract
Highly available genomic data has led to enriched analysis of various genetic disorders including breast cancer. This has significantly improved the treatment strategies leading to reduced mortality rates. Literature has identified seven breast cancer subtypes based on molecular profiles; this molecular data can be leveraged to build models to classify tumour subtypes of the patients. Identifying the right subtype of breast cancer results in better prognosis and therapeutics. Machine learning techniques like Logistic Regression (LR) and Support Vector Machines (SVM) were used to build multiclass classification models. One vs One and One vs Rest scheme were adopted with these techniques to support multiple classes. This study demonstrates and compares the models for classifying breast cancer subtypes using ma-chine learning. It was observed that LR was better choice for multiclass classifications
Keywords
Support Vector Machine, Logistic Regression, Multiclass Classification, Breast cancer subtypes, Gene expression.