BREAST CANCER CLASSIFICATION USING MACHINE LEARNING (KEY IJP************957)

• Sagar St,Sagar Sv,Madhu P,Nakul Hm

Abstract

Breast cancer (BC) is the second most prevalent type of cancer among women leading to death, and its rate of mortalityis veryhigh. Its effects will bereduced ifdiagnosed early. BCsearlydetection will greatlyboost theprognosisand likelihood ofrecovery, as it mayencourageprompt surgical care for patients. It is therefore vital to have a system enabling the healthcare industry to detect breast cancer quickly and accurately. Machinelearning (ML) is widely used in breast cancer (BC) pattern classification duetoitsadvantagesin modelling a critical featuredetection from complex BC datasets. In this paper, we propose a system for automatic detection of BC diagnosis and prognosis using ensemble of classifiers. First, we review various machine learning (ML) algorithms and ensemble of different ML algorithms. We present an overview of MLalgorithmsincluding ANN, and ensemble ofdifferent classifiers for automatic BC diagnosis and prognosisdetection. Wealsopresent and compare various ensemble models and other variants of tested ML based models with and without up-sampling technique on two benchmark datasets. Wealso studied theeffects ofusing balanced class weight on prognosisdataset and compared its performance with others. Theresults showed that theensemblemethod outperformed other state- of-the-art methodsand achieved 98.83% accuracy. Because ofhigh performance, theproposed system is ofgreat importancetothemedical industryand relevant research community. Thecomparison showsthat theproposed method outperformed other state-of-the-art methods.