Performance Analysis of Machine Learning Classifiers for Breast Cancer Diagnosis

One of the worst conditions, breast cancer is the second leading cause of death from cancer in women. Breast cells begin to develop into malignant, cancerous lumps, which are the first signs of breast cancer. The incidence of breast cancer cases is gradually rising, particularly as the population ages. Mammography screening procedures should be improved and made more effective. When it comes to medical imaging, there is always space for improvement. Cancer patients’ chances of dying can be lowered by early identification. This study compares the diagnosis of breast cancer using six different machine-learning approaches. Image preparation, categorization, and effectiveness evaluation are all part of the process overall. Using the WDBC dataset, we compare the accuracy of the Random Forest, Gaussian Naive-Bayes, Decision Tree, Support Vector, Logistic Regression, XG Boost, Bagging Classifier, and Naive Beys Gaussian machine learning models in classifying between normal tumors and malignant tumors. The results demonstrate that, in terms of accuracy, the Support vector machine outperforms all other machine learning classifiers with a score of 98.2%.