Comparative analysis in execution of machine learning in breast cancer identification: a review

Carcinoma known as breast cancer is a significant common cancer among women worldwide. In line with the global trends, it accounts for many new cancer cases and cancer-related deaths, giving it a substantial public health issue in today's culture. Early diagnosis is the most effective method to reduce the number of deaths in patients with breast cancer. Effective and early diagnosis of breast cancer ensure like mammography or biopsy to ensure the long-term survival of affected patients. Several conflicts arise in using traditional approaches, such as overdiagnosis or under-diagnosis. Machine learning is used to overcome the issues where it can strengthen the current conventional diagnosing of patients with breast cancer. The application of the classification method for diagnosing breast cancer is reviewed in this paper. Support Vector Machine (SVM), Naïve Bayes, K-Nearest Neighbour (KNN), Decision Tree, Artificial Neural Network (ANN), and logistic regression are six methods presented in the review. These techniques are integrated with conventional methods, often allow physicians to diagnose breast cancer effectively. In summary, machine learning improvises in diagnosing breast cancer in terms of accuracy, sensitivity, and specificity with excellent performance and quality of patients