Evaluating Machine Learning Classifiers for Breast Cancer Diagnosis: A Comparative Study Using Accuracy Metrics
T A Mohanaprakash, R Kalaiyarasi, M. Ramya, Kolluri Vyshnavi, Madhura Deventhiran, I. Jaichitra · 2023
Globally, breast cancer ranks among the top causes of death for women, and the number of cases is increasing yearly. For better treatment outcomes and patient survival, accurate diagnosis and prediction are essential. Developments in the early detection and diagnosis of cancer are essential for encouraging a long and healthy life. Reaching a high level of accuracy in cancer prediction improves patient care by allowing for prompt interventions. Enhancing survival rates requires machine learning-based breast cancer prediction. On the Breast Cancer Wisconsin Diagnostic dataset, this study tested all machine learning algorithm. Random Forest outperformed other classifiers and obtained the greatest accuracy (98.4%). The study emphasizes how crucial machine learning is to the detection and prognosis of breast cancer. The Python programming language and Scikit-Iearn library were used in the work, which was carried out under the Anaconda environment.