Exploring Machine Learning Algorithms for Accurate Breast Cancer Classification: A Comparative Analysis Using F2 Metric

Breast cancer remains the most prevalent form of cancer globally, and it continues to be a leading cause of cancer-related fatalities among the female population. Swift and accurate diagnosis, particularly in its early stages, has a significant impact on the treatment and survival rates of breast cancer. Technological advancements, including the integration of ML algorithms, have substantially contributed to the detection of breast cancer. Among these algorithms, machine learning-based classification methods have demonstrated exceptional effectiveness in distinguishing between breast cancer and non-cancerous data. This study focuses on comparing the performance of various supervised machine learning algorithms in detecting breast cancer. The assessment employs the WisBCD and involves both performance evaluations and data visualizations. The principal aim is to identify a classifier that attains the highest accuracy while minimizing the error rate. The implementation of these algorithms and subsequent comparisons are conducted using Python and scikit-learn libraries. The experimental findings unveil that the support vector machine algorithm surpasses the other four methods in terms of accuracy and error rate. Thus, based on this dataset, it proves to be the optimal choice in detecting breast cancer.