Comparative Analysis of Machine Learning Techniques for Early Detection of Breast Cancer

Abstract: Breast cancer is the most frequently encountered form of cancer among the populace, and women are more likely than males to develop it. Catching it early increases the likelihood of survival but due to the complex nature of masses and microcalcification, radiologists oftentimes fail to diagnose breast cancer properly. Radiologists use Computer aided diagnostic (CAD) systems to detect abnormalities, however, several uncertainties in breast cancer detection using mammograms makes it challenging. The employment of Machine Learning (ML) in the medical field for diagnosis and its accuracy is an inevitable futuristic step. ML techniques in breast cancer detection greatly help in early and accurate detection thereby increasing the patient’s survival rate. This paper compares the different popular Machine Learning techniques such as Support Vector Machine (SVM), Random Forest (RF), k Nearest Neighbor, and Decision Tree on Wisconsin Breast Cancer dataset. Various metrics for performance evaluation such as Accuracy, Precision, Recall, F1 score, Specificity, False Positive Rate, and False Negative Rate are used for model evaluation. Random Forest yielded the highest accuracy while SVM fared better than other algorithms by achieving the highest precision.