Detecting the Stage of Breast Cancer Using Machine Learning Algorithms

The cancer type that affects women the most frequently diagnosed today is breast cancer. It manifests in the breast tissue and is one of the top reasons of death for women. This malignancy is curable if it is discovered when it is still treatable. Regarding the instance of breast cancer, there are two different types of tumors: benign and malignant. Cancerous tumors are fatal because they develop significantly more quickly than benign tumors do. Therefore, early tumor type identification is crucial to ensuring that a patient with breast cancer receives the best possible care. The Wisconsin Bosom Malignant Growth Dataset, which was used in this work, came from the UCI repository. The dataset will be examined to see which artificial intelligence algorithm is better at foretelling breast cancer. In this case, classifiers including backing vector machine, strategic relapse, k-nearest neighbors, choice tree, credulous Bayes, and irregular backwoods have been used to distinguish between benign and dangerous growths. To choose the optimal algorithm, each accuracy is calculated and contrasted. The investigation demonstrates that with an accuracy of 96.5%, random forest and support vector machine perform better than other classifiers. Using these classifiers, one may create a pre-programmed indicative framework for diagnosing breast cancer.