Breast Cancer Identification and Classification Using Machine Learning Techniques

The most prevalent disease among women and a major contributor to the rising mortality rate among women is breast cancer. There is a high need for automatic diagnostic systems for early identification of breast cancer since manual breast cancer diagnosis takes a lot of time and there are few systems available. Deep learning and machine learning approaches play a vital role in developing such technologies. We have employed machine learning classification algorithms to distinguish between benign and malignant tumours. These approaches allow the computer to learn from previous data and predict the category of fresh input. Breast cancer is the major cancer in women (43.3 instances per 100,000 women) but the one with the highest mortality rate (14.3 incidents per 100.000 women). For survival, early diagnosis is essential. The issue may be successfully identified, forecasted, and evaluated using machine learning techniques. The eight machine learning methods we compared in this study were the Gaussian Naive Bayes (GNB), kNearest The experiment includes a confusion matrix, 5-fold merge, Neighbours (K-NN), Svm Classifiers (SVM), Variational Forest (RF), AdaBoost, Multilayer Perceptron (GB), and datasets from Breast Cancer Badgers. The results of the tests showed that ANN had the better spec. Efficiency (99.28 percent), F1-score (99.99 percent), recall (96.75 percent), accuracy (99.19 percent), and AUC were attained via XGBoost (99,61 percent ). Our findings demonstrated that, in the Breast Cancer Wisconsin dataset, ANN is the most successful approach for predicting tumor.