Аннотация
The increasing yearly death rates caused by breast cancer, which is the most prevalent kind of cancer and a leading cause of female mortality worldwide, emphasize the urgent requirement for progress in disease prognosis and detection to enhance overall well-being. Attaining a high level of accuracy in cancer prediction is of utmost significance in improving treatment strategies and enhancing patient survival rates. Machine learning (ML) techniques are crucial in improving the accuracy and prior identification of breast cancer. They have become a central focus of study and have shown strong effectiveness. This study applies four machine learning techniques, namely Support Vector Machine (SVM), Decision tree, Gaussian Naive Bayes (NB), and K-Nearest Neighbours (KNN), to the breast cancer Wisconsin diagnostic dataset. Following the obtained outcomes, a thorough assessment and comparison of the performance of these classifiers were carried out. The primary aim of this study is to utilize ML algorithms to forecast and identify the breast cancer, specifically by establishing the most efficient method based on the confusion matrix, accuracy, and precision. Remarkably, the SVM exhibited superior performance compared to the other models, with an impressive accuracy rate of 96.7%. The studies were performed in the Visual Studio Code environment utilizing the Python programming language and the Scikit-learn module.