Development of an Early Prediction System for Breast Cancer using Machine Learning Techniques

Clinical experience proves that breast cancer is the most popular and fatal malignancy, second only to lung cancer. Timely identification of this kind of cancer enhances the life expectancy of human beings. The accurate detection of Breast Cancer (BC) may enhance the survival of the subject. With the brilliant framework, under constant vigilance, essential medication, etc. the disease can be cured within a specific time. The present article concentrates on the performance and predictive ability of the BC detection model and its evaluation by using seven machine learning(ML) classification algorithms, including Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbours (KNN), Decision Tree (DT), Logistic Regression (LR), Artificial Neural Network (ANN), and XG-Boost (XGB). By means of the Wisconsin Breast Cancer Dataset (WBCD) as the primary data source, this work's most important goal is to compare these algorithm's results. Various criteria of performance taken into consideration include precision, accuracy, recall, and
$f - 1$
score,
$99{{\% }}$
accuracy was attained by the ANN and SVM, according to our study of the findings, and the DT provides a
$95{{\% }}$
accuracy grade, which is the lowest.