Prediction of Breast Cancer Using Machine Learning Techniques

Breast cancer affects the majority of women around the world. Females are more likely to die as a result of this condition. By employing a variety of cutting-edge procedures, the samples are collected and the main cause of breast cancer is sought. The most modern techniques are logistic regression discriminant analysis and principal component analysis, both of which are useful in determining the causes of breast cancer. The Breast Cancer Wisconsin Diagnostic Dataset collects information via the Machine Learning Repository approach. As a result of the data correlation matrix processing, we are able to positively root our job. Principal component analysis, discriminant analysis, and logistic regression are utilized to extract the features. Models like Decision Tree, Naive Bayes, Logistic Regression, Support Vector Machines, and Artificial Neural Networks are utilized and their performance is rigorously examined. The results suggest that the proposed strategy works effectively and reduces training time. These new methods help doctors understand the origins of breast cancer and distinguish between tumor kinds. Data mining techniques are used extensively, especially for feature selection. Conclusion: Among all models, the hybrid discriminant-logistic (DA-LR) feature selection model outperforms SVM and Naive Bayes. Keywords: breast cancer, naïve Bayes, neural network, machine learning, medical imaging support, vector machine Copyright (c) The Authors