What is it about?
Background: Breast cancer is the cancer with the highest mortality and morbidity rate in the world, and its prevention and treatment have become a challenge for the medical community. Machine learning and artificial intelligence methods have been extensively used to forecast breast cancer. Objective: The primary aim of this study is to evaluate and compare the efficacy of 4 conventional machine learning models in the context of breast cancer prediction. The research made use of the Wisconsin Breast Cancer dataset. Methods: To predict breast cancer in this study, 4 conventional machine learning algorithms were employed. Metrics like as ac- curacy, AUC, precision, recall, and F1 score are used to assess the algorithms’ performance. Results: In this study, the accuracy of the Logistic Regression and Support Vector Classifier is 93%. The Full-Data Accuracy of the K-fold cross-validation of Random Forest Classifier and Decision Tree Classifier is 100%.
Featured Image
Photo by National Cancer Institute on Unsplash
Why is it important?
Conclusions: The experimental results in this paper indicate that Logistic Regression and Support Vector Classifier in the Hold-out method have bet- ter performance in predicting breast cancer incidence. problem with better performance. Random Forest Classifier and Decision Tree Classifier have better prediction performance in K-fold cross- validation. This paper provides guiding suggestions for relevant medical practices.
Perspectives
Read the Original
This page is a summary of: Construction and study of breast cancer prediction model based on machine learning, October 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3644116.3644202.
You can read the full text:
Contributors
The following have contributed to this page