Authors : A. Anu Priya; T. Pramoth Krishnan; Dr. C. Suresh

Volume/Issue : Volume 9 - 2024, Issue 3 - March

Google Scholar : https://tinyurl.com/ps8ktpxn

Scribd : https://tinyurl.com/53apdh7m

DOI : https://doi.org/10.38124/ijisrt/IJISRT24MAR845

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Detecting breast cancer early is crucial for improving patient survival rates. Using machine learning models to predict breast cancer holds promise for enhancing early detection methods. However, evaluating the effectiveness of these models remains challenging. Therefore, achieving high accuracy in cancer prediction is essential for improving treatment strategies and patient outcomes. By applying various machine learning algorithms to the Breast Cancer Wisconsin Diagnostic dataset, researchers aim to identify the most efficient approach for breast cancer diagnosis. They evaluate the performance of classifiers such as Random Forest, Naïve Bayes, Decision Tree (C4.5), KNN, SVM, and Logistic Regression, considering metrics like confusion matrix, accuracy, and precision. The assessment reveals that Random Forest outperforms other classifiers, achieving the highest accuracy rate of 97%. This study is conducted using the Anaconda environment, Python programming language, and Sci-Kit Learn library, ensuring replicability and accessibility of the findings. In summary, this study demonstrates the potential of machine learning algorithms for breast cancer prediction and highlights Random Forest as the most effective approach. Its findings contribute valuable insights to the field of breast cancer diagnosis and treatment.

Keywords : Machine Learning Models, Data Exploratory Techniques, Breast Cancer Diagnosis, Tumors Classification.