Paper Key : IRJ************151
Author: Riya Satavlekar,Sarvesh Chakradeo
Date Published: 06 Nov 2023
Abstract
As reported by the World Health Organization, breast cancer ranks as the most diagnosed life-threatening malignancy among women globally, with an estimated annual incidence of approximately 2.1 million cases.3 Machine learning techniques have rapidly evolved and become indispensable tools in the field of medical diagnostics. This study aims to explore and evaluate the performance of five widely employed classifiers, including Pocket Perceptron, Support Vector Machine (SVM), Naive Bayes, Random Forest, and K-Nearest Neighbors (KNN). Multiple performance metrics such as accuracy, precision, F1 score, and ROC (AUC), were analyzed, providing a holistic view of each classifier's capabilities. The Wisconsin original breast cancer data set was used as a training set, and all the aforementioned techniques were implemented in a python environment. The results obtained in this study give insights into the strengths and weaknesses of these state of art ML techniques for breast cancer detection. These techniques continue to evolve, and they hold the promise of further enhancing our ability to identify and combat the disease effectively, ultimately improving patient care.
DOI LINK : 10.56726/IRJMETS45818 https://www.doi.org/10.56726/IRJMETS45818