Developing Machine Learning Models to Detect Breast Cancer

Breast cancer is the most common cancer in females, causing a significant amount of morbidity and mortality. In 2020, there were about 2.3 million new cases and 684,996 deaths worldwide. Early detection is critical, especially in younger women in India, where incidence rates are rising. This study explores the use of artificial intelligence and machine learning for early-stage breast cancer detection and survival prediction using the Breast Cancer Wisconsin dataset. It points out key characteristics of cell nucleus based on the feature extractions from FNA images of breast masses. Various distinct techniques of machine learning have been addressed in this study, including Random Forest, K-Nearest Neighbors, Support Vector Machines, and Logistic Regression. Out of these, Support Vector Machines and Logistic Regression produced similar results, with accuracy values of 98.24%. These results demonstrate the possibility of enhanced outcome measures and promotion of early diagnosis for the patients through machine learning.