Comparing Neural Networks and Machine Learning Approaches for Predicting the Severity of Breast Cancer

Breast cancer poses a significant health threat and ranks as a leading cause of women’s fatalities globally. To tackle this challenge, we need to focus on improving how we find and treat it early. It’s vital to develop accurate ways to diagnose breast cancer in the medical field. While mammography is effective in detecting breast cancer, the use of Computer-Aided Diagnosis (CAD) systems can further reduce breast cancer mortality rates. Radiologists and doctors use CAD systems to analyze and decide if breast cancer is ‘Benign" or Malignant". But greater research efforts are essential for enhancing our ability to understand and combat breast cancer. In our study, we looked at different computer-based machine learning methods to predict breast cancer severity. We utilized a comprehensive Breast Cancer Wisconsin dataset" to evaluate commonly used Supervised machine learning methods and Artificial Neural Network’s(ANN). Our assessment involved calculation of simple metrics such as accuracy, precision, recall, and F1 score to gauge the effectiveness of these methods. The results,that we obtained in this paper, show that machine learning and ANN’s methods have a big potential in diagnosing breast cancer early, giving useful information for early detection and personalized treatment plans. This study helps healthcare providers by guiding them on finding breast cancer early and managing its severity effectively. It also sets the stage for more research to improve how we diagnose breast cancer using other machine learning methods further in future.