Breast Cancer Prediction from Risk Factors Using Ensemble Technique

While women age, the prevalence of breast cancer rises and affects women of all races. Breast cancer kills more females than any other cause of cancer-related death. Risk Analysis for Breast cancer prediction is an important problem in medical research, and the objective of this research is to propose an ensemble approach to address the issue of breast cancer prediction using appropriate risk factors. This work will explore existing techniques and identify various risk factors causing breast cancer. Breast cancer risk analysis may be anticipated using machine learning techniques. The approach involves gathering a dataset of patients, pre-processing the dataset to eliminate unnecessary information and reduce dimensionality, normalizing features, and dividing the dataset into training and testing sets. For treatment to be successful, breast cancer detection is essential. Breast cancer recurrence can be identified using several means such as physical examinations, mammography, ultrasounds, and blood tests. However, machine learning models can aid in predicting the likelihood of breast cancer recurrence using various clinical and molecular features. By identifying high-risk individuals, treatment approaches may be tailored to each individual, lowering the chance of cancer and improving patient outcomes. The proposed research work will incorporate the identified risk factors and the extracted features to accurately predict breast cancer. The Breast Cancer Surveillance Consortium Dataset is used to evaluate and validate the efficacy of the suggested work. Random Forest gave the best results with $\mathbf{7 5. 2 \%}$ accuracy.