Identifying Breast Cancer's Nuclei Features for Machine Learning Prediction and Risk Factor Analysis

Breast cancer is a leading cause of cancer-related deaths in women worldwide. Early detection and diagnosis of breast cancer can significantly improve the chances of successful treatment and survival and thus we wanted to prove this by using several datasets and seeing whether machine learning had a part to play for early diagnosis based on its accuracy and practicality. One dataset showcases the presence of malignant tumors based on the dimensions of a breast cancer nuclei, the other shows the presence of breast cancer based on the risk factors held by a person such as their BMI. The results showed that SVM was the best machine learning algorithm for the dataset with the breast nuceli and had an accuracy of over 98% with best features whereas the dataset for the risk factors had an 84% accuracy with logistic regression. For the features that determined breast cancer the most, from the first it was the: concavity, area, perimeter and radius that showed the highest deterministic features for breast cancer whereas for the risk factors, it was: fat and working status. Overall, our study demonstrates the potential of machine learning algorithms for predicting the risk of breast cancer and highlights the importance of early detection and diagnosis in improving the chances of successful treatment and survival.