Breast Cancer Prediction Using Machine Learning with source code

One of the most prevalent cancers impacting women globally is breast cancer. To successfully treat the disease and increase survival rates, early identification of breast cancer is essential. Breast cancer prediction using machine learning has demonstrated encouraging results, which can assist healthcare professionals in making better decisions regarding patient treatment.

 The goal of this study is to use machine learning algorithms to predict breast cancer. Age, tumor size, lymph node status, and hormone receptor status are just a few of the features included in the dataset that was utilized for this study. The dataset is taken from Kaggle. 

These characteristics are used to determine whether or not a patient has breast cancer. Python and several machine learning libraries, including NumPy, Pandas, Matplotlib, and Scikit-learn, are used to build the project. The dataset is initially preprocessed, which entails categorical variables being encoded, scaling the data, and deleting missing values. Then, several machine learning techniques, including logistic regression, decision trees, random forests, and support vector machines, are trained on the data after dividing the data into training and testing sets. Each algorithm's performance is assessed using a variety of criteria, including accuracy, precision, recall, and the F1 score. The outcomes demonstrate that, in terms of accuracy and F1 score, the Random Forest method performs better than other algorithms. To aid in early identification and treatment, the trained model may be used to predict breast cancer in new patients. Overall, this project shows the effectiveness of machine learning in predicting breast cancer, which can assist healthcare professionals in making better-informed decisions about patient treatment.