Roshni Dave, Annie Sung, Kathleen Shang, Nia Jeyakrishnan
Mentor: Isita Talukdar
This project seeks to predict breast cancer mortality with AI and ML algorithms on the Kaggle Breast Cancer dataset (https://www.kaggle.com/datasets/reihanenamdari/breast-cancer)
Logistic Regression, Decision Tree, and Random Forest algorithms were implemented via sci-kit learn on a dataset of clinical information about breast cancer patients. The models were trained to predict mortality based on 6 variables: Tumor size, A Stage, Grade, Differentiation, Race, Status
Overall, Logistic Regression performed best with a prediction accuracy of 84.8%, proving that ML can be used to predict breast cancer. Feature Importance analysis suggests that Tumor size and differentiation are the most crucial factors for predicting breast cancer survivability.
Project Presentation Slides: https://docs.google.com/presentation/d/1pA5fzNfwH5kvyTra7aqCrjFDIkv-H_tWmr_-wYcy08o/edit?usp=sharing Live Presentation Recording: To Be Posted