Problem Statement: Breast cancer is the most common cancer in women worldwide. In US, 1 in 8 women are expected to get breast cancer during their lifetime (American Cancer Society, 2023). In 2020 alone, 2.3 million women were diagnosed with breast cancer worldwide, and 685,000 died from it (World Health Organization). Identification of cancer early is the key to cure. 5-year survival rate for localized stage is 99%, while it is only 30% for distant stage (ACS, 2023)
Key to early detection is identification of women at risk, and to test them early and frequently.
Data Collection & Processing: A labeled dataset with 286 instances described by 9 attributes is chosen. Data cleaning, processing including handling missing values was completed.
Training and Testing data: : 80% of the data has been used to train the ML model and 20% used for testing the model.
Visualization: Scatter plots, bar charts, box plots were used.
ML algorithms: Logistic regression, Random Forest algorithms are implemented. Additional investigation in progress.