Predictive Modeling for Early Cancer Detection: A Machine Learning Approach to Prostate, Lung, and Breast Cancer

Improving patient outcomes and lowering death rates from cancer need early identification. In this study, we use machine learning algorithms to predict three forms of cancer: prostate, lung, and breast. Lung cancer continues to be the primary cause of cancer-related mortality, while breast cancer affects women significantly worldwide. Prostate cancer is prevalent among men. By harnessing the power of machine learning techniques, our goal is to develop predictive models that can identify these cancers at an early stage, facilitating prompt intervention and treatment. Cancer research is instrumental in supporting medical treatments for patients, and machine learning is increasingly playing a vital role in cancer detection and diagnosis. As technology advances, the future holds the promise of easier cancer prediction without the need for hospital visits. Our project aims to determine the most effective algorithm among SVM and Random Forest for predicting cancer. We consider distinct attributes tailored to each cancer type, such as clump thickness for breast cancer, lifestyle factors for lung cancer, and physical attributes for prostate cancer. Users input relevant data, and our models provide predictions, such as determining benign and estimating the likelihood of being affected by lung or prostate cancer.