BREAST CANCER PREDICTION USING MACHINE LEARNING

Abstract

Breast cancer, a formidable foe plaguing women's health, demands accurate forecasts to guide treatment and extend lives. Unfortunately, doctors often grapple with unreliable prognosis models, making it difficult to craft the right strategy. Enter this research, a beacon of hope seeking to illuminate the path forward. SVM, Logistic Regression, Random Forest, and KNN. This study puts them to the test, pitting them against diverse datasets within a simulated JUPYTER environment. But their battleground isn't singular; it spans three crucial domains: predicting cancer before diagnosis, pinpointing outcomes after diagnosis and treatment, and even monitoring progress during treatment. But to understand each algorithm's strengths and weaknesses, paving the way for personalized medical strategies. This is a vital step towards a future where we can categorize and predict with laser focus, tailoring approaches to each patient's unique needs. This research lays the groundwork for further exploration, promising to delve into predicting even more parameters and exploring previously unconsidered factors lurking in the vast online domain. By refining our prediction tools and broadening our scope, we inch closer to a future where breast cancer, once a formidable foe, becomes a battle we can decisively win.