Model To Detect Breast Cancer Based On Patient Symptoms

Abstract

The number of medical data warehouses is expanding quickly these days. As a result, it is difficult for us to predict or analyse these facts in order to uncover hidden knowledge that is valuable. For forecasting medical analysis, many machine learning methods and tools are employed. The most prevalent and well-known malignancy, particularly among women, is breast cancer. It ranks among the leading global causes of death. The sole remedy is early detection, which lowers the mortality rate from breast cancer. Breast cells can develop into cancer, which is known as breast cancer. Breast cancer has recently become a highly serious disease, not just in India but also in other nations. The primary goal of this research is to diagnose breast cancer patients as early as possible. Three machine learning approaches Decision Tree, Support Vector Machine, and Logistic Regression are employed for the early detection and prevention of breast cancer patients. These techniques help reduce waiting times and human and technical errors in breast cancer diagnosis. By employing these methods, we can increase the number of lives saved and decrease the death rate by maximising early diagnosis of breast cancer. The likelihood that an infection will be successfully treated depends on precisely identifying and locating it as soon as possible using logistic regression and SVM. A significant obstacle to the diagnosis of breast cancer is the classification of the appropriate machine learning technique. Thus, in order to analyse risk levels that contribute to prognosis, we developed a model for a breast cancer early prediction system. Doctors can diagnose breast cancer using this experimental study, and patients can benefit from early therapy to prolong their lives.