Personalized Treatment Classification for Breast Cancer Patients using Random Forest Algorithm

In traditional treatments of breast cancer patients, people get the similar treatment that means it follows a "one-size-fits-all" approach. Over a while, doctors have noticed that some treatments have given better results for some people than others. Everyone has their own unique identifying features, and so the treatment to the individual patients also needs to be tailor made. Personalized medicine (PM) for breast cancer considers individual differences in people’s lifestyle, surroundings, and genetics, and it provides medicos with the information they need to target disease specific treatments. (ML)Machine learning plays an important role in personalized medicine (PM). It uses computational algorithms to analyze large amounts of data from different input sources such as medical records, molecular, genetic information, and data from clinical trials for finding patterns and predict outcomes. This information can then be used to tailor treatments specifically to an individual’s characteristics and assist doctor in finding risk of disease and finding optimal treatments. The paper discusses about application of supervised machine learning (ML)algorithm: Random Forest algorithms for classification of three treatments of breast cancer patients namely chemotherapy, hormonal therapy and amputation.