Predictive Analysis of Machine Learning Algorithms for Breast Cancer Diagnosis

Cancer is one of the fastest growing disease around the world and subpart of it Breast Cancer that is growing rapidly and mostly affecting women. Early treatment of this disease is helpful and can act as an early prevention to the upcoming major cure. However this can only be possible only if women are able to know that they are suffering with such disease and this can be only diagnosed if they come up with it and openly sharing with family and Doctors about the disease. This can lead to be a bit challenging task as to detect this disease among women using mammography as patient communication can affect mammography performance. This disease has had many ideas and myths as to how we can diagnosed it but Machine Learning the subset of Artificial Intelligence that can help Doctors and Surgeons to learn from past experiments. To treat upcoming patients with similar anomalies has had the major help of saving many patients with its set of algorithms and set of applications it provides. This paper will be focusing on five of the popular supervised Machine Learning algorithms for Diagnosing Breast Cancer this will be K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest (RF), Naïve Bayes (NB) and Decision Tree (DT) and the algorithm Random Forest gave the best results and the K Nearest Neighbor was the second best performing algorithm that produce desired results and the algorithm Naïve Bayes was the least performing algorithm.