A Comparative Analysis of Machine Learning Techniques for Breast Cancer Prediction

One of the major diseases found in women worldwide is Breast Cancer. More than 2.2M cases have been reported with about a 30% mortality rate in accordance with WHO. The rapid advancement of technology has led to breakthroughs in different fields such as medicine, automotive, etc. Despite advancements in screening technologies, achieving high sensitivity and specificity for early detection remains a challenge. Machine Learning is one of the front runners and is currently playing a vital role in solving real-world problems, particularly in the healthcare domain. Using different Machine Learning algorithms prediction of Breast Cancer has been tallied in this work. Various algorithms such as SVM (Support Vector Machine), KNN (K-Nearest Neighbours), DT (Decision Tree), and RF (Random Forest) have vast application areas. In this study, these algorithms have been tested and evaluated on the basis of precision, recall, and accuracy which are the key performance metrics for the evaluation of the model. The dataset for breast Cancer has been pulled from Kaggle, which is the most prominently used dataset by researchers. The simulation results revealed that Random Forest outperformed the others with the precision of 94.5%, recall of 94%, and accuracy of 95%, clearly showing its potential to be used for early prediction of Breast Cancer.