Breast Cancer Prediction Using Histogram Gradient Boosting Classifier

Breast cancer is a disorder where the breast cells multiply unnaturally and incessantly, causing the tissue to be destroyed. It is most commonly diagnosed in women than men. Breast cancer dates back to the ancient Egyptians when the first case was detected 3500 years ago. Since then, it has been a fatal disease that claims thousands of lives every year. But with the enhancement in technology and with the power of machine learning, this can be detected in the early stages and can be cured with proper treatment. In this paper, we suggest utilizing the histogram gradient boosting approach to accurately detect patients having breast cancer. The Wisconsin dataset was used to train the algorithm, which resulted in an accuracy of 95.2%. In addition to the proposed model, other classification algorithms were also used to contrast the effectiveness of the models. Although the histogram gradient boosting classifier produces promising results and has a lower deviation than other classifiers like random forest, we cannot draw the conclusion that it is the only classifier that is the finest because the HGB classifier's deviation won't always be lower than that of other classifiers, and the classifier also cannot be evaluated solely on the basis of deviation.