The Effective Breast Cancer Classification with the Random Forest Algorithm

Breast cancer is a serious threat to public health around the world. Breast cancer diagnosis and categorization are critical for efficient therapy and a higher likelihood of cure. The Random Forest algorithm was utilized to categorize breast cancers in this work, with the Breast Cancer Wisconsin (BCW) dataset serving as training data. The primary goal of this research is to create an effective breast cancers classification model utilizing the Random Forest method. Setting parameters and random forest configurations, such as the number of trees in the forest and random state values, were used in this study to get the best performance in breast cancer classification. The Random Forest with appropriate hyper parameters produced a highest accuracy of 99.12% in testing. This model is more accurate than earlier research in classifying breast cancers. This discovery helps to diagnose breast cancer and reduces misdiagnosis, enhancing the patient's chances of recovery.