Comparing the performance of machine learning algorithms for the prediction of breast cancer recurrence

The most widespread cancer in females around the world, breast cancer is accountable for more than 25% of all cases in females (approximately 23 percent). Considering breast cancer is the deadliest disease and death increases with late-stage diagnosis, early identification is highly recommended to lower mortality. The medical industry’s innovation and technological development have played a prominent part, and the majority of women with breast cancer have made a full recovery for the first time. The current challenge is sensing a recurrence of breast cancer at a preliminary phase after recovering from the first occurrence. In medical diagnosis, there are several approaches available for breast cancer recurrence prediction, with mammography being the most common and widely used method. However, these methods have some shortcomings, such as the fact that they necessitate additional diagnosis, which takes time, and they are not always accurate. Additional strategies for predicting breast cancer recurrence are required to improve life expectancies. Today’s world, Data Mining plays an important role in medical diagnostics, producing astounding results that help a patient survive. Using two dissimilar machine learning techniques from data mining, the Support Vector Machine algorithm and other one is the Artificial Neural Network algorithm, this learning method uses the Breast Cancer Wisconsin (Prognostic) Dataset to forecast breast cancer recurrence in the initial stages. Using metrics like Accuracy, Precision, and Recall, the algorithms’ ability in foretelling breast cancer recurrence is contrasted. At the data-preparation phase, the dataset’s missing attribute values are filled in using the K-Nearest Neighbor method.