Meme Kanseri Tahmininde Makine Öğrenme Yöntemlerinin Performansı

In the last 50 years, the effect of cancer disease on the annual number of deaths has increased significantly. This has led to an increase in research on early detection and diagnosis of cancer. Early diagnosis of cancer increases the chance of surviving the disease and reduces the possibility of recurrence of the disease. The technological advances in artificial intelligence and machine learning are used to analyse patient data, while at the same time reducing the likelihood of developing diseases. In this paper, 7 different machine learning algorithms commonly used in the literature are used for breast cancer diagnosis. These are: Logistic Regression (LR), K-Nearest Neighbours (KNN), Support Vector Machines (SVM), Radial Basis Function (RBF) Kernel, Naive Bayes, Decision Tree (DT), and Random Forest (RF) algorithms. In our study, two separate datasets were used for breast cancer diagnosis. In the first dataset, Random Forest, SVM (RBF), and SVM (Linear) algorithms had the highest accuracy value of 96.5, while the K-Nearest Neighbours algorithm had the highest sensitivity value of 98.8, and the decision tree algorithm had the highest specificity value of 98.1. The K-Nearest Neighbour algorithm was also found to be the fastest algorithm, with 1.03 seconds. In the second dataset with different data, the K-Nearest Neighbours algorithm reached the highest accuracy value of 97.7 and was observed to be the second fastest algorithm with 1.48 seconds after the Gaussian Naive Bayes algorithm with 1.14 seconds.