Abstract

Breast cancer is the most common type of cancer in the world, as the number of people infected with it reached 2.2 million women in 2020, and World Health Organization reports indicated that the incidence of it is 1 to 12 women, that is, one woman out of every woman. every 12 women. As a result, it is crucial to have high cancer-predictive accuracy to update patient survival criteria and treatment options. Research on machine learning and deep learning, whether using traditional neural networks or using convolutional neural networks, has spread widely and has proven to be a useful technology. It can be very helpful in early detection and prognosis of breast cancer. According to the six machine learning algorithms used in this study and based on the Wisconsin breast cancer diagnostic dataset, they are as follows: Naive Bays (NB), K-Nearest Neighbors (KNN), Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), and Support Vector Machine (SVM), we reached an accuracy of 99.1% with SVM that surpassed all competitors and achieved the highest accuracy. As for deep learning, we have reached an accuracy of up to 99.9%, and this is a reliable result for analysis purposes. In the presented work, the Anaconda environment (Jupyter platform) was used, which uses the Python programming language in all work.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call