An Efficient Machine Learning Algorithm for Breast Cancer Prediction

EasyChair Preprint 8706

Abstract

Cancer is a leading cause of death worldwide, with breast cancer (BC) being the most common
and prevalent with 2.26 million cases each year, and the main cause of women’s deaths, so early
and correct detection to discover BC in its first phases, help to avoid death by describing the
appropriate treatment and to maintain human life. Cancer cells are divided into two types
Malignant and Benign. The first type is more dangerous and the second type is less dangerous.
Due to the existence of artificial intelligence (AI) and the great direction to the use of machine
learning in medicine, doctors get accurate results for diagnosis. In this paper, we tend to use the
Wisconsin Breast Cancer Patients Database (WBCD) which has been collected from the UCI
repository. In this paper, the WBCD dataset is divided into 75% for training and 25% for testing
using a split test train. We addressed to research the performance of various well-known algorithms
in the discovery of BC such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN),
Naïve Bayes (NB), Decision Tree (DT), Random Forest (RF), Logistic Regression (LR) and
Artificial Neural Networks (ANN). High results indicate that the RF algorithm is 98.2% superior
to the rest of the machine learning algorithms

Keyphrases: WBCD, breast cancer, classification algorithms, machine learning

@booklet{EasyChair:8706,
  author    = {Yousif A. Alhaj and Marwan M. Al-Falah and Abdullah M. Al-Arshy and Khadeja M. Al Nashad and Zain Alabedeen Ali Al Nomi and Badr A. Al Badawi and Mustafa S. Al Khayat},
  title     = {An Efficient Machine Learning Algorithm for Breast Cancer Prediction},
  howpublished = {EasyChair Preprint 8706},
  year      = {EasyChair, 2022}}