Scopus Indexed Publications

Paper Details


Title
Comparison of Algorithms on Breast Cancer Detection in Developing Countries
Author
Zahura Zaman, AFSANA TASLIM FARIN, Md. Shakawat Al Sakib, Nabanita Saha Joya, Raka Moni, Subarna Akter Liza,
Email
Abstract

All over the world including Bangladesh Breast Cancer is one of the major cancer in women. According to a survey per minute, approximately 1 in 4 cancer patients in the world is who are diagnosed with breast cancer. Immoderate 41,000 women die because of breast cancer annually. Breast cancer is caused by several environmental factors and is caused by interactions between genetically sensitive hosts. Normally, other cells in the body divide and stop over and over again as needed. But in the cancer cell, this process occurs and does not stop. It can be one of the nothing but common cancers in both men and women, although women are in addition likely to get the disease. The risk of death can be greatly reduced by the early detection of cancer and with proper medical care. There are certain signs and symptoms of this cancer that can be used to predetermine if he/she is suffering from this disease. This paper aims to analyze the signs and symptoms with the help of machine learning. To diagnose the disease with better accuracy, the field of machine learning can help the medical professionals by using algorithms such as decision tree algorithm, random forest algorithm, linear regression algorithm, logistic regression algorithm, naive Bayes, and support vector machine. In this paper, we used a number of machine learning algorithms to detect the breast cancer patients. After using the algorithms, gradually and comparing these algorithms will find which algorithm gives principle accuracy. Using these algorithms for detecting patients can get accurate results.

Keywords
Breast cancer Survey, Diagnosis, Early detection, Machine learning, Dataset, Support vector machine, Decision tree, Random forest, Naive Bayes
Journal or Conference Name
Lecture Notes in Networks and Systems
Publication Year
2022
Indexing
scopus