Predicting Breast Cancer Using Gradient Boosting Machine
International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064


Downloads: 118 | Views: 369

Research Paper | Computers in Biology and Medicine | Turkiye | Volume 8 Issue 6, June 2019 | Popularity: 6.7 / 10


     

Predicting Breast Cancer Using Gradient Boosting Machine

Sahr Imad Abed


Abstract: Breast Cancer is an uncontrolled growth in the breast. Breast cancer is a primary cause of death in women globally. The amount of death can be reduced by eliminating the accuracies in the diagnosis of the disease. The increase in accuracy of diagnosis can be increased through the predictive technology developed using the Gradient Boosting Machine. The prediction will improve the quality of the treatment process and the survivability rate of the patients. In this paper, we propose a system that will be used for predicting breast cancer via the use of classifiers and machine learning algorithm. The system is intended to be user- friendly and cost-effective to contribute to the fight against this deadly disease. The system will estimate the risk of prevalent breast cancer in the early stage of development. Ultimately, the results of the system will be compared with the pertinent medical results of each patient. The practical part has illustrated that GBM algorithm performed better than the other models. The GBM algorithm had better specificity, accuracy, and sensitivity.


Keywords: Gradient Boosting Machine, Prediction, Algorithm, Machine Learning


Edition: Volume 8 Issue 6, June 2019


Pages: 885 - 891



Please Disable the Pop-Up Blocker of Web Browser

Verification Code will appear in 2 Seconds ... Wait



Text copied to Clipboard!
Sahr Imad Abed, "Predicting Breast Cancer Using Gradient Boosting Machine", International Journal of Science and Research (IJSR), Volume 8 Issue 6, June 2019, pp. 885-891, https://www.ijsr.net/getabstract.php?paperid=ART20197162, DOI: https://www.doi.org/10.21275/ART20197162

Top