A Comparative Study of Breast Cancer Detection and Recurrence Prediction Using CatBoost Classifier
Type of document
articlePeer-reviewed
publishedVersion
Author
Abdu-aljabar, Rana Dhia’a
Aljafaar, Khansaa Dheya
Ameen, Zinah Jaffar Mohammed
Naman, Hala A.
Rights
Creative Commons Attribution 4.0 International Licensehttp://creativecommons.org/licenses/by/4.0/
openAccess
Metadata
Show full item recordAbstract
In 2019, breast cancer accounted for over one-third of all cancer cases in women in Iraq. It affects both men and women, though it is more common in women. This study delves into advanced machine learning techniques – CatBoost, XGBoost, Random Forest, SVM, KNN, and Naive Bayes – to improve the detection and prediction of breast cancer recurrence after healing. The goal is to evaluate models using key metrics (sensitivity, specificity, precision, F1 score, accuracy, ROC, and AUC score). Among all algorithms examined, CatBoost stood out, showcasing AUC values above 98 %, 90 %, and 83% on different datasets. This research demonstrates how machine learning techniques can significantly improve the accuracy of breast cancer detection and recurrence prediction, steering healthcare providers towards better patient care outcomes and more effective treatment plans.
Collections
The following license files are associated with this item:
Except where otherwise noted, this item's license is described as Creative Commons Attribution 4.0 International License