Enhanced Neutrosophic Set and Machine Learning Approach for Breast Cancer Prediction

Abstract

Breast cancer is the most prevalent type of cancer that affects women worldwide and poses a serious risk to female mortality. In order to lower death rates and enhance treatment results, early detection is critical. Neutrosophic Set Theory (NST) and machine learning (ML) approaches are integrated in this study to provide a novel hybrid methodology (NS-ML) that improves breast cancer diagnosis. Using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset, the research transforms these data into Neutrosophic (N) representations to effectively capture uncertainties. When trained on the N-dataset instead of traditional datasets, ML algorithms such as Decision Tree (DT), Random Forest (RF), and Adaptive Boosting (AdaBoost) perform better. Notably, N-AdaBoost models achieve outstanding results with 99.12% accuracy and 100% precision, highlighting the efficacy of NS in enhancing diagnostic reliability.