Advanced Machine Learning Approaches for Breast Cancer Detection with Neutrosophic Sets

Abstract

 Breast Cancer (BC) remains a significant health challenge for women and is 
one of the leading causes of mortality worldwide. Accurate diagnosis is critical for 
successful therapy and increased survival rates. Recent advances in medical imaging and 
computational technologies have enabled more precise methods of detecting and 
evaluating breast cancer. Accurate analysis and diagnosis utilizing medical imaging have 
developed as essential research topics, providing important help in clinical decision
making for various illnesses, including breast cancer. Machine learning (ML) can 
accurately predict breast cancer. But the breast cancer data has vague and uncertainty 
information. So, the neutrosophic sets (NSs) are used in this study to deal with 
uncertainty data. We convert the original dataset into neutrosophic data with three 
components such as truth, indeterminacy, and falsity values. Then we applied four ML 
models with N-data such as logistic regression, gradient boosting (GB), k-nearest 
neighbor (KNN), and support vector machines (SVM), to improve diagnostic accuracy. 
Then we compared the ML models with and without using N-data. The results show the 
logistic regression has higher accuracy with 98.6% with the N-data and 95.80% without 
N-data. So, the NSs can improve the accuracy of ML models. 

DOI: 10.5281/zenodo.14827225