International Journal of Neutrosophic Science IJNS 2690-6805 2692-6148 10.54216/IJNS https://www.americaspg.com/journals/show/1857 2020 2020 Docente de la carrera de Medicina de la Universidad Regional Autónoma de los Andes (UNIANDES Ambato), Ecuador Rosita Elizabeth O. Torres Docente de la carrera de Medicina de la Universidad Regional Autónoma de los Andes (UNIANDES Santo Domingo), Ecuador Jhonny Rodríguez Gutià Gutiérrez Docente de la carrera de Medicina de la Universidad Regional Autónoma de los Andes (UNIANDES Ambato), Ecuador Alex G. Lara Jacome Approximately one in eight women will get breast cancer in their lifetime. Because of the risks associated with radiation exposure, various women choose to avoid getting detected with breast cancer. Non-invasive breast cancer detection methods have limitations concerning the safety of radiation exposure and the accuracy with which tumors in the breast are diagnosed. Machine learning methods are commonly used to diagnose breast cancer. This paper applied three different machine learning methods like KNN, Naïve Bayes, and ID3. These methods are applied to the Wisconsin Breast Cancer dataset. In the process of categorization, data with unbalanced classes is problematic because methods are more probable to categorize fresh observations to the majority class since the likelihood of cases forming the plurality class is considerably high. So neutrosophic set is used to overcome the vague and uncertain data. This paper used single-valued neutrosophic numbers to evaluate the criteria. This paper used ROC and accuracy to evaluate the methods. The KNN has a 96.7%, Naïve Bayes has a 95.2%, and ID3 has a 95.3% accuracy. 2023 2023 162 173 10.54216/IJNS.210115 https://www.americaspg.com/articleinfo/21/show/1857