Application of Rough Sets to Predict the Breast Cancer Risk Association with Routine Blood Analyses

For women around the globe, breast cancer has been a significant cause of mortality. Around same time, early diagnosis and high prediction precision are critical to improving quality care recovery rate patient. Expert systems machine learning techniques gaining prominence in this area as result efficient classification diagnostic ability. This paper introduces model hybrid (RS QA) based on rough set theoryand quasi-optimal (AQ) rule induction algorithm. To find minimal attributes that completely define results, tool is used. The selected characteristics were collected, ensuring standard classification. Then produce decision rules, we use These models allow expert be built conceptual rules IF THEN sort. suggested experiment performed using Coimbra Breast Cancer Dataset (BCCD) sets measures can obtained routine blood tests. Using precision, sensitivity, specificity, receiver operating (ROC) curves, efficiency our approach was assessed. Experimental results indicate highest accuracy (91.7 percent), sensitivity (83.3 (94.3) by proposed (RS_QA) model.