Algorithm Based Tool to Determine First Distant Recurrence Pattern in Breast Cancer Patients after Curative Surgery

Abstract

In this paper fuzzy logic is used to predict first sight of distant relapse pattern in breast cancer patients after curative surgery with data. The overly expressed proteins, their structures and inhibitors are listed. Few of the proteins chosen are COX2, PgR, Nestin, SNAI 1, CK 5 and GATA3. Three primary sites of metastasis that is bone, brain and skin are chosen. The data elements are grouped into clusters and membership functions are thus obtained. A system of neurons, either artificial or organic in nature is trained with these relationship equations to estimate the first metastasis site. This network is tested for various available combinations of proteins. The table hence developed is defuzzified using lambda cut sets. These results are then compared to the ones obtained with the neuro fuzzy model.