Optimizing explainability of Breast Cancer Recurrence using FuzzyGenetic

Abstract

Breast cancer is the most common cancer diagnosed in the world, being the cause of death of 685,000 people worldwide in 2020. Due to the aggressiveness of the disease, early-stage identification, treatment, and remission detection are important to ensure longevity to those who may have cancer. In this paper, we propose a fuzzy-genetic approach for breast cancer recurrence classification. To this end, we use a Genetic Algorithm to design automatically the fuzzy inference system with the objective of balancing between accuracy and explainability. The proposed system achieved an accuracy of 91.30%, finding eleven rules with a maximum of three antecedents per rule, which provided a competitive result compared to other Machine Learning approaches.