NEURO-FUZZY EXPERT SYSTEM FOR DIAGNOSIS OF BREAST CANCER WITH GINI INDEX RANDOM FOREST-BASED FEATURE IMPORTANCE MEASURE ALGORITHM

Abstract

Breast cancer is one of the common type cancers and also one of deadliest cancers after lung cancer. The cancer is the most common cancer in women worldwide, in Nigeria, with population of about 187 million people and it represents about 12% of all new cancer cases and 25% of all cancers in women. However, conventional clinical diagnosis process of diseases is often associated with uncertainty and ambiguity due to complexity and fuzziness in the course of diagnosis of most of the deadly diseases such as COVID-19, Coronary artery diseases, breast cancer, diabetes mellitus among other. Therefore, artificial techniques such as fuzzy logic, and neural network can be used to deal with the uncertainty and ambiguity of the diverse nature of clinical and medical diagnosis or decision making. In this work, a hybrid AI intelligent expert system based on neural network and fuzzy logic artificial intelligence techniques for diagnosis of breast cancer has developed so as to provide a promising solution of how to deal uncertainty and vagueness often associated with the clinical and decision making in the course of diagnosis of breast cancer and also to assist the healthcare workers in diagnosing and predicting breast cancer in its early stage. the result of the performance evaluation of the system showed that the system achieved an accuracy of 96.77% for its ability to accurately diagnose healthy, mild and severe breast cancer patients, and system achieved a sensitivity of 96.77% and a specificity of 97.10% respectively for its ability to correct diagnose health cases of the breast cancer.