Multi-Agent Based Diagnostic Model for Breast Tumour Classification
Yusuf Musa Malgwi, Gregory Maksha Wajiga, Etemi Joshua Garba · American Journal of Data Mining and Knowledge Discovery · 2019
Breast cancer is one of the most hazardous of all types of cancer affecting mainly women. It is the second leading cause of death in Nigerian women. It is difficult to classify breast tumour. The diagnosis of breast cancer on patients in hospitals and clinics is highly subjective and it is reliant on the physician’s expertise. This may often lead to incorrect diagnosis and long waiting time to diagnose breast tumour which may increase the possibility of Cancer metastasizing. This study focused on developing a multi-agent based model for diagnosis of breast tumours using the k-Nearest Neighbor (k-NN) algorithm by classifying the nature of the tumours based on their associated patterns of symptoms and other risk factors of Cancer diseases. A k-NN algorithm using Java and MYSQ was developed to extract and classify the symptoms associated with Breast Cancer. Java Agent Development Environment (JADE) was used for the modeling and simulation. The accuracy score was tested on a breast tumour clinical datasets which were gotten and formed from Federal Medical Centers (FMC) Yola and Gombe in Nigeria. The experimental result of the prediction model shows a percentage accuracy score of 98.9%.