A Method Based on Process Mining for Breast Cancer Diagnosis with Whale Optimization Algorithm and Support Vector Machine

Abstract

ABSTRACT Breast cancer is the second most common cancer among women and the second leading cause of death in the world. According to the statistics of the National Cancer Center, one out of every eight women in the United States is diagnosed with breast cancer. This cancer is the most common malignancy among Iranian women and the main focus of attention in Iran. The data shows that in recent years, the prevalence of the disease has been growing. All tumors are not cancerous and may be benign or malignant. Benign tumors grow abnormally but are rarely fatal. However, some benign breast masses can also increase the risk of breast cancer. The process mining is one of the methods used to diagnose or predict cancers. This method is one of the most popular approaches to breast cancer diagnosis. Process mining approaches can help doctors in better detection of breast cancer by reducing the number of false positive and negative results. The whale optimization algorithm is one of the new meta-heuristic algorithms and imitates the behavior of whale hunting. This algorithm starts with a set of random solutions, in each iteration the search agents update their position according to each of the search agents randomly or with the best solution obtained so far. In this research, using the whale algorithm method, a method to reduce cancer diagnosis error in a number of patients with 9 types of contamination has been investigated and presented. Therefore, in this research, with the help of MATLAB software and using the advantages of whale algorithm optimization, this number of diseases has been categorized, as a result of which the diagnosis error is reduced.