Clinical and paraclinical factors selection for multiple myeloma diagnosis

Multiple myeloma (Kahler's disease) is a complex blood cancer that affects the plasma cells, which produce the antibodies to protect the human body. The diagnosis of multiple myeloma is difficult in the early stage and depends on several medical exams and tests in advanced stages, thus its process is very long and can discourage patients. In this study, the fast correlation-based filter (FCBF) method has been proposed to predict the clinical and paraclinical factors for multiple myeloma diagnosis. The obtained results by the proposed method are compared to the other filter-based feature selection algorithms, where the proposed FCBF method achieved the best performance.