Broad Learning with Attribute Selection for Rheumatoid Arthritis

Rheumatoid arthritis (RA) patients have osteoarticular deformation in the early stage, and suffer worse from joint deformity and even loss of function in the later stage. Accurate evaluation of the patient’s physical condition is of importance as it would significantly help to decide appropriate care, medications or medical interventions needed. Thus, a fast and efficient risk factor selection algorithm demonstrates a clinical significance for the more precise diagnosis, and an accurate prediction model will hopefully be able to improve current treatment. In this paper, we designed a novel and universal architecture, broad learning attribute selection system (BLAS), to deal with the risk factor diagnosis and disease performance prediction on RA patients. The attribute selection based on rough set and entropy can identify significant risk factors affecting RA and broad learning possesses the ability of randomly generating nodes to investigate the desired connection weights simultaneously without the need for deep architecture. Experiments on clinical RA patients’ dataset demonstrated that our proposed BLAS model achieved the highest average accuracy of 99.67% with mean absolute error of 0.32%, compared with the state-of-the-art methods. The results proved the robust classification ability of BLAS in RA risk factors assessment and prediction.