Dueto the sparsity and separation and a large amount of calculations in high-order interactions, Logistic regression is not
 accurate enough to detect the main and interaction effects between genetic markers at very high orders. The multifactorial
 dimension reduction algorithm is considered a powerful algorithm for identifying high-order interactions in high dimensional
 structures. In this study, information of 748 patients with Behcet’s disease who were referred to the Rheumatology Research
 Center, Shariati Hospital, Tehran, and 776 healthy controls were used to identify the interaction effects between ERAP1 gene
 polymorphisms involved in the occurrence of Behcet’s disease using the multifactor dimensionality reduction algorithm.
 Data analysis was performed using MDR 3.0.2 software. The models obtained from the multifactorial dimensional reduction
 algorithm with balanced accuracy above 0.6 have been determined to increase the risk of Behcet’s disease. The multi-factor
 reduction algorithm has high power and speed in calculating the interaction effects of polymorphisms or genetic mutations
 and identifying important interactions.