The residual stenosis estimation of an arterio-venous shunt(AVS)is a valuable for evaluating outcomes of percutaneous transluminal angioplasty(PTA)treatment and surgical revision.This study proposes a fractional order feature based classifier to estimate the residual stenosis in arteriovenous shunts.The auscultation method provides a non-invasive technique to record phonoangiography signals.The Burg autoregressive method and fractional-order self-synchronization error formulation are then used to extract the characteristic features between the loop site(L-site)and venous anastomosis site(V-site).In order to estimate the vascular lumen,a generalized regression neural network(GRNN)is designed as a classifier to estimate residual stenosis.For 42 long-term follow-up patients,the results of examination show the proposed classifier efficiently estimates residual stenosis.