Abstract: End-stage renal disease has become one of the important public health problems due to its long-term and incurable nature. Maintenance hemodialysis is the most effective renal replacement therapy for patients with end-stage renal disease, and arteriovenous fistula (AVF) is the frequently used blood access for hemodialysis. However, maturation of newly established AVF and maintenance of AVF patency are two critical obstacles required to be solved. Recently, artificial intelligence (AI) has been successfully used in the field of dialysis. AI provides a novel alternative for the management of AVF. This article reviews recent advances in the application of AI for management of AVF dealing with six aspects: decision-making of AVF site, postoperative maturity prediction, functional monitoring, acoustic feature monitoring, thrombosis and stenosis prediction, and aneurysm grading, aiming to provide references for the application of AI for management of AVF in maintenance hemodialysis patients.

Key words: Artificial intelligence, Maintenance hemodialysis, Arteriovenous fistula, Machine learning