Artificial Intelligence-based Prediction of Radio-cephalic Arteriovenous Fistula Maturation Using Preoperative Duplex Examination

Seoul National University

Status: Completed

Conditions: Machine Learning; Arteriovenous Fistula; Artificial Intelligence (AI); Renal Insufficiency, Chronic

Treatments: Procedure: Arteriovenous fistula

Study type: Observational

Funder types: Other

Identifiers

NCT06600750

S2020-3118-0001

Details and patient eligibility

About

The goal of this observational study is to assess the efficacy of AI-driven models in analyzing comprehensive ultrasonographic variables across multiple forearm locations to predict successful AVF maturation. The main question it aims to answer is:

Can AI-driven models analyzing comprehensive ultrasonographic variables accurately predict the successful maturation of arteriovenous fistulas (AVFs)?

Participants who underwent radiocephalic arteriovenous fistula (AVF) creation had their preoperative ultrasonographic data analyzed using AI-driven models to predict successful AVF maturation over a four-year retrospective period.

Enrollment: 494 patients

Sex: All

Volunteers: No Healthy Volunteers

Inclusion criteria

• patients who underwent RCAVF due to advanced chronic kidney disease from 2018 to 2022

Exclusion criteria

• Patients who did not have follow-up data available

Trial design

494 participants in 1 patient group

Patients who underwent radiocephalic arteriovenous fistula due to advanced chronic kidney disease

Description:

Patients who underwent radiocephalic arteriovenous fistula due to advanced chronic kidney disease

Treatment:

Procedure: Arteriovenous fistula