ATC Abstracts

American Transplant Congress abstracts

  • Home
  • Meetings Archive
    • 2022 American Transplant Congress
    • 2021 American Transplant Congress
    • 2020 American Transplant Congress
    • 2019 American Transplant Congress
    • 2018 American Transplant Congress
    • 2017 American Transplant Congress
    • 2016 American Transplant Congress
    • 2015 American Transplant Congress
    • 2013 American Transplant Congress
  • Keyword Index
  • Resources
    • 2021 Resources
    • 2016 Resources
      • 2016 Welcome Letter
      • ATC 2016 Program Planning Committees
      • ASTS Council 2015-2016
      • AST Board of Directors 2015-2016
    • 2015 Resources
      • 2015 Welcome Letter
      • ATC 2015 Program Planning Committees
      • ASTS Council 2014-2015
      • AST Board of Directors 2014-2015
      • 2015 Conference Schedule
  • Search

Distinct Phenotypes of Kidney Transplant Recipients with Delayed Graft Function Identified Through Machine Learning Consensus Clustering

C. Jadlowiec1, C. Thongprayoon2, N. Leeaphorn3, W. Kaewput4, P. Pattharanitima5, M. Cooper6, W. Cheungpasitporn2

1Division of Transplant Surgery, Mayo Clinic Arizona, Phoenix, AZ, 2Division of Nephrology and Hypertension, Mayo Clinic Rochester, Rochester, MN, 3Renal Transplant Program, University of Missouri-Kansas City School of Medicine/Saint Luke's Health System, Kansas City, MO, 4Department of Military and Community Medicine, Phramongkutklao College of Medicine, Bangkok, Thailand, 5Department of Internal Medicine, Thammasat University, Pathum Thani, Thailand, 6Medstar Georgetown Transplant Institute, Georgetown University School of Medicine, Washington, DC

Meeting: 2022 American Transplant Congress

Abstract number: 1800

Keywords: Donation, Donors, marginal, Graft survival, Kidney transplantation

Topic: Clinical Science » Organ Inclusive » 72 - Machine Learning, Artificial Intelligence and Social Media in Transplantation

Session Information

Session Name: Machine Learning, Artificial Intelligence and Social Media in Transplantation

Session Type: Poster Abstract

Date: Tuesday, June 7, 2022

Session Time: 7:00pm-8:00pm

 Presentation Time: 7:00pm-8:00pm

Location: Hynes Halls C & D

*Purpose: The significance of delayed graft function (DGF) and its impact on kidney transplant (KT) outcomes remains debated. We aimed to assess outcomes for KT recipients with DGF using an unsupervised machine learning (ML) approach.

*Methods: The OPTN/UNOS database was used to perform consensus cluster analysis on recipient-, donor-, and transplant-related characteristics in KT recipients with DGF. We identified each cluster’s key characteristics using the standardized mean difference of >0.3.

*Results: There were 17,073 KT recipients with DGF; 96% received a deceased donor KT. Most KT came from locally allocated, non-extended criterion donor (ECD), standard kidney donor profile index (KDPI<85%) donors with lower cold ischemia times (CIT). Cluster analysis identified 4 distinct clusters of KT recipients with DGF. Cluster 1 recipients were young high PRA re-transplants. They received HLA matched standard KDPI kidneys. Cluster 2 included older black diabetic low PRA first-time KT recipients. They were likely to receive high KDPI kidneys from older, hypertensive ECD donors with longer CIT. Cluster 3 recipients were likely to be young black non-diabetic first-time KT recipients who received standard KDPI kidneys from young, non-hypertensive non-ECD donors. Cluster 4 recipients were older white diabetic first-time KT recipients who received standard KDPI kidneys. For clusters 1, 2, 3 and 4, 1-year patient survival was: 95.7%, 92.5%, 97.2%, 94.3% (p<0.001); 1-year death-censored graft survival was: 92.7%, 92.5%, 93.7%, 92.9% (p=0.08). Patient survival was highest in cluster 3 and lowest in cluster 2. One-year rejection was highest in clusters 1 (10.2%) and 3 (7.0%) and lowest in cluster 4 (3.8%). All clusters were evenly distributed over all of UNOS regions.

*Conclusions: Despite varying recipient-, donor-, and transplant-related characteristics, there were no differences in death-censored graft survival between clusters. Clinical outcomes specific to DGF have historically been described in a binary fashion, however factors contributing to DGF are complex and varied. Recipient factors, independent of DGF, play a more significant role in post-transplant outcomes. These findings from a ML clustering approach provide additional understanding towards individualized medicine and opportunities to improve utilization of kidneys at risk for DGF.

  • Tweet
  • Click to email a link to a friend (Opens in new window) Email
  • Click to print (Opens in new window) Print

To cite this abstract in AMA style:

Jadlowiec C, Thongprayoon C, Leeaphorn N, Kaewput W, Pattharanitima P, Cooper M, Cheungpasitporn W. Distinct Phenotypes of Kidney Transplant Recipients with Delayed Graft Function Identified Through Machine Learning Consensus Clustering [abstract]. Am J Transplant. 2022; 22 (suppl 3). https://atcmeetingabstracts.com/abstract/distinct-phenotypes-of-kidney-transplant-recipients-with-delayed-graft-function-identified-through-machine-learning-consensus-clustering/. Accessed May 30, 2025.

« Back to 2022 American Transplant Congress

Visit Our Partner Sites

American Transplant Congress (ATC)

Visit the official site for the American Transplant Congress »

American Journal of Transplantation

The official publication for the American Society of Transplantation (AST) and the American Society of Transplant Surgeons (ASTS) »

American Society of Transplantation (AST)

An organization of more than 3000 professionals dedicated to advancing the field of transplantation. »

American Society of Transplant Surgeons (ASTS)

The society represents approximately 1,800 professionals dedicated to excellence in transplantation surgery. »

Copyright © 2013-2025 by American Society of Transplantation and the American Society of Transplant Surgeons. All rights reserved.

Privacy Policy | Terms of Use | Cookie Preferences