Distinct Phenotypes of Kidney Transplant Recipients Aged 80 Years or Older in the United States by Machine Learning Consensus Clustering

S. A. Mao¹, C. Thongprayoon², M. A. Mao³, C. C. Jadlowiec⁴, N. Leeaphorn⁵, M. Cooper⁶, W. Cheungpasitporn²

¹Transplant Surgery, Mayo Clinic, Jacksonville, FL, ²Nephrology and Hypertension, Mayo Clinic, Rochester, MN, ³Nephrology and Hypertension, Mayo Clinic, Jacksonville, FL, ⁴Transplant Surgery, Mayo Clinic, Phoenix, AZ, ⁵Renal Transplant Program, University of Missouri-Kansas City School of Medicine/Saint Luke's Health System, Kansas City, MO, ⁶MedStar Georgetown Transplant Institute, Georgetown University School of Medicine, Washington, DC

Meeting: 2022 American Transplant Congress

Abstract number: 1794

Keywords: Graft survival, Organ Selection/Allocation, Outcome, Prediction models

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: Our study aimed to cluster very elderly kidney transplant recipients aged 80 years and above using an unsupervised machine learning approach.

*Methods: We performed consensus cluster analysis based on recipient-, donor-, and transplant-related characteristics in 419 very elderly (age ≥80 at time of transplant) kidney transplant recipients in the OPTN/UNOS database from 2010 to 2019. We identified each cluster’s key characteristics using the standardized mean difference. We compared posttransplant outcomes including death-censored graft failure, overall mortality, and acute allograft rejection among the assigned clusters.

*Results: Consensus cluster analysis identified three distinct clusters that best represented the clinical characteristics of very elderly kidney transplant recipients. Recipients in cluster 1 received standard KDPI kidneys from deceased donors. Recipients in cluster 2 received kidneys from older, hypertensive deceased donors with a KDPI score ≥85%. Kidneys for cluster 2 patients had longer cold ischemia time and the highest use of machine perfusion. Recipients in cluster 3 were preemptive or had a dialysis duration less than 1 year. These recipients received living donor kidney transplants. Cluster 3 had the most favorable posttransplant outcomes. Compared to cluster 3, cluster 1 had comparable survival but higher death-censored graft failure, while cluster 2 had lower patient survival, higher death-censored graft failure, and more acute rejection (see figure).

*Conclusions: Our study utilized an unsupervised machine learning approach to cluster very elderly kidney transplant recipients based on their clinical characteristics into three clinically unique clusters with distinct posttransplant outcomes.

To cite this abstract in AMA style:

Mao SA, Thongprayoon C, Mao MA, Jadlowiec CC, Leeaphorn N, Cooper M, Cheungpasitporn W. Distinct Phenotypes of Kidney Transplant Recipients Aged 80 Years or Older in the United States by Machine Learning Consensus Clustering [abstract]. Am J Transplant. 2022; 22 (suppl 3). https://atcmeetingabstracts.com/abstract/distinct-phenotypes-of-kidney-transplant-recipients-aged-80-years-or-older-in-the-united-states-by-machine-learning-consensus-clustering/. Accessed May 9, 2025.

« Back to 2022 American Transplant Congress