Comparative analysis of outcomes in high KDPI spectrum kidney transplants using unsupervised machine learning algorithm

Mahmoudreza Moein, Alireza Golkarieh, Isabella Vlassis, Reza Saidi and Michael Lioudis

PLOS ONE, 2025, vol. 20, issue 8, 1-16

Abstract: Background: The Kidney Donor Profile Index (KDPI) is a continuous metric used to estimate the risk of allograft failure for kidneys from deceased donors. Lower KDPI scores are associated with longer post-transplant kidney function. This study aims to evaluate the outcomes of kidney transplantation using high-KDPI kidneys (98–100%) compared to those with moderately high KDPI scores (85–97%), employing a novel case-matching approach using machine learning. Methods: We conducted a retrospective analysis of the United Network for Organ Sharing (UNOS) database, examining kidney transplants performed in the United States between January 2000 and May 2020. An unsupervised machine learning algorithm was used to match recipients of KDPI 98–100% kidneys with recipients of KDPI 85–97% kidneys based on key baseline characteristics, including recipient age, body mass index (BMI), cold ischemia time, HLA mismatch, ethnicity, and gender. Results: A total of 6,624 matched cases were selected for analysis. The mean follow-up duration was 4.5 years for the KDPI 98–100% cohort and 4.6 years for the KDPI 85–97% cohort. The five-year allograft survival was 51.7% for the KDPI 98–100% group versus 58% for the KDPI 85–97% group (P

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0324265 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 24265&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0324265

DOI: 10.1371/journal.pone.0324265

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().