EUVIMEDObjevte EUVIMED
Crossref

Re‐assessing prolonged cold ischemia time in kidney transplantation through machine learning consensus clustering

Caroline C Jadlowiec iD, Charat Thongprayoon iD, Supawit Tangpanithandee iD, Rachana Punukollu iD, Napat Leeaphorn iD, Matthew Cooper iD, Wisit Cheungpasitporn iD

Clinical Transplantation · 2024

DOI: 10.1111/ctr.15201 ↗

At a glance

Journal article in Clinical Transplantation, 2024. Written by Caroline C Jadlowiec and 6 co-authors. Institution: Division of Transplant Surgery, Mayo Clinic, Phoenix, Arizona, USA. Major MEDLINE topics: Kidney Transplantation. Cited 7 times so far (Crossref); 28 references.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

We aimed to cluster deceased donor kidney transplant recipients with prolonged cold ischemia time (CIT) using an unsupervised machine learning approach.

Methods

We performed consensus cluster analysis on 11 615 deceased donor kidney transplant patients with CIT exceeding 24 h using OPTN/UNOS data from 2015 to 2019. Cluster characteristics of clinical significance were identified, and post‐transplant outcomes were compared.

Results

Consensus cluster analysis identified two clinically distinct clusters. Cluster 1 was characterized by young, non‐diabetic patients who received kidney transplants from young, non‐hypertensive, non‐ECD deceased donors with lower KDPI scores. In contrast, the patients in cluster 2 were older and more likely to have diabetes. Cluster 2 recipients were more likely to receive transplants from older donors with a higher KDPI. There was lower use of machine perfusion in Cluster 1 and incrementally longer CIT in Cluster 2. Cluster 2 had a higher incidence of delayed graft function (42% vs. 29%), and lower 1‐year patient (95% vs. 98%) and death‐censored (95% vs. 97%) graft survival compared to Cluster 1.

Conclusions

Unsupervised machine learning characterized deceased donor kidney transplant recipients with prolonged CIT into two clusters with differing outcomes. Although Cluster 1 had more favorable recipient and donor characteristics and better survival, the outcomes observed in Cluster 2 were also satisfactory. Overall, both clusters demonstrated good survival suggesting opportunities for transplant centers to incrementally increase CIT.

Subjects

MeSH terms (MEDLINE)

Kidney TransplantationHumansDelayed Graft FunctionGraft RejectionCold IschemiaConsensusGraft SurvivalTissue DonorsCluster AnalysisMachine Learning

Author keywords

artificial intelligenceclusteringcold ischemia timekidney transplantmachine learningoutcomepost-transplantation outcome

Authors and institutions

  • Division of Transplant Surgery, Mayo Clinic, Phoenix, Arizona, USA.
  • Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, Minnesota, USA.
  • Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Jacksonville, Florida, USA.
  • Division of Transplant Surgery, Medical College of Wisconsin, Milwaukee, Wisconsin, USA.

ORCID profiles: Caroline C Jadlowiec, Charat Thongprayoon, Supawit Tangpanithandee, Rachana Punukollu, Napat Leeaphorn, Matthew Cooper, Wisit Cheungpasitporn

Cite

APA

Jadlowiec, C. C., Thongprayoon, C., Tangpanithandee, S., Punukollu, R., Leeaphorn, N., Cooper, M., & Cheungpasitporn, W. (2024). Re‐assessing prolonged cold ischemia time in kidney transplantation through machine learning consensus clustering. Clinical Transplantation. https://doi.org/10.1111/ctr.15201

Vancouver

Jadlowiec CC, Thongprayoon C, Tangpanithandee S, Punukollu R, Leeaphorn N, Cooper M, et al. Re‐assessing prolonged cold ischemia time in kidney transplantation through machine learning consensus clustering. Clinical Transplantation. 2024. doi:10.1111/ctr.15201

BibTeX
@article{Jadlowiec2024,
  author = {Jadlowiec, Caroline C and Thongprayoon, Charat and Tangpanithandee, Supawit and Punukollu, Rachana and Leeaphorn, Napat and Cooper, Matthew and Cheungpasitporn, Wisit},
  title = {Re‐assessing prolonged cold ischemia time in kidney transplantation through machine learning consensus clustering},
  journal = {Clinical Transplantation},
  year = {2024},
  doi = {10.1111/ctr.15201}
}
Start for free →