AUTHOR=Jadlowiec Caroline C. , Thongprayoon Charat , Leeaphorn Napat , Kaewput Wisit , Pattharanitima Pattharawin , Cooper Matthew , Cheungpasitporn Wisit 

TITLE=Use of Machine Learning Consensus Clustering to Identify Distinct Subtypes of Kidney Transplant Recipients With DGF and Associated Outcomes

JOURNAL=Transplant International

VOLUME=Volume 35 - 2022

YEAR=2022

URL=https://www.frontierspartnerships.org/journals/transplant-international/articles/10.3389/ti.2022.10810

DOI=10.3389/ti.2022.10810

ISSN=1432-2277

ABSTRACT=Data on delayed graft function (DGF), and its impact on outcomes, remains varied. An unsupervised machine learning (ML) consensus clustering approach was applied to categorize the clinical phenotypes of kidney transplant (KT) recipients with DGF and their paired donors using OPTN/UNOS data from 2015 to 2019. DGF was observed in 20.9% (n=17,073) of KT. Most kidneys came from donors, with a KDPI score <85%. Four clinically distinct clusters were identified. Cluster 1 recipients were young, high PRA re-transplants. Cluster 2 recipients were older diabetics who were more likely to receive higher KDPI kidneys. Cluster 3 recipients were young, black, and non-diabetic; they received lower KDPI kidneys. Cluster 4 recipients were middle-aged, had diabetes or hypertension and received well-matched standard KDPI kidneys. By cluster, one-year patient survival was 95.7%, 92.5%, 97.2% and 94.3% (p<0.001); one-year graft survival was 89.7%, 87.1%, 91.6%, and 88.7% (p<0.001). There were no differences between clusters when accounting for death-censored graft loss (p=0.08). Application of unsupervised ML resulted in the identification of four clinically distinct DGF clusters. The majority of kidneys utilized in the United States continue to come from standard KDPI donors. Despite cluster-specific differences in graft survival, there were no differences in death-censored graft loss. This finding underscores room to expand use of high KDPI kidneys, particularly for recipients within clusters 2 and 4. Greater emphasis on recipient comorbidities and donor-recipient pairing, rather than donor characteristics, as contributors to DGF, may help improve utilization for DGF at-risk kidneys