A Multi-step precision pathway for predicting allograft survival in heterogeneous cohorts of kidney transplant recipients

Yunwei Zhang, Danny Deng, Samuel Muller, Germaine Wong, Jean Yee Hwa Yang

Research output: Contribution to journalArticlepeer-review

7 Downloads (Pure)


Accurate prediction of allograft survival after kidney transplantation allows early identification of at-risk recipients for adverse outcomes and initiation of preventive interventions to optimize post-transplant care. Many prediction algorithms do not model cohort heterogeneity and may lead to inaccurate assessment of longer-term graft outcomes among minority groups. Using data from a national Australian kidney transplant cohort (2008–2017) as the derivation set, we developed P-Cube, a multi-step precision prediction pathway model for predicting overall graft survival in three ethnic subgroups: European Australians, Asian Australians and Aboriginal and Torres Strait Islander Peoples. The concordance index for the European Australians, Asian Australians, and Aboriginal and Torres Strait Islander Peoples subpopulations were 0.99 (0.98–0.99), 0.93 (0.92–0.94) and 0.92 (0.91–0.93), respectively. Similar findings were observed when validating P-cube using an external dataset [Scientific Registry of Transplant Recipient Registry (2006–2020)]. Six sub-categories of recipients with distinct risk factor profiles were identified. Some factors such as blood group compatibility were considered important across the entire transplant population. Other factors such as human leukocyte antigen (HLA)-DR mismatches were unique to older recipients. The P-cube model identifies allograft survival specific risk factors within a heterogenous population and offers personalized survival predictions in a diverse cohort.

Original languageEnglish
Article number11338
Pages (from-to)1-8
Number of pages8
JournalTransplant International
Issue number9
Publication statusPublished - Sept 2023

Bibliographical note

© 2023 Zhang, Deng, Muller, Wong and Yang. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.


  • allograft survival prediction
  • kidney transplantation
  • kidney transplantation graft survival
  • prediction model


Dive into the research topics of 'A Multi-step precision pathway for predicting allograft survival in heterogeneous cohorts of kidney transplant recipients'. Together they form a unique fingerprint.

Cite this