A Machine Learning-Driven Virtual Biopsy System For Kidney Transplant Patients

Daniel Yoo, Gillian Divard, Marc Raynaud, Aaron Cohen, Tom D. Mone, John Thomas Rosenthal, Andrew J. Bentall, Mark D. Stegall, Maarten Naesens, Huanxi Zhang, Changxi Wang, Juliette Gueguen, Nassim Kamar, Antoine Bouquegneau, Ibrahim Batal, Shana M. Coley, John S. Gill, Federico Oppenheimer, Erika De Sousa-Amorim, Dirk R. J. Kuypers, Antoine Durrbach, Daniel Seron, Marion Rabant, Jean-Paul Duong Van Huyen, Patricia Campbell, Soroush Shojai, Michael Mengel, Oriol Bestard, Nikolina Basic-Jukic, Ivana Jurić, Peter Boor, Lynn D. Cornell, Mariam P. Alexander, P. Toby Coates, Christophe Legendre, Peter P. Reese, Carmen Lefaucheur, Olivier Aubert and Alexandre Loupy ()
Additional contact information
Daniel Yoo: Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration
Gillian Divard: Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration
Marc Raynaud: Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration
Aaron Cohen: OneLegacy
Tom D. Mone: OneLegacy
John Thomas Rosenthal: David Geffen School of Medicine at UCLA
Andrew J. Bentall: Mayo Clinic Transplant Center
Mark D. Stegall: Department of Surgery, Mayo Clinic
Maarten Naesens: Immunology and Transplantation, KU Leuven
Huanxi Zhang: Sun Yat-sen University, Guangzhou
Changxi Wang: Sun Yat-sen University, Guangzhou
Juliette Gueguen: Néphrologie-Immunologie Clinique, Hôpital Bretonneau, CHU Tours
Nassim Kamar: Paul Sabatier University, INSERM
Antoine Bouquegneau: Centre hospitalier universitaire de Liège
Ibrahim Batal: Columbia University Medical Center
Shana M. Coley: Columbia University Medical Center
John S. Gill: University of British Columbia
Federico Oppenheimer: Hospital Clínic i Provincial de Barcelona
Erika De Sousa-Amorim: Hospital Clínic i Provincial de Barcelona
Dirk R. J. Kuypers: Immunology and Transplantation, KU Leuven
Antoine Durrbach: AP-HP Hôpital Henri Mondor
Daniel Seron: Autonomous University of Barcelona
Marion Rabant: Assistance Publique - Hôpitaux de Paris
Jean-Paul Duong Van Huyen: Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration
Patricia Campbell: University of Alberta
Soroush Shojai: University of Alberta
Michael Mengel: University of Alberta
Oriol Bestard: Autonomous University of Barcelona
Nikolina Basic-Jukic: University Hospital Centre Zagreb
Ivana Jurić: University Hospital Centre Zagreb
Peter Boor: RWTH Aachen University Hospital
Lynn D. Cornell: Mayo Clinic
Mariam P. Alexander: Mayo Clinic
P. Toby Coates: University of Adelaide, Royal Adelaide Hospital Campus
Christophe Legendre: Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration
Peter P. Reese: Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration
Carmen Lefaucheur: Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration
Olivier Aubert: Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration
Alexandre Loupy: Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration

Nature Communications, 2024, vol. 15, issue 1, 1-12

Abstract: Abstract In kidney transplantation, day-zero biopsies are used to assess organ quality and discriminate between donor-inherited lesions and those acquired post-transplantation. However, many centers do not perform such biopsies since they are invasive, costly and may delay the transplant procedure. We aim to generate a non-invasive virtual biopsy system using routinely collected donor parameters. Using 14,032 day-zero kidney biopsies from 17 international centers, we develop a virtual biopsy system. 11 basic donor parameters are used to predict four Banff kidney lesions: arteriosclerosis, arteriolar hyalinosis, interstitial fibrosis and tubular atrophy, and the percentage of renal sclerotic glomeruli. Six machine learning models are aggregated into an ensemble model. The virtual biopsy system shows good performance in the internal and external validation sets. We confirm the generalizability of the system in various scenarios. This system could assist physicians in assessing organ quality, optimizing allograft allocation together with discriminating between donor derived and acquired lesions post-transplantation.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.nature.com/articles/s41467-023-44595-z Abstract (text/html)

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:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-023-44595-z

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-023-44595-z

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().