Université Paris Cité, INSERM U970 PARCC, Paris Institute for Transplantation and Organ Regeneration, F-75015, Paris, France.
Kidney Transplant Department, Saint-Louis Hospital, Assistance Publique - Hôpitaux de Paris, Paris, France.
Nat Commun. 2024 Jan 16;15(1):554. doi: 10.1038/s41467-023-44595-z.
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.
在肾移植中，使用零天活检来评估器官质量，并区分供体遗传病变和移植后获得的病变。然而，许多中心不进行此类活检，因为它们具有侵入性、昂贵，并且可能会延迟移植手术。我们旨在使用常规收集的供体参数生成一种非侵入性的虚拟活检系统。通过使用来自 17 个国际中心的 14,032 份零天肾脏活检，我们开发了一种虚拟活检系统。使用 11 个基本供体参数来预测四种 Banff 肾脏病变：动脉硬化、小动脉玻璃样变性、间质纤维化和肾小管萎缩以及肾小球硬化的百分比。将 6 个机器学习模型聚合到一个集成模型中。虚拟活检系统在内部和外部验证集中表现出良好的性能。我们在各种情况下确认了系统的可泛化性。该系统可以帮助医生评估器官质量，与移植后获得的病变一起优化同种异体移植的分配。
