Development and Validation of a Virtual Biopsy System in Kidney Transplant

Kidney Transplantation

Kidney transplantation, Day-zero biopsy, Machine learning, Non-invasive biopsy, Common parameters

Currently, kidney allograft biopsies are routinely performed to determine diagnosis and prognosis of kidney allografts. The histological interpretation of these biopsies is based on the Banff consensus for renal allograft pathology. The purpose of this study is to provide to the physicians a reliable estimation of renal allograft lesions of the day zero biopsy (kidney donor biopsy performed before transplantation).

In kidney transplantation, day-zero biopsies are essential to assess organ quality and discriminate the donor transmitted or acquired lesions and disease progression post-transplant. However, many centers worldwide do not perform those biopsies because they are invasive and costly. We aimed to develop and validate a non-invasive virtual biopsy system. Our goal was to provide clinicians with a virtual biopsy system to guide diagnostics, therapeutics and immediate patient management post-transplant and to minimize additional risks and costs to perform day-zero biopsies only using standard donor parameters. To circumvent these limitations, we sought to build and validate a virtual biopsy system that uses routinely collected donor parameters to predict kidney day-zero biopsy results. Since machine learning has demonstrated its clinical relevance in many medical specialties and superior performance to logistic regression, we based our analyses on machine learning methods as well as traditional statistical approaches using large and qualified international cohort donors who underwent routine and protocolized collection of donor parameters together with day-zero biopsy assessment using the standards of the international Banff allograft histopathology classification.

No related papers found yet.

France