Development of an objective, standardized tool for surgical assessment of deceased donor kidneys: The Cambridge Kidney Assessment Tool

Abstract

Quality assessment in kidney transplantation involves inspection to identify negative markers of organ quality. However, there is a paucity of evidence guiding surgical appraisal, and currently there is no evidence to differentiate important features from those that can be safely ignored. We propose a method to standardize surgical assessment and derived a simple rule to rapidly identify kidneys suitable for transplantation. Donor and recipient data were recorded alongside clinical outcomes in a prospectively maintained database. We developed a proforma (Cambridge Kidney Assessment Tool, CKAT) and used it to assess deceased donor kidney transplants. Factors predictive of utilization were identified by multivariate and univariate logistic regression analysis of CKAT‐assessment scores, and test performance was evaluated using standard 2 × 2 contingency tables. Ninety‐seven kidneys were included at a single center (2013‐2014), and 184 CKAT assessments were performed. A CKAT threshold of “Carrell + Perfusion >3” was highly specific (99%) and performed favorably to consultant opinion (specificity 95%). 96% of the kidneys implanted in accordance with the rule survived to 1 year (mean eGFR 45.3 mL/min/1.73 m2). To our knowledge, this is the first attempt to objectively define macroscopic features that are relevant to kidney utilization. Common language could support training in organ assessment and ultimately help address unnecessary discard of donor kidneys.

Macroscopic assessment of the quality of cold perfusion after deceased‐donor kidney procurement: A United Kingdom population‐based cohort study

“…These results suggest that further work is required to refine the current grading scale. Recently, Ayorinde et al have developed a pre‐implantation, objective macroscopic scoring system (Cambridge Kidney Assessment Tool, CKAT) 14 . Of the variables included in their system, the quality of the Carrel patch and the perfusion grade were found to be independently associated with organ utilization.…”

“…Previous national registry studies have explored factors associated with retrieval damage of kidneys, but overlooked the effects of perfusion defects on organ utilization and outcomes 11,12 . Most transplant programs require the retrieving surgeon to comment on the QOP, 13 but it remains a poorly defined entity, with no validated categorization and/or quantification 14 . Studies have shown that considerable disagreement can exist in assessing QOP, even among experienced surgeons within the same center 15,16 .…”

Outcomes of Declined Deceased Donor Kidney Offers That Are Subsequently Implanted: A UK Registry Study

“…[44][45][46][47] More accurate risk-assessment and prediction tools are urgently needed to support better organ offer decision-making on an individual level. [48][49][50] Organ offering schemes need further refinements to better match deceased donor kidneys and potential recipients. In 2019, the United Kingdom changed its deceased donor kidney offering algorithm to more effectively "longevity match" organs and potential recipients.…”

Artificial Intelligence You Can Trust: What Matters Beyond Performance When Applying Artificial Intelligence to Renal Histopathology?

“…One area where AI may be particularly useful is in characterizing chronic injury in deceased donor kidneys that have been retrieved for transplantation. It is now widespread practice (up to 80% of retrieved kidneys in some US states) 16 to perform urgent preimplantation biopsy analysis of kidneys from elderly, “expanded criteria” deceased donors, in order to identify those kidneys that have no, or minimal, chronic injury, and that are therefore suitable for transplantation 14 , 17 – 23 . However, time and cost constraints, allied to a relative scarcity of specialist expertise, limit evaluation of preimplantation biopsies to a single slide.…”

“…Whichever approach is taken, ultimately the choice of which artery to score and how may remain ambiguous, and assessors could reasonably disagree. This has implications for determining the performance of the model against a perceived “gold standard.” Although this is not a problem limited to AI assessments, 22 regardless, AI models are expected to work well for all users, and designs that provide the highest quality insight into the decision-making process may therefore be favored. These should allow a human overseer to intuitively grasp and interact with model output.…”