Prospective Validation of Prediction Model for Kidney Discard

Rescue Allocation Modes in Eurotransplant Kidney Transplantation: Recipient Oriented Extended Allocation Versus Competitive Rescue Allocation-A Retrospective Multicenter Outcome Analysis

BACKGROUND

Whenever the kidney standard allocation (SA) algorithms according to the Eurotransplant (ET) Kidney Allocation System or the Eurotransplant Senior Program fail, rescue allocation (RA) is initiated. There are 2 procedurally different modes of RA: recipient oriented extended allocation (REAL) and competitive rescue allocation (CRA). The objective of this study was to evaluate the association of patient survival and graft failure with RA mode and whether or not it varied across the different ET countries.

METHODS

The ET database was retrospectively analyzed for donor and recipient clinical and demographic characteristics in association with graft outcomes of deceased donor renal transplantation (DDRT) across all ET countries and centers from 2014 to 2021 using Cox proportional hazards methods.

RESULTS

Seventeen thousand six hundred seventy-nine renal transplantations were included (SA 15 658 [89%], REAL 860 [4.9%], and CRA 1161 [6.6%]). In CRA, donors were older, cold ischemia times were longer, and HLA matches were worse in comparison with REAL and especially SA. Multivariable analyses showed comparable graft and recipient survival between SA and REAL; however, CRA was associated with shorter graft survival. Germany performed 76% of all DDRTs after REAL and CRA and the latter mode reduced waiting times by up to 2.9 y.

CONCLUSIONS

REAL and CRA are used differently in the ET countries according to national donor rates. Both RA schemes optimize graft utilization, lead to acceptable outcomes, and help to stabilize national DDRT programs, especially in Germany.

Prediction of High-Risk Donors for Kidney Discard and Nonrecovery Using Structured Donor Characteristics and Unstructured Donor Narratives

Importance

Despite the unmet need, many deceased-donor kidneys are discarded or not recovered. Inefficient allocation and prolonged ischemia time are contributing factors, and early detection of high-risk donors may reduce organ loss.

Objective

To evaluate the feasibility of machine learning (ML) and natural language processing (NLP) classification of donors with kidneys that are used vs not used for organ transplant.

Design, Setting, and Participants

This retrospective cohort study used donor information (structured donor characteristics and unstructured donor narratives) from the United Network for Organ Sharing (UNOS). All donor offers to a single transplant center between January 2015 and December 2020 were used to train and validate ML models to predict donors who had at least 1 kidney transplanted (at our center or another center). The donor data from 2021 were used to test each model.

Exposures

Donor information was provided by UNOS to the transplant centers with potential transplant candidates. Each center evaluated the donor and decided within an allotted time whether to accept the kidney for organ transplant.

Main Outcomes and Measures

Outcome metrics of the test cohort included area under the receiver operating characteristic curve (AUROC), F1 score, accuracy, precision, and recall of each ML classifier. Feature importance and Shapley additive explanation (SHAP) summaries were assessed for model explainability.

Results

The training/validation cohort included 9555 donors (median [IQR] age, 50 [36-58] years; 5571 male [58.3%]), and the test cohort included 2481 donors (median [IQR] age, 52 [40-59] years; 1496 male [60.3%]). Only 20% to 30% of potential donors had at least 1 kidney transplanted. The ML model with a single variable (Kidney Donor Profile Index) showed an AUROC of 0.69, F1 score of 0.42, and accuracy of 0.64. Multivariable ML models based on basic a priori structured donor data showed similar metrics (logistic regression: AUROC = 0.70; F1 score = 0.42; accuracy = 0.62; random forest classifier: AUROC = 0.69; F1 score = 0.42; accuracy = 0.64). The classic NLP model (bag-of-words model) showed its best metrics (AUROC = 0.60; F1 score = 0.35; accuracy = 0.59) by the logistic regression classifier. The advanced Bidirectional Encoder Representations From Transformers model showed comparable metrics (AUROC = 0.62; F1 score = 0.39; accuracy = 0.69) only after appending basic donor information. Feature importance and SHAP detected the variables (and words) that affected the models most.

Conclusions and Relevance

Results of this cohort study suggest that models using ML can be applied to predict donors with high-risk kidneys not used for organ transplant, but the models still need further elaboration. The use of unstructured data is likely to expand the possibilities; further exploration of new approaches will be necessary to develop models with better predictive metrics.

Evaluation of Opening Offers Early for Deceased Donor Kidneys at Risk of Nonutilization

BACKGROUND

Reducing nonutilization of kidneys recovered from deceased donors is a current policy concern for kidney allocation in the United States. The likelihood of nonutilization is greater with a higher kidney donor risk index (KDRI) offer. We examine how opening offers for organs with KDRI >1.75 to the broader waitlist at varying points of time affects usage rates.

METHODS

We simulate kidney allocation using data for January 2018 to June 2019 from Organ Procurement and Transplantation Network. For the simulation experiment, allocation policy is modified so that KDRI >1.75 organs are offered to all local candidates (same donation service area) after a set amount of cold time simultaneously. Open offers to candidates nationally are similarly examined.

RESULTS

Simulation results ( n =50 replications) estimate that opening offers locally for KDRI >1.75 after 10 hours yields a nonutilization rate of 38% (range: 35%-42%), less than the prevailing rate of 55% of KDRI >1.75 kidneys. Opening offers after 5 hours yields 30% (range: 26%-34%), reducing the prevailing nonutilization rate by 45%. Opening offers nationally after 10 and 5 hours yields nonutilization rates of 11% (range: 8%-15%) and 6% (range: 4%-9%) for KDRI >1.75 kidneys, respectively.

CONCLUSIONS

Simulation findings indicate that opening offers and adjusting their timing can significantly reduce nonutilization of high-KDRI kidneys.

Deceased donor kidneys from higher distressed communities are significantly less likely to be utilized for transplantation

The proportion of kidneys procured for transplantation but not utilized exceeds 20% in the United States. Factors associated with nonutilization are complex, and further understanding of novel causes are critically important. We used the national Scientific Registry of Transplant Recipients data (2010-2022) to evaluate associations of Distressed Community Index (DCI) of deceased donor residence and likelihood of kidney nonutilization (n = 209 413). Deceased donors from higher distressed communities were younger, had an increased history of hypertension and diabetes, were CDC high-risk, and had higher terminal creatinine and donation after brain death. Mechanisms and circumstances of death varied significantly by DCI. The proportion of kidney nonutilization was 19.9%, which increased by DCI quintile (Q1 = 18.1% to Q5 = 21.6%). The adjusted odds ratio of nonutilization from the highest quintile DCI communities was 1.22 (95% CI = 1.16-1.28; reference = lowest DCI), which persisted stratified by donor race. Donors from highly distressed communities were highly variable by the donor service area (range: 1%-51%; median = 21%). There was no increased risk for delayed graft function or death-censored graft loss by donor DCI but modest increased adjusted hazard for overall graft loss (high DCI = 1.05; 95% CI = 1.01-1.10; reference = lowest DCI). Results indicate that donor residential distress is associated with significantly higher rates of donor kidney nonutilization with notable regional variation and minimal impact on recipient outcomes.

Identify Hard-to-Place Kidneys for Early Engagement in Accelerated Placement With a Deep Learning Optimization Approach

Recommended practices that follow match-run sequences for hard-to-place kidneys succumb to many declines, accruing cold ischemic time and exacerbating kidney quality that may lead to unnecessary kidney discard. Hard-to-place deceased donor kidneys accepted and transplanted later in the match-run sequence may threaten higher graft failure rates. Accelerated placement is a practice for organ procurement organizations (OPOs) to allocate high-risk kidneys out of sequence and reach patients at aggressive transplant centers. The current practice of assessing hard-to-place kidneys and engaging in accelerated kidney placements relies heavily on the kidney donor profile index (KDPI) and the number of declines. Although this practice is reasonable, it also accrues cold ischemic time and increases the risk for kidney discard. We use a deep learning optimization approach to quickly identify kidneys at risk for discard. This approach uses Organ Procurement and Transplantation Network data to model kidney disposition. We filter discards and develop a model to predict transplant and discard of recovered and not transplanted kidneys. Kidneys with a higher probability of discard are deemed hard-to-place kidneys, which require early engagement for accelerated placement. Our approach will aid in identifying hard-to-place kidneys before or after procurement and support OPOs to deviate from the match-run for accelerated placement. Compared with the KDPI-only prediction of the kidney disposition, our approach demonstrates a 10% increase in correctly predicting kidneys at risk for discard. Future work will include developing models to identify candidates with an increased benefit from using hard-to-place kidneys.

Clinical Utility in Adopting Race-free Kidney Donor Risk Index

Recent events of racial injustice prompted us to study potential impact of removing race from kidney donor risk index (KDRI) calculator.

The use of marginal kidneys in dual kidney transplantation to expand kidney graft utilization

PURPOSE OF REVIEW

The purpose of this review is to chronicle the history of dual kidney transplantation (DKT) and identify opportunities to improve utilization of marginal deceased donor (MDD) kidneys through DKT.

RECENT FINDINGS

The practice of DKT from adult MDDs dates back to the mid-1990s, at which time the primary indication was projected insufficient nephron mass from older donors. Multiple subsequent studies of short- and long-term success have been reported focusing on three major aspects: Identifying appropriate selection criteria/scoring systems based on pre- and postdonation factors; refining technical aspects; and analyzing longer-term outcomes. The number of adult DKTs performed in the United States has declined in the past decade and only about 60 are performed annually. For adult deceased donor kidneys meeting double allocation criteria, >60% are ultimately not transplanted. MDDs with limited renal functional capacity represent a large proportion of potential kidneys doomed to either discard or nonrecovery.

SUMMARY

DKT may reduce organ discard and optimize the use of kidneys from MDDs. New and innovative technologies targeting ex vivo organ assessment, repair, and regeneration may have a major impact on the decision whether or not to use recovered kidneys for single or DKT.

Dual kidney transplants from adult marginal donors: Review and perspective

The practice of dual kidney transplantation (DKT) from adult marginal deceased donors (MDDs) dates back to the mid-1990s with initial pioneering experiences reported by the Stanford and Maryland groups, at which time the primary indication was estimated insufficient nephron mass from older donors. Multiple subsequent studies of short and long-term success have been reported focusing on three major aspects of DKT: Identifying appropriate selection criteria and developing scoring systems based on pre- and post-donation factors; refining technical aspects; and analyzing mid-term outcomes. The number of adult DKTs performed in the United States has declined in the past decade and only about 60 are performed annually. For adult deceased donor kidneys meeting double allocation criteria, >60% are ultimately not transplanted. Deceased donors with limited renal functional capacity represent a large proportion of potential kidneys doomed to either discard or non-recovery. However, DKT may reduce organ discard and optimize the use of kidneys from MDDs. In an attempt to promote utilization of MDD kidneys, the United Network for Organ Sharing introduced new allocation guidelines pursuant to DKT in 2019. The purpose of this review is to chronicle the history of DKT and identify opportunities to improve utilization of MDD kidneys through DKT. This article is protected by copyright. All rights reserved.

Hardest-to-place kidney transplant outcomes in the United States

The outcomes of hardest-to-place kidney transplants-accepted last in the entire match run after being refused by previous centers-are unclear, potentially translating to risk aversion and unnecessary organ discard. We aimed to determine the outcomes of hardest-to-place kidney transplants and whether the organ acceptance position on the match run sufficiently captures the risk. This is a cohort study of the United Network for Organ Sharing data of all adult kidney-only transplant recipients from deceased donors between 2007 and 2018. Multiple regression models assessed delayed graft function, graft survival, and patient survival stratified by share type: local versus shared kidney acceptance position scaled by tertile. Among 127 028 kidney transplant recipients, 92 855 received local kidneys. The remaining received shared kidneys at sequence number 1-4 (n = 12 322), 5-164 (n = 10 485) and >164 (n = 11 366). Hardest-to-place kidneys, defined as the latest acceptance group in the match-run, were associated with delayed graft function (adjusted odds ratio 1.83, 95% confidence interval [CI] 1.74-1.92) and all-cause allograft failure (adjusted hazard ratio [aHR] 1.11, 95% CI 1.04-1.17). Results of this IRB-approved study were robust to the exclusion of operational allocation bypass and mandatory shares. The hardest-to-place kidneys accepted later in the match run were associated with higher graft failure and delayed graft function.

Predicting Kidney Discard Using Machine Learning

BACKGROUND

Despite the kidney supply shortage, 18%-20% of deceased donor kidneys are discarded annually in the United States. In 2018, 3569 kidneys were discarded.

METHODS

We compared machine learning (ML) techniques to identify kidneys at risk of discard at the time of match run and after biopsy and machine perfusion results become available. The cohort consisted of adult deceased donor kidneys donated between December 4, 2014, and July 1, 2019. The studied ML models included Random Forests (RF), Adaptive Boosting (AdaBoost), Neural Networks (NNet), Support Vector Machines (SVM), and K-nearest Neighbors (KNN). In addition, a Logistic Regression (LR) model was fitted and used for comparison with the ML models' performance.

RESULTS

RF outperformed other ML models. Of 8036 discarded kidneys in the test dataset, LR correctly classified 3422 kidneys, whereas RF correctly classified 4762 kidneys (area under the receiver operative curve [AUC]: 0.85 versus 0.888, and balanced accuracy: 0.681 versus 0.759). For the kidneys with kidney donor profile index of >85% (6079 total), RF significantly outperformed LR in classifying discard and transplant prediction (AUC: 0.814 versus 0.717, and balanced accuracy: 0.732 versus 0.657). More than 388 kidneys were correctly classified using RF. Including biopsy and machine perfusion variables improved the performance of LR and RF (LR's AUC: 0.888 and balanced accuracy: 0.74 versus RF's AUC: 0.904 and balanced accuracy: 0.775).

CONCLUSIONS

Kidneys that are at risk of discard can be more accurately identified using ML techniques such as RF.

Determinants of kidney transplant candidates' decision to accept organ donor intervention transplants and participate in post-transplant research: A conjoint analysis

Deceased organ donor intervention research aims to increase organ quality and quantity for transplantation. We assessed the proportion of kidney transplant candidates who would accept "intervention organs," participate in organ intervention research, and factors influencing acceptance. Kidney transplant candidates were presented 12 hypothetical scenarios, which varied three attributes, donor age, predicted waiting time to receive another organ offer, and research risk to the organ. Candidates were also randomly assigned to one of two conditions varying recipient risk. For each scenario, candidates agreed to accept the intervention organ or remain waitlisted. We fit a multivariable logit model to determine the association between scenario attributes and the acceptance decision. Of 249 participants, most (96%) accepted intervention organs under some or all conditions. Factors independently associated with candidates' greater likelihood of accepting an intervention organ included: low risk to the kidney from the intervention (OR 20.53 [95% Confidence Interval (CI), 13.91-30.29]); younger donor age (OR 3.72 [95% CI, 2.83-4.89]), longer time until the next organ offer (OR 3.48 [95% CI, 2.65-4.57]), and greater trust in their transplant physician (OR 1.03 [95% CI, 1.00-1.06]). Candidates with a lower likelihood of acceptance had been waitlisted longer (OR 0.97 per month [95% CI, 0.96-0.99]) and were Black (OR 0.21 [95% CI, 0.08-0.55]). Most candidates would accept an intervention organ, which should encourage transplant leaders to conduct deceased donor organ intervention trials.

Estimating the potential pool of uncontrolled DCD donors in the United States

Organs from uncontrolled DCD donors (uDCDs) have expanded donation in Europe since the 1980s, but are seldom used in the United States. Cited barriers include lack of knowledge about the potential donor pool, lack of robust outcomes data, lack of standard donor eligibility criteria and preservation methods, and logistical and ethical challenges. To determine whether it would be appropriate to invest in addressing these barriers and building this practice, we sought to enumerate the potential pool of uDCD donors. Using data from the Nationwide Emergency Department Sample, the largest all-payer emergency department (ED) database, between 2013 and 2016, we identified patients who had refractory cardiac arrest in the ED. We excluded patients with contraindications to both deceased donation (including infection, malignancy, cardiopulmonary disease) and uDCD (including hemorrhage, major polytrauma, burns, and poisoning). We identified 9828 (range: 9454-10 202) potential uDCDs/y; average age was 32 years, and all were free of major comorbidity. Of these, 91.1% had traumatic deaths, with major causes including nonhead blunt injuries (43.2%) and head injuries (40.1%). In the current era, uDCD donors represent a significant potential source of unused organs. Efforts to address barriers to uDCD in the United States should be encouraged.

Risk Factors for No Valid Liver Graft. Multivariate Study Based on the Variables Included in the Donation Protocol of the National Trasplant Organisation

INTRODUCTION

Among the strategies designed to optimize the number of existing liver grafts for transplantation, the implementation of the graft assessment process is one of the least explored. The main objective is to identify the risk factors presented by liver donors for «NO validity». Secondly, we analyzed the coincidence between the surgeon's assessment and that of the anatomo-pathologist in the invalid donors.

MATERIAL AND METHOD

Retrospective study conducted from a prospective database that analyzes 190 liver donors, 95 valid and 95 NOT valid. The variables of each of them corresponding to the donation protocol of the National Transplant Organization are studied. Through a multivariate study we determine the independent risk factors of NO validity. We checked the causes of NO validity argued with the histopathological findings of these grafts.

RESULTS

The independent risk factors of non-validity in the multivariate study (P < .05) were: dyslipidemia, personal medical history other than cardiovascular and abdominal surgical risk factors, GGT, BrT, and the result of previous liver ultrasound. The 3 most frequent causes of NO validity were: steatosis, fibrosis and macroscopic appearance of the organ. 78% of the biopsies confirmed the NO validity of the graft (in 57.9% of the cases the histological findings coincided with those described by the surgeon). The 22.1% of the biopsies hadńt pathological findings.

CONCLUSIONS

The determination of the risk factors of NO validity will contribute to the design of future assessment scores that are useful tools in the process of liver graft assessment.).

Can donor narratives yield insights? A natural language processing proof of concept to facilitate kidney allocation

Although expedited placement could ameliorate stagnant kidney utilization, precisely identifying difficult-to-place organs is crucial to mitigate potential harms associated with this policy. Existing algorithms have only leveraged structured data from the Organ Procurement and Transplantation Network (OPTN); however, detailed, free text case information about a donor exists. No known research exists about the utility of these data. We developed a model to predict the probability of delay or discard for adult deceased kidney donors between 2010 and 2018, leveraging donor free text data. The resultant model had a c-statistic of 0.75 compared to 0.80 ( Reduced Probability of Delay or Discard [model], r-PODD) and 0.77 ( Kidney Donor Profile Index, KDPI) on the test dataset. Analysis of the top predictive words suggest both known and potentially novel clinical factors (ie, a known factor such as hypertension vs a novel factor such as stents), and nuanced social factors (intravenous drug use) could negatively affect kidney utilization. These findings suggest that donor narratives have utility; the natural language processing (NLP) model is only moderately correlated with existing indices and provides directional evidence about additional cardiovascular risk factors that may affect kidney utilization. More research is needed to understand the potential to enhance existing indices of kidney utilization to better enable and mitigate the effects of policy interventions such as expedited placement.