Background: Kidney transplantation is the optimal treatment for patients with end-stage renal disease. Short- and long-term kidney graft survival is influenced by a number of donor and recipient factors. Predicting the success of kidney transplantation is important for optimizing kidney allocation. Objective: The aim of this study was to predict the risk of kidney graft failure across three temporal cohorts (within 1 year, within 5 years, and after 5 years following a transplant) based on donor and recipient characteristics. We analyzed a large data set comprising over 50,000 kidney transplants covering an approximate 20-year period. Methods: We applied machine learning–based classification algorithms to develop prediction models for the risk of graft failure for three different temporal cohorts. Deep learning–based autoencoders were applied for data dimensionality reduction, which improved the prediction performance. The influence of features on graft survival for each cohort was studied by investigating a new nonoverlapping patient stratification approach. Results: Our models predicted graft survival with area under the curve scores of 82% within 1 year, 69% within 5 years, and 81% within 17 years. The feature importance analysis elucidated the varying influence of clinical features on graft survival across the three different temporal cohorts. Conclusions: In this study, we applied machine learning to develop risk prediction models for graft failure that demonstrated a high level of prediction performance. Acknowledging that these models performed better than those reported in the literature for existing risk prediction tools, future studies will focus on how best to incorporate these prediction models into clinical care algorithms to optimize the long-term health of kidney recipients.

Background.: Coronavirus disease 2019 (COVID-19) has resulted in significant morbidity and mortality in solid organ transplant (SOT) recipients. The National COVID Cohort Collaborative was developed to facilitate analysis of patient-level data for those tested for COVID-19 across the United States. Methods.: In this study, we identified a cohort of SOT recipients testing positive or negative for COVID-19 (COVID+ and COVID−, respectively) between January 1, 2020, and November 20, 2020. Univariable and multivariable logistic regression were used to determine predictors of a positive result among those tested. Outcomes following COVID-19 diagnosis were also explored. Results.: Of 18 121 SOT patients tested, 1925 were positive (10.6%). COVID+ SOT patients were more likely to have a kidney transplant and be non-White race. Comorbidities were common in all SOT patients but significantly more common in those who were COVID+. Of COVID+ SOT, 42.9% required hospital admission. COVID+ status was the strongest predictor of acute kidney injury (AKI), rejection, and graft failure in the 90 d after testing. A total of 40.9% of COVID+ SOT experienced a major adverse renal or cardiac event, 16.3% experienced a major adverse cardiac event, 35.3% experienced AKI, and 1.5% experienced graft loss. Conclusions.: In the largest US cohort of COVID+ SOT recipients to date, we identified patient factors associated with the diagnosis of COVID-19 and outcomes following infection, including a high incidence of major adverse renal or cardiac event and AKI.

Background: Prolonged warm ischemia time (WIT) and cold ischemia time (CIT) are independently associated with post-transplant graft failure; their combined impact has not been previously studied. We explored the effect of combined WIT/CIT on all-cause graft failure following kidney transplantation. Methods: The Scientific Registry of Transplant Recipients was used to identify kidney transplant recipients from January 2000 to March 2015 (after which WIT was no longer separately reported), and patients were followed until September 2017. A combined WIT/CIT variable (excluding extreme values) was separately derived for live and deceased donor recipients using cubic splines; for live donor recipients, the reference group was WIT 10 to 0 to <0.42 hours, and for deceased donor recipients the WIT was 10 to <25 minutes and CIT 1 to <7.75 hours. The adjusted association between combined WIT/CIT and all-cause graft failure (including death) was analyzed using Cox regression. Secondary outcomes included delayed graft function (DGF). Results: A total of 137 125 recipients were included. For live donor recipients, patients with prolonged WIT/CIT (60 to ≤120 minutes/3.04 to ≤24 hours) had the highest adjusted hazard ratio (HR) for graft failure (HR = 1.61, 95% confidence interval [CI] = 1.14-2.29 relative to the reference group). For deceased donor recipients, a WIT/CIT of 63 to ≤120 minutes/28 to ≤48 hours was associated with an adjusted HR of 1.35 (95% CI = 1.16-1.58). Prolonged WIT/CIT was also associated with DGF for both groups although the impact was more driven by CIT. Conclusions: Combined WIT/CIT is associated with graft loss following transplantation. Acknowledging that these are separate variables with different determinants, we emphasize the importance of capturing WIT and CIT independently. Furthermore, efforts to reduce WIT and CIT should be prioritized.

Clinical outcomes in solid organ transplant (SOT) recipients with breakthrough COVID (BTCo) after two doses of mRNA vaccination compared to the non-immunocompromised/immunosuppressed (ISC) general population, are not well described. In a cohort of adult patients testing positive for COVID-19 between December 10, 2020 and April 4, 2022, we compared the cumulative incidence of BTCo in a non-ISC population to SOT recipients (overall and by organ type) using the National COVID Cohort Collaborative (N3C) including data from 36 sites across the United States. We assessed the risk of complications post-BTCo in vaccinated SOT recipients versus SOT with unconfirmed vaccination status (UVS) using multivariable Cox proportional hazards and logistic regression. BTCo occurred in 4776 vaccinated SOT recipients over a median of 149 days (IQR 99–233), with the highest cumulative incidence in heart recipients. The relative risk of BTCo was greatest in SOT recipients (relative to non-ISC) during the pre-Delta period (HR 2.35, 95% CI 1.80–3.08). The greatest relative benefit with vaccination for both non-ISC and SOT cohorts was in BTCo mortality (HR 0.37, 95% CI 0.36–0.39 for non-ISC; HR 0.67, 95% 0.57–0.78 for SOT relative to UVS). While the relative benefit of vaccine was less in SOT than non-ISC, SOT patients still exhibited significant benefit with vaccination.