Live-donor kidney transplant outcome prediction (L-TOP) using artificial intelligence.

Outcome prediction for live-donor kidney transplantation improves clinical and patient decisions and donor selection. However, the concurrently used models are of limited discriminative or calibration power and there is a critical need to improve the selection process. We aimed to assess the value of various artificial intelligence (AI) algorithms to improve the risk stratification index. We evaluated pre-transplant variables among 66 914 live-donor kidney transplants (performed between 01/12/2007-01/06/2021) from the United Network of Organ Sharing database, randomized into training (80%) and test (20%) sets. The primary outcome measure was death-censored graft survival. We tested four machine learning models for discrimination (time-dependent concordance index, CTD, and area under the ROC curve) and calibration (integrated Brier score, IBS). We used decision curve analysis to assess the potential clinical utility. Among the models, the deep Cox mixture model showed the best discriminative performance (AUC = 0.70, 0.68, and 0.68 at 5, 10, and 13 years post-transplant, respectively). CTD reached 0.70, 0.67, and 0.66 at 5, 10, and 13 years post-transplant. The IBS score was 0.09, indicating good calibration. In comparison, applying the Living Kidney Donor Profile Index (LKDPI) on the same cohort produced a CTD of 0.56 and an AUC of 0.55-0.58 only. Decision curve analysis showed an additional net benefit compared to the LKDPI, 'Treat all' and 'Treat None' approaches. Our AI-based deep Cox mixture model, termed Live-Donor Kidney Transplant Outcome Prediction outperforms existing prediction models, including the LKDPI, with the potential to improve decisions for optimum live donor selection by ranking potential transplant pairs based on graft survival. This model could be adopted to improve the outcomes of paired exchange programs.

Deceased-Donor Kidney Transplant Outcome Prediction Using Artificial Intelligence to Aid Decision-Making in Kidney Allocation.

In kidney transplantation, pairing recipients with the highest longevity with low-risk allografts to optimize graft-donor survival is a complex challenge. Current risk prediction models exhibit limited discriminative and calibration capabilities and have not been compared to modern decision-assisting tools. We aimed to develop a highly accurate risk-stratification index using artificial intelligence (AI) techniques. Using data from the UNOS database (156,749 deceased kidney transplants, 2007-2021), we randomly divided transplants into training (80%) and validation (20%) sets. The primary measure was death-censored graft survival. Four machine learning models were assessed for calibration (integrated Brier score [IBS]) and discrimination (time-dependent concordance [CTD] index), compared with existing models. We conducted decision curve analysis and external validation using UK Transplant data. The Deep Cox mixture model showed the best discriminative performance (area under the curve [AUC] = 0.66, 0.67, and 0.68 at 6, 9, and 12 years post-transplant), with CTD at 0.66. Calibration was adequate (IBS = 0.12), while the kidney donor profile index (KDPI) model had lower CTD (0.59) and AUC (0.60). AI-based D-TOP outperformed the KDPI in evaluating transplant pairs based on graft survival, potentially enhancing deceased donor selection. Advanced computing is poised to influence kidney allocation schemes.

Therapeutic Donor Kidney Transplant Outcomes: Comparing Early US Experiences Using Optimal Matching.

Background: Therapeutic donors (TDs) are individuals who undergo organ removal for medical treatment with no replacement organ, and the organ is then transplanted into another person. Transplant centers in the United States have started using TDs for kidney transplantation (KT). TD-KT recipient outcomes may be inferior to those of non-TD-living-donor (non-TD-LD)-KT or deceased-donor (DD)-KT because of the conditions that led to nephrectomy; however, these outcomes have not been sufficiently evaluated. Methods: This was a retrospective cohort study using Organ Procurement and Transplantation Network data. Via optimal matching methods, we created 1:4 fivesomes with highly similar characteristics for TD-KT and non-TD-LD-KT recipients and then separately for TD-KT and DD-KT recipients. We compared a 6-mo estimated glomerular filtration rate (eGFR) between groups (primary endpoint) and a composite of death, graft loss, or eGFR <30 mL/min/1.73 m2 at 6 mo (secondary). Results: We identified 36 TD-KT recipients with 6-mo eGFR. There was also 1 death and 2 graft losses within 6 mo. Mean ± SD 6-mo eGFR was not significantly different between TD-KT, non-TD-LD-KT, and DD-KT recipients (59.9 ± 20.7, 63.3 ± 17.9, and 59.9 ± 23.0 mL/min/1.73 m2, respectively; P > 0.05). However, the 6-mo composite outcome occurred more frequently with TD-KT than with non-TD-LD-KT and DD-KT (18%, 2% [P < 0.001], and 8% [P = 0.053], respectively). Conclusions: Early graft function was no different between well-matched groups, but TD-KT demonstrated a higher risk of otherwise poor 6-mo outcomes compared with non-TD-LD-KT and DD-KT. Our results support selective utilization of TD kidneys; however, additional studies are needed with more detailed TD kidney information to understand how to best utilize these kidneys.

Comparison of Short-Term Outcomes in Kidney Transplant Recipients from SARS-CoV-2-Infected versus Noninfected Deceased Donors.

BACKGROUND: Acceptable post-transplant outcomes were reported in kidney transplant recipients from donors with coronavirus disease 2019 (COVID-19); however, there are no comparative studies with well-matched controls. METHODS: This multicenter, prospective observational study, which included three transplant centers in the United States, enrolled 61 kidney recipients from severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-infected deceased donors. Using optimal matching methods, we matched every recipient to three comparators receiving kidneys from SARS-CoV-2-negative deceased donors with otherwise highly similar characteristics in the same transplant centers to compare 6-month eGFR. RESULTS: Among recipients of SARS-CoV-2-infected donor kidneys, one recipient died with a functional graft within 6 months. Mean 6-month eGFR was not significantly different between SARS-CoV-2-infected and noninfected donor groups (55±21 and 57±25 ml/min per 1.73 m 2 , respectively; P = 0.61). Six-month eGFR in recipients from SARS-CoV-2-infected donors who died of reasons other than COVID-19 was not significantly different from those from SARS-CoV-2-negative donors (58±22 and 56±25 ml/min per 1.73 m 2 , respectively; P = 0.51). However, recipients from donors who died of COVID-19 had significantly lower 6-month eGFR than those from SARS-CoV-2-negative donors (46±17 and 58±27 ml/min per 1.73 m 2 , respectively; P = 0.03). No donor-to-recipient SARS-CoV-2 transmission was observed. CONCLUSIONS: Six-month eGFR was not significantly different between recipients of kidneys from SARS-CoV-2-infected and noninfected donors. However, those receiving kidneys from donors who died of COVID-19 had significantly lower 6-month eGFR. Donor-to-recipient SARS-CoV-2 transmission was not observed.

Cannabis Use and Risk of Acute Kidney Injury in Patients with Advanced Chronic Kidney Disease Transitioning to Dialysis.

Background: The current social and legal landscape is likely to foster the medicinal and recreational use of cannabis. Synthetic cannabinoid use is associated with acute kidney injury (AKI) in case reports; however, the association between natural cannabis use and AKI risk in patients with advanced chronic kidney disease (CKD) is unknown. Materials and Methods: From a nationally representative cohort of 102,477 U.S. veterans transitioning to dialysis between 2007 and 2015, we identified 2215 patients with advanced CKD who had undergone urine toxicology (UTOX) tests within a year before dialysis initiation and had inpatient serial serum creatinine levels measured within 7 days after their UTOX test. The exposure of interest was cannabis use compared with no use as ascertained by the UTOX test. We examined the association of this exposure with AKI using logistic regression and inverse probability of treatment weighting with extensive adjustment for potential confounders. Results: The mean age of the overall cohort was 61 years; 97% were males, 51% were African Americans, 97% had hypertension, 76% had hyperlipidemia, and 75% were diabetic. AKI occurred in 56% of the cohort, and in multivariable-adjusted analysis, cannabis use (when compared with no substance use) was not associated with significantly higher odds of AKI (odds ratio 0.85, 95% confidence interval 0.38-1.87; p=0.7). These results were robust to various sensitivity analyses. Conclusions: In this observational study examining patients with advanced CKD, cannabis use was not associated with AKI risk. Additional studies are needed to characterize the impact of cannabis use on risk of kidney disease and injury.

Liver Outcome in Renal Transplant Recipients Who Acquired Hepatitis C Infection From an Infected Graft: Study Based on Liver Biopsy Findings.

Long-term liver outcome in hepatitis C virus (HCV)-negative kidney recipients who acquired HCV infection from viremic donors is of intense interest in the transplant community. We evaluated the incidence of fibrosis in liver biopsy specimens of recipients who were transplanted with HCV-infected grafts. Methods: Patients were evaluated in the hepatology clinic, and 29 patients agreed to undergo liver biopsy. The liver histology was scored by the meta-analysis of histological data in viral hepatitis scoring system and was assessed by hepatopathologists. The fibrosis score was compared between patients who initiated direct-acting antiviral (DAA) within 6 wk (n = 6) and after 6 wk (n = 29). Results: Eighty-nine aviremic patients were transplanted with HCV-infected grafts between March 2018 and October 2019. All patients developed HCV infection and were treated with DAA treatment after kidney transplantation (median, 70 d; interquartile range, 55-85 d). All patients (n = 89) achieved sustained virologic response with DAA. The median follow-up time from kidney transplant to liver biopsy was 28 mo (interquartile range, 26-30 mo). Twenty-five patients (86%) had F0, and 4 patients (14%) had F1 fibrosis. No patient had advanced fibrosis (F3-F4). Grade 1 inflammation was present in 6 (21%) patients, whereas 26 (90%) patients had iron accumulation in the hepatocytes and reticuloendothelial cells. There was no difference in the fibrosis score between patients who received treatment within 6 wk versus after 6 wk (P = 0.55). Conclusions: Kidney transplantation of HCV-infected graft to HCV-negative recipients is safe and has no long-term liver-related complications with successful eradication of HCV. In our cohort, delayed treatment did not affect sustained virologic response or liver histology.

CMV specific T cell immune response in hepatitis C negative kidney transplant recipients receiving transplant from hepatitis C viremic donors and hepatitis C aviremic donors.

Kidney transplants (KT) from hepatitis C (HCV) viremic donors to HCV negative recipients has shown promising renal outcomes, however, high incidence of cytomegalovirus (CMV) viremia were reported. We performed a prospective cohort study of 52 HCV negative KT recipients from Methodist University Hospital including 41 receiving transplants from HCV aviremic donors and 11 from HCV viremic donors. CMV specific CD4+ and CD8 + T cell immunity was measured by intracellular flow cytometry assay. Primary outcome was the development of positive CMV specific CD4+ and CD8 + T cell immune response in the entire cohort and each subgroup. The association between donor HCV status and CMV specific CD4+ and CD8 + T cell immune response was analyzed by Cox proportional hazard models. Mean recipient age was 48 ± 13 years, with 73% male and 82% African American. Positive CMV specific CD4+ and CD8 + T cell immune response was found in 53% and 47% of the cohort at 1 month, 65% and 70% at 2 months, 80% and 75% at 4 months, 89% and 87% at 6 months, and 94% and 94% at 9 months post-transplant, respectively. There was no significant difference in the incidence of positive CMV specific T cell immune response between recipients of transplants from HCV aviremic donors compared to HCV viremic donors in unadjusted (for CD8+: HR = 1.169, 95%CI: 0.521-2.623; for CD4+: HR = 1.208, 95%CI: 0.543-2.689) and adjusted (for CD8+: HR = 1.072, 95%CI: 0.458-2.507; for CD4+: HR = 1.210, 95%CI: 0.526-2.784) Cox regression analyses. HCV viremia in donors was not associated with impaired development of CMV specific T cell immunity in this cohort.

Genetic Etiologies for Chronic Kidney Disease Revealed through Next-Generation Renal Gene Panel.

INTRODUCTION: Chronic kidney disease (CKD) is a major public health issue in the USA. Identification of monogenic causes of CKD, which are present in ∼10% of adult cases, can impact prognosis and patient management. Broad gene panels can provide unbiased testing approaches, which are advantageous in phenotypically heterogeneous diseases. However, the use and yield of broad genetic panels by nephrologists in clinical practice is not yet well characterized. METHODS: Renal genetic testing, ordered exclusively for clinical purposes, predominantly by general and transplant nephrologists within the USA, was performed on 1,007 consecutive unique patient samples. Testing was performed using a commercially available next-generation sequencing-based 382 gene kidney disease panel. Pathogenic (P) and likely pathogenic (LP) variants were reported. Positive findings included a monoallelic P/LP variant in an autosomal dominant or X-linked gene and biallelic P/LP variants in autosomal recessive genes. RESULTS: Positive genetic findings were identified in 21.1% (212/1,007) of cases. A total of 220 positive results were identified across 48 genes. Positive results occurred most frequently in the PKD1 (34.1%), COL4A5 (10.9%), PKD2 (10.0%), COL4A4 (6.4%), COL4A3 (5.9%), and TTR (4.1%) genes. Variants identified in the remaining 42 genes comprised 28.6% of the total positive findings, including single positive results in 26 genes. Positive results in >1 gene were identified in 7.5% (16/212) of cases. CONCLUSIONS: Use of broad panel genetic testing by clinical nephrologists had a high success rate, similar to results obtained by academic centers specializing in genetics.

Nutritional and dietary interventions to prolong renal allograft survival after kidney transplantation.

PURPOSE OF REVIEW: Diet plays an important role in slowing progression of chronic kidney disease in native and transplanted kidneys. There is limited evidence on the association on dietary intake with renal allograft function. Mechanisms of major nutrients and dietary patterns with focusing on a plant-based diet related to kidney transplant health and longevity are reviewed. RECENT FINDINGS: High dietary protein intake may adversely affect renal allograft. Low protein plant-focused diets such as Dietary Approaches to Stop Hypertension, plant-dominant low-protein diet and Mediterranean diets appear associated with favorable outcomes in slowing renal allograft function decline. The mechanism may be related to a change in renal hemodynamic by decreasing glomerular hyperfiltration from low dietary protein intake and plant-based ingredients. Recent observational studies of association between dietary protein intake and kidney allograft outcomes are conflicting. Although strong evidence is still lacking, a low protein diet of 0.6-0.8 g/kg/day with at least 50% of the protein source from plant-based components in kidney transplant recipients with stable kidney allograft function should be considered as the dietary target. SUMMARY: Dietary intervention with low-protein plant-focused meals may improve outcomes in kidney transplant recipients, but the evidence remains limited and further studies are warranted.

Association of donor hepatitis C virus infection status and risk of BK polyomavirus viremia after kidney transplantation.

Kidney transplantation (KT) from deceased donors with hepatitis C virus (HCV) into HCV-negative recipients has become more common. However, the risk of complications such as BK polyomavirus (BKPyV) remains unknown. We assembled a retrospective cohort at four centers. We matched recipients of HCV-viremic kidneys to highly similar recipients of HCV-aviremic kidneys on established risk factors for BKPyV. To limit bias, matches were within the same center. The primary outcome was BKPyV viremia ≥1000 copies/ml or biopsy-proven BKPyV nephropathy; a secondary outcome was BKPyV viremia ≥10 000 copies/ml or nephropathy. Outcomes were analyzed using weighted and stratified Cox regression. The median days to peak BKPyV viremia level was 119 (IQR 87-182). HCV-viremic KT was not associated with increased risk of the primary BKPyV outcome (HR 1.26, p = .22), but was significantly associated with the secondary outcome of BKPyV ≥10 000 copies/ml (HR 1.69, p = .03). One-year eGFR was similar between the matched groups. Only one HCV-viremic kidney recipient had primary graft loss. In summary, HCV-viremic KT was not significantly associated with the primary outcome of BKPyV viremia, but the data suggested that donor HCV might elevate the risk of more severe BKPyV viremia ≥10 000 copies/ml. Nonetheless, one-year graft function for HCV-viremic recipients was reassuring.

Association of dyskalemias with short-term health care utilization in patients with advanced CKD.

BACKGROUND: Patients with advanced chronic kidney disease (CKD) are at high risk for dyskalemias, which may induce arrhythmias that require immediate emergent or hospital care. The association of dyskalemias with short-term hospital/emergency room (ER) visits in advanced CKD is understudied. OBJECTIVE: To assess the association of dyskalemias with short-term hospital/ER visits in an advanced CKD population. METHODS: From among 102,477 US veterans transitioning to dialysis from 2007 to 2015, we identified 21,366 patients with 2 predialysis outpatient eGFR < 30 ml/min/1.73m2 90-365 days apart (with the second eGFR serving as the index date) and at least 1 potassium (K) in the baseline period (1 year before index) and 1 outpatient K (oK) in the follow-up (1 year after the index but before dialysis initiation). We examined the association of time-varying hypokalemia (K < 3.5 mEq/L) and hyperkalemia (K > 5.5 mEq/L) vs referent (3.5-5.5 mEq/L) with separate hospital and ER visits within 2 calendar days following each oK value over the 1-year follow-up period from the index. We used generalized estimating equations with binary distribution and logit link to model the exposure-outcome relationship adjusted for various confounders. We conducted various subgroup and sensitivity analyses to test the robustness of our results. RESULTS: Over the 1-year follow-up, 125,266 oK measurements were observed, of which 6.8% and 3.7% were classified as hyper- and hypokalemia, respectively. In the multivariable-adjusted model, hyperkalemia (adjusted odds ratio [aOR] = 2.04; 95% CI = 1.88-2.21) and hypokalemia (aOR = 1.66; 95% CI = 1.48-1.86) were associated with significantly higher odds of hospital visits. Similarly, hyperkalemia (aOR = 1.83; 95% CI = 1.65-2.03) and hypokalemia (aOR = 1.24; 95% CI = 1.07-1.44) were associated with significantly higher odds of ER visits. Results were robust to subgroups and sensitivity analyses. CONCLUSIONS: In patients with advanced CKD, dyskalemias are associated with higher risk of hospital/ER visits. Interventions targeted at lowering the risk of dyskalemias might help in reducing the health care utilization and associated economic burden among patients with advanced CKD experiencing dyskalemias. DISCLOSURES: This study was supported by grant 5U01DK102163 from the National Institute of Health (NIH) to Kamyar Kalantar-Zadeh and Csaba P. Kovesdy and by resources from the US Department of Veterans Affairs. The data reported here have been supplied in part by the United States Renal Data System (USRDS). Support for VA/CMS data were provided by the Department of Veterans Affairs, Veterans Health Administration, Office of Research and Development, Health Services Research and Development, VA Information Resource Center (project numbers SDR 02-237 and 98-004). Opinions expressed in this article are those of the authors and do not necessarily represent the opinion of the Department of Veterans Affairs or the funding institution. Kovesdy has received honoraria from Akebia, Ardelyx, Astra Zeneca, Bayer, Boehringer-Ingelheim, Cara Therapeutics, Reata, and Tricida unrelated to this study. Kalantar-Zadeh has received honoraria and/or support from Abbott, Abbvie, ACI Clinical (Cara Therapeutics), Akebia, Alexion, Amgen, American Society of Nephrology, Astra-Zeneca, Aveo, BBraun, Chugai, Cytokinetics, Daiichi, DaVita, Fresenius, Genentech, Haymarket Media, Hofstra Medical School, International Federation of Kidney Foundations, International Society of Hemodialysis, International Society of Renal Nutrition & Metabolism, Japanese Society of Dialysis Therapy, Hospira, Kabi, Keryx, Kissei, Novartis, OPKO, National Institutes of Health, National Kidney Foundations, Pfizer, Regulus, Relypsa, Resverlogix, Dr Schaer, Sandoz, Sanofi, Shire, Veterans Affairs, Vifor, UpToDate, and ZS-Pharma, unrelated to this study. Gatwood has received research support from AstraZeneca, Merck & Co., and GlaxoSmithKline unrelated to this study. Obi has received research support from Relypsa/Vifor Pharma Inc. The remaining authors declare that they have no relevant financial interests.

Association between ezetimibe usage and hepatitis C RNA levels in uninfected kidney transplant recipients who received hepatitis C infected kidneys.

Kidney transplantation (KT) from hepatitis C virus infected (HCV+) donors to HCV negative recipients achieve excellent graft function but have relatively higher rates of post-KT co-infections presumably due to prolonged HCV viremia in transmission-and-treat approach. Ezetimibe acts as an antagonist of Niemann-Pick C1-Like 1 receptor required for HCV entry and theoretically can reduce HCV viremia. However, no data is available to examine the role of ezetimibe as a bridge therapy between KT surgery and direct acting antiviral (DAA) initiation. A retrospective cohort study including 70 HCV+ to HCV negative KT recipients from Methodist University Hospital and Vanderbilt University Medical Center was performed to determine the association between ezetimibe usage and HCV viremia. Twenty patients received ezetimibe daily while 50 patients did not. Primary outcome of study was mean HCV RNA level at 1-2 weeks post-KT and before initiation of DAA. Median (IQR) viral load (VL) in log copies/ml was one log lower in ezetimibe group versus non-ezetimibe group (4.1 [3.7-5.3] vs. 5.1 [4.4-5.5], P = .01), and highest VL was also lower in ezetimibe group (4.2 [3.7-5.4] vs. 5.4 [4.7-5.9], P = .006). We concluded that ezetimibe bridge therapy might be associated with reduction in HCV VL while waiting for DAA initiation in HCV+ to HCV negative KT recipients.

Robotic-assisted Kidney Transplantation With Simultaneous Bilateral Nephrectomies Is an Efficient, Feasible, and Safe Way to Manage Patients With Renal Failure Secondary to Adult Polycystic Kidney Disease.

Kidney transplantation has become the standard of care for end-stage renal disease secondary to adult polycystic kidney disease. Open surgical techniques remain the gold standard, although minimally invasive methods have gained traction in recent years. Native nephrectomy is frequently needed secondary to size or symptoms. Continued developments in surgical technology have allowed for the introduction of computer-assisted surgery (Robotics). We aim to describe the feasibility, safety, and efficiency of simultaneous laparoscopic bilateral nephrectomy and robotic-assisted kidney transplantation to treat end-stage renal kidney transplantation secondary to polycystic kidney disease. In this initial experience, 3 patients underwent kidney transplantation with a simultaneous bilateral nephrectomy. All patients tolerated the procedure well with no postoperative blood transfusions, dialysis, or surgical site infections. Simultaneous laparoscopic bilateral nephrectomy and robotic-assisted kidney transplantation may be feasible, safe, and efficient techniques. Complications were minimal, with short hospital stays. Supplemental Video; http://links.lww.com/TXD/A352.

Association of Dyskalemias with Ischemic Stroke in Advanced Chronic Kidney Disease Patients Transitioning to Dialysis.

INTRODUCTION: Hypo- and hyperkalemia are associated with a higher risk of ischemic stroke. However, this association has not been examined in an advanced chronic kidney disease (CKD) population. METHODS: From among 102,477 US veterans transitioning to dialysis between 2007 and 2015, 21,357 patients with 2 pre-dialysis outpatient estimated glomerular filtration rates <30 mL/min/1.73 m2 90-365 days apart and at least 1 potassium (K) each in the baseline and follow-up period were identified. We separately examined the association of both baseline time-averaged K (chronic exposure) and time-updated K (acute exposure) treated as categorized (hypokalemia [K <3.5 mEq/L] and hyperkalemia [K >5.5 mEq/L] vs. referent [3.5-5.5 mEq/L]) and continuous exposure with time to the first ischemic stroke event prior to dialysis initiation using multivariable-adjusted Cox regression models. RESULTS: A total of 2,638 (12.4%) ischemic stroke events (crude event rate 41.9 per 1,000 patient years; 95% confidence interval [CI] 40.4-43.6) over a median (Q1-Q3) follow-up time of 2.56 (1.59-3.89) years were observed. The baseline time-averaged K category of hypokalemia (adjusted hazard ratio [aHR], 95% CI: 1.35, 1.01-1.81) was marginally associated with a significantly higher risk of ischemic stroke. However, time-updated hyperkalemia was associated with a significantly lower risk of ischemic stroke (aHR, 95% CI: 0.82, 0.68-0.98). The exposure-outcome relationship remained consistent when using continuous K levels for both the exposures. DISCUSSION/CONCLUSION: In patients with advanced CKD, hypokalemia (chronic exposure) was associated with a higher risk of ischemic stroke, whereas hyperkalemia (acute exposure) was associated with a lower risk of ischemic stroke. Further studies in this population are needed to explore the mechanisms underlying these associations.