Early renal function recovery and long-term graft survival in kidney transplantation

Predicting kidney allograft survival with explainable machine learning

INTRODUCTION

Despite significant progress over the last decades in the survival of kidney allografts, several risk factors remain contributing to worsening kidney function or even loss of transplants. We aimed to evaluate a new machine learning method to identify these variables which may predict the early graft loss in kidney transplant patients and to assess their usefulness for improving clinical decisions.

MATERIAL AND METHODS

A retrospective cohort study was carried out with 627 kidney transplant patients followed at least three months. All these data were pre-processed, and their selected features were used to develop an automatically working a machine learning algorithm; this algorithm was then applied for training and parameterization of the model; and finally, the tested model was then used for the analysis of patients' features that were the most impactful for the prediction of clinical outcomes. Our models were evaluated using the Area Under the Curve (AUC), and the SHapley Additive exPlanations (SHAP) algorithm was used to interpret its predictions.

RESULTS

The final selected model achieved a precision of 0.81, a sensitivity of 0.61, a specificity of 0.89, and an AUC value of 0.84. In our model, serum creatinine levels of kidney transplant patients, evaluated at the hospital discharge, proved to be the most important factor in the decision-making for the allograft loss. Patients with a weight equivalent to a BMI closer to the normal range prior to a kidney transplant are less likely to experience graft loss compared to patients with a BMI below the normal range. The age of patients at transplantation and Polyomavirus (BKPyV) infection had significant impact on clinical outcomes in our model.

CONCLUSIONS

Our algorithm suggests that the main characteristics that impacted early allograft loss were serum creatinine levels at the hospital discharge, as well as the pre-transplant values such as body weight, age of patients, and their BKPyV infection. We propose that machine learning tools can be developed to effectively assist medical decision-making in kidney transplantation.

Studying the effect of donor kidney volume ratios to recipients' body surface area, body mass index, and total body weight on post-transplant graft function

OBJECTIVES

The goal of this study was to retrospectively investigate the relationship between renal transplanted volume indexes (Total kidney volume (TKV)/Body surface area (BSA), Renal parenchymal volume (RPV)/BSA, Renal cortical volume (RCV)/BSA, RPV/Body mass index (BMI), RCV/BMI, RPV/Weight, RCV/Weight), and short- and long-term function of the graft.

METHODS

One-hundred and twelve live donor-recipient pairs from 2017 to 2018, whose donors underwent preoperative renal computed tomography angiography and recipients survived during 12 months of follow-up, were included in this study.

RESULTS

The crude and adjusted linear regressions for the effect of volume measurements by voxel and ellipsoid methods on the estimated glomerular filtration rate (eGFR) at different post-transplantation times demonstrated that the RPV/weight ratio had the most substantial crude effect on the eGFR 12 months and 4 years after renal transplant. Receiver operating characteristic (ROC) curves for six different renal volume ratios demonstrated no significant difference between these ratios in terms of discriminative ability (p value < 0.05). A strong direct correlation between TKV calculated by the ellipsoid formula with RPV and RCV measured using OsiriX software was noted. Analysis of ROC curves for renal volume indices has demonstrated fair to good discriminative ability of our cut-off points to estimate 4-year post-transplantation eGFR > 60 mL/min.

CONCLUSION

Renal transplant recipients' volume indices, such as RPV/weight, had strong correlations with eGFR at different points in time, and renal transplant recipients with the volume ratios higher than our cut-off points had a good chance of having a 4-year post-transplantation eGFR higher than 60 mL/min.

Predicting Long-term Outcomes in Deceased Donor Kidney Transplant Recipients Using Three Short-term Graft Characteristics

Key Points

Delayed graft function is not an ideal measure of graft function, yet is used to assess risk in kidney transplantation. We propose a model that combines it with two other measures of 90-day graft function to identify recipients at incremental risk of inferior long-term outcomes.

Background

Delayed graft function (DGF) in kidney transplant recipients is used to determine graft prognosis, make organ utilization decisions, and as an important end point in clinical trials. However, DGF is not an ideal measure of graft function. We aimed to develop and validate a model that provides incremental risk assessment for inferior patient and graft outcomes.

Methods

We included adult kidney-only deceased donor transplant recipients from 1996 to 2016. In addition to DGF, two short-term measures were used to assess risk: renal function recovery <100% (attaining half the donor's eGFR) and recipient's 90-day eGFR <30. Recipients were at no, low, moderate, or high risk if they met zero, one, two, or all criteria, respectively. Cox proportional hazard models were used to assess the independent relationship between exposure and death-censored graft failure (DCGF) and mortality.

Results

Of the 792 eligible recipients, 24.5% experienced DGF, 40.5% had renal function recovery <100%, and 6.9% had eGFR <30. Over a median follow-up of 7.3 years, the rate of DCGF was 18.7% and mortality was 25.1%. When compared with recipients at no risk, those at low, moderate, and high risk were noted to have an increase in risk of DCGF (adjusted hazard ratio [aHR], 1.53; 95% confidence interval [CI], 1.03 to 2.27; aHR, 2.84; 95% CI, 1.68 to 4.79; aHR, 15.46; 95% CI, 8.04 to 29.71) and mortality (aHR, 1.16; 95% CI, 0.84 to 1.58; aHR, 1.85; 95% CI, 1.13 to 3.07; aHR, 2.66; 95% CI, 1.19 to 5.97). When using a hierarchical approach, each additional exposure predicted the risk of DCGF better than DGF alone and 100 random bootstrap replications supported the internal validity of the risk model. In an external validation cohort deemed to be at lower risk of DCGF, similar nonsignificant trends were noted.

Conclusion

We propose a risk model that provides an incremental assessment of recipients at higher risk of adverse long-term outcomes than DGF alone. This can help advance the field of risk assessment in transplantation and inform therapeutic decision making in patients at the highest spectrum of inferior outcomes.

Kidney donation: bridging the gap in the shortage of kidney transplants in Malaysia

Purpose

The purpose of this study was to identify factors that affect willingness to donate kidneys posthumously among Malaysians.

Design/methodology/approach

A questionnaire-based cross-sectional study assessing demographics, attitude, spirituality, knowledge and willingness to donate a kidney was conducted among adult Malaysians with oral informed consent. The total number of samples was 1,001 respondents. Univariate and multivariate logistic regression was performed.

Findings

A total of 29.17% (n = 292) were willing to donate kidneys, while the remaining 70.83% (n = 709) were not. The mean spirituality score was 80.95 ± 13.79 (maximum score 100), mean attitude score was 52.88 ± 8.074 (maximum score 70) and mean knowledge score was 1.84 ± 0.99 (maximum score 5). A higher score demonstrated a stronger spiritual level, positive attitude and better knowledge. Factors affecting willingness to donate a kidney were ethnicity (odds ratio [OR] = 15.625, 95% confidence interval [CI] = 0.043–0.094) and attitude toward kidney donation score (OR = 0.924, 95% CI = 0.902–0.945).

Originality/value

Culture-specific steps to improve programs that may contribute toward improving kidney donation posthumously among Malaysians should be developed. Results drawn from this work demonstrate that policymakers, health-care workers and stakeholders should work together to promote effective policies and program implementation to reduce the ever-increasing gap between the need and shortage crisis of kidney donation.

Early estimated glomerular filtration rate and depression in kidney transplantation recipients: a longitudinal study

Depression is a common psychological problem in kidney transplantation (KT) recipients and affects long-term graft outcomes. Estimated glomerular filtration rate (eGFR) as a commonly used indicator of renal function plays a vital role in follow-up detection after KT. The aim of this study is to observe the change of early eGFR within 3 months after KT and to explore the correlation between eGFR and depression before and after transplantation. The Self-rating Depression Scale was used to evaluate depression. Among 135 patients with KT, 128 patients completed the longitudinal study. We used a one-way repeated-measures analysis of variance to analyze eGFR and a generalized estimating equation model to examine the relationship between depression and eGFR in KT recipients with pre-transplant and 30, 60, 90 days post-transplant. The mean eGFR of KT recipients at four time-points was 5.97 ± 4.83, 72.84 ± 26.06, 79.06 ± 26.45 and 81.79 ± 25.62, respectively. The results demonstrated that eGFR kept steady at 60 days and 90 days post-transplant; depression was significantly associated with eGFR. Earlier identification and treatment of depression in KT recipients may be essential to promote their recovery of early renal function.

Treatment of transplant kidneys during machine perfusion

The increasing use of donation after circulatory death (DCD) and extended criteria donor (ECD) organs has raised awareness of the need to improve the quality of kidneys for transplantation. Treating kidneys during the preservation interval could improve early and long-term graft function and survival. Dynamic modes of preservation including hypothermic machine perfusion (HMP) and normothermic machine perfusion (NMP) may provide the functional platforms to treat these kidneys. Therapies in the field of regenerative medicine including cellular therapies and genetic modification and the application of biological agents targeting ischaemia reperfusion injury (IRI) and acute rejection are a growing area of research. This review reports on the application of cellular and gene manipulating therapies, nanoparticles, anti-inflammatory agents, anti-thrombolytic agents and monoclonal antibodies administered during HMP and NMP in experimental models. The review also reports on the clinical effectiveness of several biological agents administered during HMP. All of the experimental studies provide proof of principle that therapies can be successfully delivered during HMP and NMP. However, few have examined the effects after transplantation. Evidence for clinical application during HMP is sparse and only one study has demonstrated a beneficial effect on graft function. More investigation is needed to develop perfusion strategies and investigate the different experimental approaches.

Role of Prior Split Renal Function for Living Kidney Transplantation in Recipients and Donors

PURPOSE

The purpose of this study was to determine the relationship between pre-operative donor split renal function (SRF) and the renal function outcome of donors and recipients after kidney transplantation (KT).

METHODS

A total of 217 living KT cases were investigated. The estimated glomerular filtration rate (eGFR) change of recipients and donors, as well as graft survival, were analyzed based on the donor SRF. The difference in SRF (dSRF) in a donor was defined as follows: the SRF of the donated kidney minus the SRF of the remaining kidney determined by pre-operative ^99mTc-diethylenetriaminepentaacetic acid in the donors. The dSRF was categorized into tertiles.

RESULTS

The dSRF was not associated with the eGFR in recipients in any tertile at 6 or 12 months post-KT. The overall graft and patient survival did not differ significantly among tertiles. Donors in the high tertile, who donated kidneys with a higher SRF, showed a greater reduction in eGFR than did donors in the low and middle tertile after adjustment for function of the not-donated kidney (-34 ± 1.9 vs -28 ± 2.2, and -27 ± 1.3 mL/min/1.73 m², P < .05).

CONCLUSIONS

The dSRF did not affect the post-KT renal function or graft survival in recipients. However, the donors who donated the better functioning kidney had a poorer renal function after donation.

Prognostic value for long-term graft survival of estimated glomerular filtration rate and proteinuria quantified at 3 months after kidney transplantation

Background

The estimated glomerular filtration rate (eGFR) measured at 1 year is the usual benchmark applied in kidney transplantation (KT). However, acting on earlier eGFR values could help in managing KT during the first post-operative year. We aimed to assess the prognostic value for long-term graft survival of the early (3 months) quantification of eGFR and proteinuria following KT.

Methods

The 3-, 6- and 12-month eGFR using the Modified Diet in Renal Disease equation (eGFR_MDRD) was determined and proteinuria was measured in 754 patients who underwent their first KT between 2000 and 2010 (with a mean follow-up of 8.3 years) in our centre. Adjusted associations with graft survival were estimated using a multivariable Cox model. The predictive accuracy was estimated using the C-index and net reclassification index. These same analyses were measured in a multicentre validation cohort of 1936 patients.

Results

Both 3-month eGFR_MDRD and proteinuria were independent predictors of return to dialysis (all P < 0.05) and there was a strong correlation between eGFR at 3 and 12 months (Spearman’s ρ = 0.76). The predictive accuracy of the 3-month eGFR was within a similar range and did not differ significantly from the 12-month eGFR in either the derivation cohort [C-index 62.6 (range 57.2–68.1) versus 66.0 (range 60.1–71.9), P = 0.41] or the validation cohort [C-index 69.3 (range 66.4–72.1) versus 71.7 (range 68.7–74.6), P = 0.25].

Conclusion

The 3-month eGFR was a valuable predictor of the long-term return to dialysis whose predictive accuracy was not significantly less than that of the 12-month eGFR in multicentre cohorts totalling >2500 patients. Three-month outcomes may be useful in randomized controlled trials targeting early therapeutic interventions.

Assessing Time of Full Renal Recovery Following Minimally Invasive Partial Nephrectomy

OBJECTIVE

To assess renal function in the operated kidney at different time points post partial nephrectomy (PN) and establish the time in which optimal recovery occurs. Recovery of renal function post-PN has received significant attention. However, the optimal time to determine full recovery has not been clearly established.

MATERIALS AND METHODS

Renal function following minimally invasive (laparoscopic and robotic) PNs performed between 2002 and 2015 was reviewed. Patients included in this study had renal function assessed preoperatively as well as 3 days, 6-12 weeks, and 1 year post-PN, using a combination of estimated glomerular filtration rate (eGFR) from serum creatinine and relative renal uptake (RRU) from Tc99m-MAG3 renal scintigraphy. Together, eGFR and RRU provide the ipsilateral renal function (IRF) of the operated organ.

RESULTS

At 6-12 weeks postoperatively, percent preserved eGFR, RRU, and IRF (relative to preoperative baselines) were 92.1%, 83.3%, and 77.4% respectively. %IRF at 6-12 weeks was significantly improved from %IRF at 3 days postoperatively, but did not differ significantly from 1 year postoperatively. Furthermore, 89% of patients had RRU values at 6-12 weeks which differed by less than 5% from RRU values at 1 year.

CONCLUSION

Our data suggest that renal function recovery at 6-12 weeks was equivalent to long-term recovery at 1 year in the majority of post-PN patients. This has important implications for post-PN follow-up, particularly in assessing the functional outcomes utilizing novel minimally invasive PN strategies, as well as in planning staged procedures for bilateral synchronous renal masses.

Big Data, Predictive Analytics, and Quality Improvement in Kidney Transplantation: A Proof of Concept

We sought proof of concept of a Big Data Solution incorporating longitudinal structured and unstructured patient-level data from electronic health records (EHR) to predict graft loss (GL) and mortality. For a quality improvement initiative, GL and mortality prediction models were constructed using baseline and follow-up data (0-90 days posttransplant; structured and unstructured for 1-year models; data up to 1 year for 3-year models) on adult solitary kidney transplant recipients transplanted during 2007-2015 as follows: Model 1: United Network for Organ Sharing (UNOS) data; Model 2: UNOS & Transplant Database (Tx Database) data; Model 3: UNOS, Tx Database & EHR comorbidity data; and Model 4: UNOS, Tx Database, EHR data, Posttransplant trajectory data, and unstructured data. A 10% 3-year GL rate was observed among 891 patients (2007-2015). Layering of data sources improved model performance; Model 1: area under the curve (AUC), 0.66; (95% confidence interval [CI]: 0.60, 0.72); Model 2: AUC, 0.68; (95% CI: 0.61-0.74); Model 3: AUC, 0.72; (95% CI: 0.66-077); Model 4: AUC, 0.84, (95 % CI: 0.79-0.89). One-year GL (AUC, 0.87; Model 4) and 3-year mortality (AUC, 0.84; Model 4) models performed similarly. A Big Data approach significantly adds efficacy to GL and mortality prediction models and is EHR deployable to optimize outcomes.