The impact of deceased donor maintenance on delayed kidney allograft function: A machine learning analysis

Effect of Cardiac Arrest in Brain-dead Donors on Kidney Graft Function

BACKGROUND

Cardiac arrest (CA) causes renal ischemia in one-third of brain-dead kidney donors before procurement. We hypothesized that the graft function depends on the time interval between CA and organ procurement.

METHODS

We conducted a retrospective population-based study on a prospectively curated database. We included 1469 kidney transplantations from donors with a history of resuscitated CA in 2015-2017 in France. CA was the cause of death (primary CA) or an intercurrent event (secondary CA). The main outcome was the percentage of delayed graft function, defined by the use of renal replacement therapy within the first week posttransplantation.

RESULTS

Delayed graft function occurred in 31.7% of kidney transplantations and was associated with donor function, vasopressors, cardiovascular history, donor and recipient age, body mass index, cold ischemia time, and time to procurement after primary cardiac arrest. Short cold ischemia time, perfusion device use, and the absence of cardiovascular comorbidities were protected by multivariate analysis, whereas time <3 d from primary CA to procurement was associated with delayed graft function (odds ratio 1.38).

CONCLUSIONS

This is the first description of time to procurement after a primary CA as a risk factor for delayed graft function. Delaying procurement after CA should be evaluated in interventional studies.

Clinical Deployment of Machine Learning Tools in Transplant Medicine: What Does the Future Hold?

Medical applications of machine learning (ML) have shown promise in analyzing patient data to support clinical decision-making and provide patient-specific outcomes. In transplantation, several applications of ML exist which include pretransplant: patient prioritization, donor-recipient matching, organ allocation, and posttransplant outcomes. Numerous studies have shown the development and utility of ML models, which have the potential to augment transplant medicine. Despite increasing efforts to develop robust ML models for clinical use, very few of these tools are deployed in the healthcare setting. Here, we summarize the current applications of ML in transplant and discuss a potential clinical deployment framework using examples in organ transplantation. We identified that creating an interdisciplinary team, curating a reliable dataset, addressing the barriers to implementation, and understanding current clinical evaluation models could help in deploying ML models into the transplant clinic setting.

Machine Learning Model to Predict Graft Rejection After Kidney Transplantation

BACKGROUND

There are few predictive studies about early posttransplant outcomes taking into account baseline and posttransplant variables. The objective of this study was to create a predictive model for 30-day graft rejection using machine learning techniques.

METHODS

Retrospective study with 1255 patients undergoing transplant from living and deceased donors at a tertiary health service in Brazil. Recipient, donor, transplantation, and postoperative period data were collected from physical and electronic records. We split the data into derivation (training) and validation (test) datasets. Five supervised machine learning algorithms were developed with this subset of variables in the training set: Simple Logistic Regression, Lasso, Multilayer Perceptron, XGBoost, and Light GBM.

RESULTS

There were 147 (12.48%) cases of graft rejection within 30 days of transplantation. The best model was XGBoost (accuracy, 0.839; receiver operating characteristic area under the curve, 0.715; precision, 0.900). The model showed that deceased donor transplantation, glomerulopathy as an underlying disease, and donor's use of vasoactive drugs had more than 20% importance as rejection risk factors. The variables with the greatest predictive values were thymoglobulin induction and delayed graft function.

CONCLUSIONS

We fitted a machine learning model to predict 30-day graft rejection after kidney transplantation that reaches a higher accuracy and precision. Machine learning models could contribute to predicting kidney survival using nontraditional approaches.

A Machine Learning Prediction Model for Immediate Graft Function After Deceased Donor Kidney Transplantation

BACKGROUND

After kidney transplantation (KTx), the graft can evolve from excellent immediate graft function (IGF) to total absence of function requiring dialysis. Recipients with IGF do not seem to benefit from using machine perfusion, an expensive procedure, in the long term when compared with cold storage. This study proposes to develop a prediction model for IGF in KTx deceased donor patients using machine learning algorithms.

METHODS

Unsensitized recipients who received their first KTx deceased donor between January 1, 2010, and December 31, 2019, were classified according to the conduct of renal function after transplantation. Variables related to the donor, recipient, kidney preservation, and immunology were used. The patients were randomly divided into 2 groups: 70% were assigned to the training and 30% to the test group. Popular machine learning algorithms were used: eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine, Gradient Boosting classifier, Logistic Regression, CatBoost classifier, AdaBoost classifier, and Random Forest classifier. Comparative performance analysis on the test dataset was performed using the results of the AUC values, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score.

RESULTS

Of the 859 patients, 21.7% (n = 186) had IGF. The best predictive performance resulted from the eXtreme Gradient Boosting model (AUC, 0.78; 95% CI, 0.71-0.84; sensitivity, 0.64; specificity, 0.78). Five variables with the highest predictive value were identified.

CONCLUSIONS

Our results indicated the possibility of creating a model for the prediction of IGF, enhancing the selection of patients who would benefit from an expensive treatment, as in the case of machine perfusion preservation.

Revisiting transplant immunology through the lens of single-cell technologies

Solid organ transplantation (SOT) is the standard of care for end-stage organ disease. The most frequent complication of SOT involves allograft rejection, which may occur via T cell- and/or antibody-mediated mechanisms. Diagnosis of rejection in the clinical setting requires an invasive biopsy as there are currently no reliable biomarkers to detect rejection episodes. Likewise, it is virtually impossible to identify patients who exhibit operational tolerance and may be candidates for reduced or complete withdrawal of immunosuppression. Emerging single-cell technologies, including cytometry by time-of-flight (CyTOF), imaging mass cytometry, and single-cell RNA sequencing, represent a new opportunity for deep characterization of pathogenic immune populations involved in both allograft rejection and tolerance in clinical samples. These techniques enable examination of both individual cellular phenotypes and cell-to-cell interactions, ultimately providing new insights into the complex pathophysiology of allograft rejection. However, working with these large, highly dimensional datasets requires expertise in advanced data processing and analysis using computational biology techniques. Machine learning algorithms represent an optimal strategy to analyze and create predictive models using these complex datasets and will likely be essential for future clinical application of patient level results based on single-cell data. Herein, we review the existing literature on single-cell techniques in the context of SOT.

Toward generalizing the use of artificial intelligence in nephrology and kidney transplantation

With its robust ability to integrate and learn from large sets of clinical data, artificial intelligence (AI) can now play a role in diagnosis, clinical decision making, and personalized medicine. It is probably the natural progression of traditional statistical techniques. Currently, there are many unmet needs in nephrology and, more particularly, in the kidney transplantation (KT) field. The complexity and increase in the amount of data, and the multitude of nephrology registries worldwide have enabled the explosive use of AI within the field. Nephrologists in many countries are already at the center of experiments and advances in this cutting-edge technology and our aim is to generalize the use of AI among nephrologists worldwide. In this paper, we provide an overview of AI from a medical perspective. We cover the core concepts of AI relevant to the practicing nephrologist in a consistent and simple way to help them get started, and we discuss the technical challenges. Finally, we focus on the KT field: the unmet needs and the potential role that AI can play to fill these gaps, then we summarize the published KT-related studies, including predictive factors used in each study, which will allow researchers to quickly focus on the most relevant issues.

The promise of machine learning applications in solid organ transplantation

Solid-organ transplantation is a life-saving treatment for end-stage organ disease in highly selected patients. Alongside the tremendous progress in the last several decades, new challenges have emerged. The growing disparity between organ demand and supply requires optimal patient/donor selection and matching. Improvements in long-term graft and patient survival require data-driven diagnosis and management of post-transplant complications. The growing abundance of clinical, genetic, radiologic, and metabolic data in transplantation has led to increasing interest in applying machine-learning (ML) tools that can uncover hidden patterns in large datasets. ML algorithms have been applied in predictive modeling of waitlist mortality, donor–recipient matching, survival prediction, post-transplant complications diagnosis, and prediction, aiming to optimize immunosuppression and management. In this review, we provide insight into the various applications of ML in transplant medicine, why these were used to evaluate a specific clinical question, and the potential of ML to transform the care of transplant recipients. 36 articles were selected after a comprehensive search of the following databases: Ovid MEDLINE; Ovid MEDLINE Epub Ahead of Print and In-Process & Other Non-Indexed Citations; Ovid Embase; Cochrane Database of Systematic Reviews (Ovid); and Cochrane Central Register of Controlled Trials (Ovid). In summary, these studies showed that ML techniques hold great potential to improve the outcome of transplant recipients. Future work is required to improve the interpretability of these algorithms, ensure generalizability through larger-scale external validation, and establishment of infrastructure to permit clinical integration.

Artificial Intelligence-A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant

Delayed-graft function (DGF) might be responsible for shorter graft survival. Therefore, a clinical tool predicting its occurrence is vital for the risk assessment of transplant outcomes. In a single-center study, we conducted data mining and machine learning experiments, resulting in DGF predictive models based on random forest classifiers (RF) and an artificial neural network called multi-layer perceptron (MLP). All designed models had four common input parameters, determining the best accuracy and discriminant ability: donor’s eGFR, recipient’s BMI, donor’s BMI, and recipient–donor weight difference. RF and MLP designs, using these parameters, achieved an accuracy of 84.38% and an area under curve (AUC) 0.84. The model additionally implementing a donor’s age, gender, and Kidney Donor Profile Index (KDPI) accomplished an accuracy of 93.75% and an AUC of 0.91. The other configuration with the estimated post-transplant survival (EPTS) and the kidney donor risk profile (KDRI) achieved an accuracy of 93.75% and an AUC of 0.92. Using machine learning, we were able to assess the risk of DGF in recipients after kidney transplant from a deceased donor. Our solution is scalable and can be improved during subsequent transplants. Based on the new data, the models can achieve better outcomes.

Comparative analysis of kidney transplant costs related to recovery of renal function after the procedure

Introduction:

The number of kidney transplants (KTx) is increasing in Brazil and, consequently, the costs of this procedure increase the country's health budget. We retrospectively evaluated the data of kidney transplant procedures until hospital discharge, according to kidney function recovery after the procedure.

Methods:

Retrospective analysis of the non-sensitized, 1st KTx from deceased donors performed between Jan/2010 to Dec/2017.

Results:

Out of the 1300 KTx from deceased donors performed in this period, 730 patients were studied and divided into 3 groups: Immediate Renal Function (IRF) - decrease in serum creatinine ≥ 10% on two consecutive days; Delayed Graft Function (DGF) - decrease in serum creatinine <10% on two consecutive days, without the need for dialysis, and Dialysis (D) - need for dialysis during the first week. Patients in group D stayed longer in the hospital compared to DGF and IRF (21, 11 and 8 days respectively, p < 0.001). More D patients (21%) were admitted to the ICU and performed a greater number of laboratory tests (p < 0.001) and renal biopsies (p < 0.001), in addition to receiving a higher amount of immunosuppressants. Total hospital costs were higher in group D and DGF compared to IRF (U$ 7.021,48; U$ 3.603,42 and U$ 2.642,37 respectively, p < 0.001).

Conclusion:

The costs of the transplant procedure is impacted by the recovery of kidney function after the transplant. The reimbursement for each of these different kidney function outcomes should be individualized in order to cover their real costs.

Artificial intelligence and kidney transplantation

Artificial intelligence and its primary subfield, machine learning, have started to gain widespread use in medicine, including the field of kidney transplantation. We made a review of the literature that used artificial intelligence techniques in kidney transplantation. We located six main areas of kidney transplantation that artificial intelligence studies are focused on: Radiological evaluation of the allograft, pathological evaluation including molecular evaluation of the tissue, prediction of graft survival, optimizing the dose of immunosuppression, diagnosis of rejection, and prediction of early graft function. Machine learning techniques provide increased automation leading to faster evaluation and standardization, and show better performance compared to traditional statistical analysis. Artificial intelligence leads to improved computer-aided diagnostics and quantifiable personalized predictions that will improve personalized patient care.

Exploring the causes of the high incidence of delayed graft function after kidney transplantation in Brazil: a multicenter study

This retrospective multicenter (n = 18) cohort study evaluated the incidence, risk factors, and the impact of delayed graft function (DGF) on 1-year kidney transplant (KT) outcomes. Of 3992 deceased donor KT performed in 2014-2015, the incidence of DGF was 54%, ranging from 29.9% to 87.7% among centers. Risk factors (_{lower-bound-95%CI} OR _{upper-bound-95%CI} ) were male gender (_1.066 1.249_1.463 ), diabetic kidney disease (_1.053 1.296_1.595 ), time on dialysis (_1.005 1.007_1.009 ), retransplantation (_1.035 1.397_1.885 ), preformed anti-HLA antibodies (_1.011 1.383_1.892 ), HLA mismatches (_1.006 1.066_1.130 ), donor age (_1.011 1.017_1.023 ), donor final serum creatinine (sCr) (_1.239 1.317_1.399 ), cold ischemia time (CIT) (_1.031 1.043_1.056 ), machine perfusion (_0.401 0.542_0.733 ), and induction therapy with rabbit antithymocyte globulin (rATG) (_0.658 0.800_0.973 ). Duration of DGF > 4 days was associated with inferior renal function and DGF > 14 days with the higher incidences of acute rejection, graft loss, and death. In conclusion, the incidence and duration of DGF were high and associated with inferior graft outcomes. While late referral and poor donor maintenance account for the high overall incidence of DGF, variability in donor and recipient selection, organ preservation method, and type of induction agent may account for the wide variation observed among transplant centers.

How will artificial intelligence and bioinformatics change our understanding of IgA Nephropathy in the next decade?

IgA nephropathy (IgAN) is the most common glomerulonephritis. It is characterized by the deposition of immune complexes containing immunoglobulin A (IgA) in the kidney’s glomeruli, triggering an inflammatory process. In many patients, the disease has a progressive course, eventually leading to end-stage kidney disease. The current understanding of IgAN’s pathophysiology is incomplete, with the involvement of several potential players, including the mucosal immune system, the complement system, and the microbiome. Dissecting this complex pathophysiology requires an integrated analysis across molecular, cellular, and organ scales. Such data can be obtained by employing emerging technologies, including single-cell sequencing, next-generation sequencing, proteomics, and complex imaging approaches. These techniques generate complex “big data,” requiring advanced computational methods for their analyses and interpretation. Here, we introduce such methods, focusing on the broad areas of bioinformatics and artificial intelligence and discuss how they can advance our understanding of IgAN and ultimately improve patient care. The close integration of advanced experimental and computational technologies with medical and clinical expertise is essential to improve our understanding of human diseases. We argue that IgAN is a paradigmatic disease to demonstrate the value of such a multidisciplinary approach.

Toward Advancing Long-Term Outcomes of Kidney Transplantation with Artificial Intelligence

After decades of pioneering advances and improvements, kidney transplantation is now the renal replacement therapy of choice for most patients with end-stage kidney disease (ESKD). Despite this success, the high risk of premature death and frequent occurrence of graft failure remain important clinical and research challenges. The current burst of studies and other innovative initiatives using artificial intelligence (AI) for a wide range of analytical and practical applications in biomedical areas seems to correlate with the same trend observed in publications in the kidney transplantation field, and points toward the potential of such novel approaches to address the aforementioned aim of improving long-term outcomes of kidney transplant recipients (KTR). However, at the same time, this trend underscores now more than ever the old methodological challenges and potential threats that the research and clinical community needs to be aware of and actively look after with regard to AI-driven evidence. The purpose of this narrative mini-review is to explore challenges for obtaining applicable and adequate kidney transplant data for analyses using AI techniques to develop prediction models, and to propose next steps in the field. We make a call to act toward establishing the strong collaborations needed to bring innovative synergies further augmented by AI, which have the potential to impact the long-term care of KTR. We encourage researchers and clinicians to submit their invaluable research, including original clinical and imaging studies, database studies from registries, meta-analyses, and AI research in the kidney transplantation field.

The Impact of Hypothermic Pulsatile Machine Perfusion Versus Static Cold Storage: A Donor-Matched Paired Analysis in a Scenario of High Incidence of Delayed Kidney Graft Function

BACKGROUND The present study analyzed the impact of hypothermic pulsatile machine perfusion (MP) following a long period of static cold (SC) storage in the peculiar Brazilian scenario of high incidence of delayed graft function (DGF), despite good donor characteristics. MATERIAL AND METHODS A retrospective analysis, with a 1-year follow-up, of 206 recipients of donor-matched paired kidneys was performed. Of the 206 donor kidneys, 103 were maintained exclusively in static cold storage (SC group) and 103 were kept on machine perfusion after a period of SC preservation (MP group). All donors were brain dead. RESULTS Only 4.9% of the kidneys were from expanded-criteria donors. Static cold ischemia time (CIT) in the SC group was 20.8±4.1 hours vs. 15.8±6.2 hours in the MP group (P<0.001). Dynamic CIT in the MP group was 12.3±5.7 hours. MP significantly reduced DGF incidence (29.1% vs. 55.3%, P<0.001), and this effect was confirmed in multivariable analysis (OR, 1.115; 95% CI, 1.033-1.204, P=0.001). No differences were observed between the groups with regard to DGF duration, length of hospital stay, incidence of primary nonfunction and acute rejection, graft loss, death, or renal function. CONCLUSIONS In this Brazilian setting, MP following a long period of SC preservation was associated with reduced DGF incidence in comparison with SC storage without MP.

Proposal of a new equation for estimating resting energy expenditure of acute kidney injury patients on dialysis: a machine learning approach

Background

The objective of this study was to develop a new predictive equation of resting energy expenditure (REE) for acute kidney injury patients (AKI) on dialysis.

Materials and methods

A cross-sectional descriptive study was carried out of 114 AKI patients, consecutively selected, on dialysis and mechanical ventilation, aged between 19 and 95 years. For construction of the predictive model, 80% of cases were randomly separated to training and 20% of unused cases to validation. Several machine learning models were tested in the training data: linear regression with stepwise, rpart, support vector machine with radial kernel, generalised boosting machine and random forest. The models were selected by ten-fold cross-validation and the performances evaluated by the root mean square error.

Results

There were 364 indirect calorimetry measurements in 114 patients, mean age of 60.65 ± 16.9 years and 68.4% were males. The average REE was 2081 ± 645 kcal. REE was positively correlated with C-reactive protein, minute volume (MV), expiratory positive airway pressure, serum urea, body mass index and inversely with age. The principal variables included in the selected model were age, body mass index, use of vasopressors, expiratory positive airway pressure, MV, C-reactive protein, temperature and serum urea. The final r-value in the validation set was 0.69.

Conclusion

We propose a new predictive equation for estimating the REE of AKI patients on dialysis that uses a non-linear approach with better performance than actual models.