Prediction of graft survival of living-donor kidney transplantation: nomograms or artificial neural networks? Transplantation. 2008;86:1401-1406. [PMID: 19034010 DOI: 10.1097/tp.0b013e31818b221f]

Cherry on Top or Real Need? A Review of Explainable Machine Learning in Kidney Transplantation

Research on solid organ transplantation has taken advantage of the substantial acquisition of medical data and the use of artificial intelligence (AI) and machine learning (ML) to answer diagnostic, prognostic, and therapeutic questions for many years. Nevertheless, despite the question of whether AI models add value to traditional modeling approaches, such as regression models, their "black box" nature is one of the factors that have hindered the translation from research to clinical practice. Several techniques that make such models understandable to humans were developed with the promise of increasing transparency in the support of medical decision-making. These techniques should help AI to close the gap between theory and practice by yielding trust in the model by doctors and patients, allowing model auditing, and facilitating compliance with emergent AI regulations. But is this also happening in the field of kidney transplantation? This review reports the use and explanation of "black box" models to diagnose and predict kidney allograft rejection, delayed graft function, graft failure, and other related outcomes after kidney transplantation. In particular, we emphasize the discussion on the need (or not) to explain ML models for biological discovery and clinical implementation in kidney transplantation. We also discuss promising future research paths for these computational tools.

Predicting long-term outcomes of kidney transplantation in the era of artificial intelligence

The ability to accurately predict long-term kidney transplant survival can assist nephrologists in making therapeutic decisions. However, predicting kidney transplantation (KT) outcomes is challenging due to the complexity of the factors involved. Artificial intelligence (AI) has become an increasingly important tool in the prediction of medical outcomes. Our goal was to utilize both conventional and AI-based methods to predict long-term kidney transplant survival. Our study included 407 KTs divided into two groups (group A: with a graft lifespan greater than 5 years and group B: with poor graft survival). We first performed a traditional statistical analysis and then developed predictive models using machine learning (ML) techniques. Donors in group A were significantly younger. The use of Mycophenolate Mofetil (MMF) was the only immunosuppressive drug that was significantly associated with improved graft survival. The average estimated glomerular filtration rate (eGFR) in the 3rd month post-KT was significantly higher in group A. The number of hospital readmissions during the 1st year post-KT was a predictor of graft survival. In terms of early post-transplant complications, delayed graft function (DGF), acute kidney injury (AKI), and acute rejection (AR) were significantly associated with poor graft survival. Among the 35 AI models developed, the best model had an AUC of 89.7% (Se: 91.9%; Sp: 87.5%). It was based on ten variables selected by an ML algorithm, with the most important being hypertension and a history of red-blood-cell transfusion. The use of AI provided us with a robust model enabling fast and precise prediction of 5-year graft survival using early and easily collectible variables. Our model can be used as a decision-support tool to early detect graft status.

Application of nanotechnology in breast cancer screening under obstetrics and gynecology through the use of CNN and ANFIS

Breast cancer is the leading reason of death among women aged 35 to 54. Breast cancer diagnosis still presents significant challenges, and preventing the disease's most severe symptoms requires early detection. The role of nanotechnology in the tumor-treatment has recently attracted a lot of interest. In cancer therapies, nanotechnology plays a major role in the medication distribution process. Nanoparticles have the ability to target tumors. Nanoparticles are favorable and maybe preferable for usage in tumor detection and imaging due to their incredibly small size. Quantum dots, semiconductor crystals with increased labeling and imaging capabilities for cancer cells, are one of the particles that have received the most research attention. The design of the research is cross-sectional and descriptive. From April through September of 2020, data were gathered at the State Hospital. All pregnant women who came to the hospital throughout the first and second trimesters of the research's data collection were included in the study population. 100 pregnant women between the ages of 20 and 40 who had not yet had a mammogram comprised the research sample. 1100 digitized mammography images are included in the dataset, which was obtained from a hospital. Convolutional neural networks (CNN) were used to scan all images, and breast masses and mass comparisons were made using the malignant-benign categorization. The adaptive neuro-fuzzy inference system (ANFIS) then examined all of the data obtained by CNN in order to identify breast cancer early using inputs based on the nine different inputs. The precision of the mechanism used in this technique to determine the ideal radius value is significantly impacted by the radius value. Nine variables that define breast cancer indicators were utilized as inputs to the ANFIS classifier, which was then used to identify breast cancer. The parameters were given the necessary fuzzy functions, and the combined dataset was applied to train the method. Testing was initially performed by 30% of dataset that was later done with the real data obtained from the hospital. The accuracy of the results for 30% data was 84% (specificity =72.7%, sensitivity =86.7%) and the results for the real data was 89.8% (sensitivity =82.3%, specificity =75.9%), respectively.

Machine learning models in predicting graft survival in kidney transplantation: meta-analysis

BACKGROUND

The variations in outcome and frequent occurrence of kidney allograft failure continue to pose important clinical and research challenges despite recent advances in kidney transplantation. The aim of this systematic review was to examine the current application of machine learning models in kidney transplantation and perform a meta-analysis of these models in the prediction of graft survival.

METHODS

This review was registered with the PROSPERO database (CRD42021247469) and all peer-reviewed original articles that reported machine learning model-based prediction of graft survival were included. Quality assessment was performed by the criteria defined by Qiao and risk-of-bias assessment was performed using the PROBAST tool. The diagnostic performance of the meta-analysis was assessed by a meta-analysis of the area under the receiver operating characteristic curve and a hierarchical summary receiver operating characteristic plot.

RESULTS

A total of 31 studies met the inclusion criteria for the review and 27 studies were included in the meta-analysis. Twenty-nine different machine learning models were used to predict graft survival in the included studies. Nine studies compared the predictive performance of machine learning models with traditional regression methods. Five studies had a high risk of bias and three studies had an unclear risk of bias. The area under the hierarchical summary receiver operating characteristic curve was 0.82 and the summary sensitivity and specificity of machine learning-based models were 0.81 (95 per cent c.i. 0.76 to 0.86) and 0.81 (95 per cent c.i. 0.74 to 0.86) respectively for the overall model. The diagnostic odds ratio for the overall model was 18.24 (95 per cent c.i. 11.00 to 30.16) and 29.27 (95 per cent c.i. 13.22 to 44.46) based on the sensitivity analyses.

CONCLUSION

Prediction models using machine learning methods may improve the prediction of outcomes after kidney transplantation by the integration of the vast amounts of non-linear data.

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.

Machine learning support for decision making in kidney transplantation: step-by-step development of a technological solution (Preprint)

Background

Kidney transplantation is the preferred treatment option for patients with end-stage renal disease. To maximize patient and graft survival, the allocation of donor organs to potential recipients requires careful consideration.

Objective

This study aimed to develop an innovative technological solution to enable better prediction of kidney transplant survival for each potential donor-recipient pair.

Methods

We used deidentified data on past organ donors, recipients, and transplant outcomes in the United States from the Scientific Registry of Transplant Recipients. To predict transplant outcomes for potential donor-recipient pairs, we used several survival analysis models, including regression analysis (Cox proportional hazards), random survival forests, and several artificial neural networks (DeepSurv, DeepHit, and recurrent neural network [RNN]). We evaluated the performance of each model in terms of its ability to predict the probability of graft survival after kidney transplantation from deceased donors. Three metrics were used: the C-index, integrated Brier score, and integrated calibration index, along with calibration plots.

Results

On the basis of the C-index metrics, the neural network–based models (DeepSurv, DeepHit, and RNN) had better discriminative ability than the Cox model and random survival forest model (0.650, 0.661, and 0.659 vs 0.646 and 0.644, respectively). The proposed RNN model offered a compromise between the good discriminative ability and calibration and was implemented in a technological solution of technology readiness level 4.

Conclusions

Our technological solution based on the RNN model can effectively predict kidney transplant survival and provide support for medical professionals and candidate recipients in determining the most optimal donor-recipient pair.

Determining the Level of Importance of Variables in Predicting Kidney Transplant Survival Based on a Novel Ranking Method

BACKGROUND

Kidney transplantation is the best alternative treatment for end-stage renal disease. To optimal use of donated kidneys, graft predicted survival can be used as a factor to allocate kidneys. The performance of prediction techniques is highly dependent on the correct selection of predictors. Hence, the main objective of this research is to propose a novel method for ranking the effective variables for predicting the kidney transplant survival.

METHODS

Five classification models were used to classify kidney recipients in long- and short-term survival classes. Synthetic minority oversampling and random undersampling were used to overcome the imbalanced class problem. In dealing with missing values, 2 approaches were used (eliminating and imputing them). All variables were categorized into 4 levels. The ranking was evaluated using the sensitivity analysis approach.

RESULTS

Thirty-four of the 41 variables were identified as important variables, of which, 5 variables were categorized in very important level ("Recipient creatinine at discharge," "Recipient dialysis time," "Donor history of diabetes," "Donor kidney biopsy," and "Donor cause of death"), 17 variables in important level, and 12 variables in the low important level.

CONCLUSIONS

In this study, we identify new variables that have not been addressed in any of the previous studies (eg, AGE_DIF and MATCH_GEN). On the other hand, in kidney allocation systems, 2 main criteria are considered: equity and utility. One of the utility subcriteria is the graft survival. Our study findings can be used in the design of systems to predict the graft survival.

Evaluation of Salivary Indoxyl Sulfate with Proteinuria for Predicting Graft Deterioration in Kidney Transplant Recipients

Acute kidney injury (AKI) is a significant risk factor for developing chronic kidney disease and progression to end-stage renal disease in elderly patients. AKI is also a relatively common complication after kidney transplantation (KTx) associated with graft failure. Since the lifespan of a transplanted kidney is limited, the risk of the loss/deterioration of graft function (DoGF) should be estimated to apply the preventive treatment. The collection of saliva and urine is more convenient than collecting blood and can be performed at home. The study aimed to verify whether non-invasive biomarkers, determined in saliva and urine, may be useful in the prediction of DoGF in kidney transplant recipients (KTRs) (n = 92). Salivary and serum toxins (p-cresol sulfate, pCS; indoxyl sulfate, IS) concentrations were determined using liquid chromatography-tandem mass spectrometry (LC-MS/MS). Urinary proteins, hemoglobin, and glucose were measured using a semi-quantitative strip test. Salivary IS (odds ratio (OR) = 1.19), and proteinuria (OR = 3.69) were demonstrated as independent factors for the prediction of DoGF. Satisfactory discriminatory power (area under the receiver operating characteristic curve (AUC) = 0.71 ± 0.07) and calibration of the model were obtained. The model showed that categories of the increasing probability of the risk of DoGF are associated with the decreased risk of graft survival. The non-invasive diagnostic biomarkers are a useful screening tool to identify high-risk patients for DoGF.

The Future Role of Machine Learning in Clinical Transplantation

The use of artificial intelligence and machine learning (ML) has revolutionized our daily lives and will soon be instrumental in healthcare delivery. The rise of ML is due to multiple factors: increasing access to massive datasets, exponential increases in processing power, and key algorithmic developments that allow ML models to tackle increasingly challenging questions. Progressively more transplantation research is exploring the potential utility of ML models throughout the patient journey, although this has not yet widely transitioned into the clinical domain. In this review, we explore common approaches used in ML in solid organ clinical transplantation and consider opportunities for ML to help clinicians and patients. We discuss ways in which ML can aid leverage of large complex datasets, generate cutting-edge prediction models, perform clinical image analysis, discover novel markers in molecular data, and fuse datasets to generate novel insights in modern transplantation practice. We focus on key areas in transplantation in which ML is driving progress, explore the future potential roles of ML, and discuss the challenges and limitations of these powerful tools.

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.

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.

Machine learning for predicting long-term kidney allograft survival: a scoping review

Supervised machine learning (ML) is a class of algorithms that "learn" from existing input-output pairs, which is gaining popularity in pattern recognition for classification and prediction problems. In this scoping review, we examined the use of supervised ML algorithms for the prediction of long-term allograft survival in kidney transplant recipients. Data sources included PubMed, the Cumulative Index to Nursing and Allied Health Literature, and the Institute for Electrical and Electronics Engineers (IEEE) Xplore libraries from inception to November 2019. We screened titles and abstracts and potentially eligible full-text reports to select studies and subsequently abstracted the data. Eleven studies were identified. Decision trees were the most commonly used method (n = 8), followed by artificial neural networks (ANN) (n = 4) and Bayesian belief networks (n = 2). The area under receiver operating curve (AUC) was the most common measure of discrimination (n = 7), followed by sensitivity (n = 5) and specificity (n = 4). Model calibration examining the reliability in risk prediction was performed using either the Pearson r or the Hosmer-Lemeshow test in four studies. One study showed that logistic regression had comparable performance to ANN, while another study demonstrated that ANN performed better in terms of sensitivity, specificity, and accuracy, as compared with a Cox proportional hazards model. We synthesized the evidence related to the comparison of ML techniques with traditional statistical approaches for prediction of long-term allograft survival in patients with a kidney transplant. The methodological and reporting quality of included studies was poor. Our study also demonstrated mixed results in terms of the predictive potential of the models.

Use of the Living Kidney Donor Profile Index in the Canadian Kidney Transplant Recipient Population: A Validation Study

Background:

The Living Kidney Donor Profile Index (LKDPI) was derived in a cohort of kidney transplant recipients (KTR) from the United States to predict the risk of total graft failure. There are important differences in patient demographics, listing practices, access to transplantation, delivery of care, and posttransplant mortality in Canada as compared with the United States, and the generalizability of the LKDPI in the Canadian context is unknown.

Objective:

The purpose of this study was to externally validate the LKDPI in a large contemporary cohort of Canadian KTR.

Design:

Retrospective cohort validation study.

Setting:

Toronto General Hospital, University Health Network, Toronto, Ontario, Canada

Patients:

A total of 645 adult (≥18 years old) living donor KTR between January 1, 2006 and December 31, 2016 with follow-up until December 31, 2017 were included in the study.

Measurements:

The predictive performance of the LKDPI was evaluated. The outcome of interest was total graft failure, defined as the need for chronic dialysis, retransplantation, or death with graft function.

Methods:

The Cox proportional hazards model was used to examine the relation between the LKDPI and total graft failure. The Cox proportional hazards model was also used for external validation and performance assessment of the model. Discrimination and calibration were used to assess model performance. Discrimination was assessed using Harrell’s C statistic and calibration was assessed graphically, comparing observed versus predicted probabilities of total graft failure.

Results:

A total of 645 living donor KTR were included in the study. The median LKDPI score was 13 (interquartile range [IQR] = 1.1, 29.9). Higher LKDPI scores were associated with an increased risk of total graft failure (hazard ratio = 1.01; 95% confidence interval [CI] = 1.0-1.02; P = .02). Discrimination was poor (C statistic = 0.55; 95% CI = 0.48-0.61). Calibration was as good at 1-year posttransplant but suboptimal at 3- and 5-years posttransplant.

Limitations:

Limitations include a relatively small sample size, predicted probabilities for assessment of calibration only available for scores of 0 to 100, and some missing data handled by imputation.

Conclusions:

In this external validation study, the predictive ability of the LKDPI was modest in a cohort of Canadian KTR. Validation of prediction models is an important step to assess performance in external populations. Potential recalibration of the LKDPI may be useful prior to clinical use in external cohorts.

Using machine learning techniques to develop risk prediction models to predict graft failure following kidney transplantation: protocol for a retrospective cohort study

Background: A mechanism to predict graft failure before the actual kidney transplantation occurs is crucial to clinical management of chronic kidney disease patients.  Several kidney graft outcome prediction models, developed using machine learning methods, are available in the literature.  However, most of those models used small datasets and none of the machine learning-based prediction models available in the medical literature modelled time-to-event (survival) information, but instead used the binary outcome of failure or not. The objective of this study is to develop two separate machine learning-based predictive models to predict graft failure following live and deceased donor kidney transplant, using time-to-event data in a large national dataset from Australia.   Methods: The dataset provided by the Australia and New Zealand Dialysis and Transplant Registry will be used for the analysis. This retrospective dataset contains the cohort of patients who underwent a kidney transplant in Australia from January 1 st, 2007, to December 31 st, 2017.  This included 3,758 live donor transplants and 7,365 deceased donor transplants.  Three machine learning methods (survival tree, random survival forest and survival support vector machine) and one traditional regression method, Cox proportional regression, will be used to develop the two predictive models.  The best predictive model will be selected based on the model's performance. Discussion: This protocol describes the development of two separate machine learning-based predictive models to predict graft failure following live and deceased donor kidney transplant, using a large national dataset from Australia.   Furthermore, these two models will be the most comprehensive kidney graft failure predictive models that have used survival data to model using machine learning techniques.  Thus, these models are expected to provide valuable insight into the complex interactions between graft failure and donor and recipient characteristics.

Using machine learning techniques to develop risk prediction models to predict graft failure following kidney transplantation: protocol for a retrospective cohort study

Background: A mechanism to predict graft failure before the actual kidney transplantation occurs is crucial to clinical management of chronic kidney disease patients.  Several kidney graft outcome prediction models, developed using machine learning methods, are available in the literature.  However, most of those models used small datasets and none of the machine learning-based prediction models available in the medical literature modelled time-to-event (survival) information, but instead used the binary outcome of failure or not. The objective of this study is to develop two separate machine learning-based predictive models to predict graft failure following live and deceased donor kidney transplant, using time-to-event data in a large national dataset from Australia.   Methods: The dataset provided by the Australia and New Zealand Dialysis and Transplant Registry will be used for the analysis. This retrospective dataset contains the cohort of patients who underwent a kidney transplant in Australia from January 1 st, 2007, to December 31 st, 2017. This included 3,758 live donor transplants and 7,365 deceased donor transplants. Three machine learning methods (survival tree, random survival forest and survival support vector machine) and one traditional regression method, Cox proportional regression, will be used to develop the two predictive models (for live donor and deceased donor transplants). The best predictive model will be selected based on the model's performance. Discussion: This protocol describes the development of two separate machine learning-based predictive models to predict graft failure following live and deceased donor kidney transplant, using a large national dataset from Australia. Furthermore, these two models will be the most comprehensive kidney graft failure predictive models that have used survival data to model using machine learning techniques. Thus, these models are expected to provide valuable insight into the complex interactions between graft failure and donor and recipient characteristics.

Machine learning in predicting graft failure following kidney transplantation: A systematic review of published predictive models

INTRODUCTION

Machine learning has been increasingly used to develop predictive models to diagnose different disease conditions. The heterogeneity of the kidney transplant population makes predicting graft outcomes extremely challenging. Several kidney graft outcome prediction models have been developed using machine learning, and are available in the literature. However, a systematic review of machine learning based prediction methods applied to kidney transplant has not been done to date. The main aim of our study was to perform an in-depth systematic analysis of different machine learning methods used to predict graft outcomes among kidney transplant patients, and assess their usefulness as an aid to decision-making.

METHODS

A systemic review of machine learning methods used to predict graft outcomes among kidney transplant patients was carried out using a search of the Medline, the Cumulative Index to Nursing and Allied Health Literature, EMBASE, PsycINFO and Cochrane databases.

RESULTS

A total of 295 articles were identified and extracted. Of these, 18 met the inclusion criteria. Most of the studies were published in the United States after 2010. The population size used to develop the models varied from 80 to 92,844, and the number of features in the models ranged from 6 to 71. The most common machine learning methods used were artificial neural networks, decision trees and Bayesian belief networks. Most of the machine learning based predictive models predicted graft failure with high sensitivity and specificity. Only one machine learning based prediction model had modelled time-to-event (survival) information. Seven studies compared the predictive performance of machine learning models with traditional regression methods and the performance of machine learning methods was found to be mixed, when compared with traditional regression methods.

CONCLUSION

There was a wide variation in the size of the study population and the input variables used. However, the prediction accuracy provided mixed results when machine learning and traditional predictive methods are compared. Based on reported gains in predictive performance, machine learning has the potential to improve kidney transplant outcome prediction and aid medical decision making.

Prediction of delayed graft function after kidney transplantation: comparison between logistic regression and machine learning methods

Background

Predictive models for delayed graft function (DGF) after kidney transplantation are usually developed using logistic regression. We want to evaluate the value of machine learning methods in the prediction of DGF.

Methods

497 kidney transplantations from deceased donors at the Ghent University Hospital between 2005 and 2011 are included. A feature elimination procedure is applied to determine the optimal number of features, resulting in 20 selected parameters (24 parameters after conversion to indicator parameters) out of 55 retrospectively collected parameters. Subsequently, 9 distinct types of predictive models are fitted using the reduced data set: logistic regression (LR), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), support vector machines (SVMs; using linear, radial basis function and polynomial kernels), decision tree (DT), random forest (RF), and stochastic gradient boosting (SGB). Performance of the models is assessed by computing sensitivity, positive predictive values and area under the receiver operating characteristic curve (AUROC) after 10-fold stratified cross-validation. AUROCs of the models are pairwise compared using Wilcoxon signed-rank test.

Results

The observed incidence of DGF is 12.5 %. DT is not able to discriminate between recipients with and without DGF (AUROC of 52.5 %) and is inferior to the other methods. SGB, RF and polynomial SVM are mainly able to identify recipients without DGF (AUROC of 77.2, 73.9 and 79.8 %, respectively) and only outperform DT. LDA, QDA, radial SVM and LR also have the ability to identify recipients with DGF, resulting in higher discriminative capacity (AUROC of 82.2, 79.6, 83.3 and 81.7 %, respectively), which outperforms DT and RF. Linear SVM has the highest discriminative capacity (AUROC of 84.3 %), outperforming each method, except for radial SVM, polynomial SVM and LDA. However, it is the only method superior to LR.

Conclusions

The discriminative capacities of LDA, linear SVM, radial SVM and LR are the only ones above 80 %. None of the pairwise AUROC comparisons between these models is statistically significant, except linear SVM outperforming LR. Additionally, the sensitivity of linear SVM to identify recipients with DGF is amongst the three highest of all models. Due to both reasons, the authors believe that linear SVM is most appropriate to predict DGF.

Clinical decision support system for end-stage kidney disease risk estimation in IgA nephropathy patients

BACKGROUND

The progression of IgA nephropathy (IgAN) to end-stage kidney disease (ESKD) depends on several factors that are not quite clear and tangle the risk assessment. We aimed at developing a clinical decision support system (CDSS) for a quantitative risk assessment of ESKD and its timing using available clinical data at the time of renal biopsy.

METHODS

We included a total of 1040 biopsy-proven IgAN patients with long-term follow-up from Italy (N = 546), Norway (N = 441) and Japan (N = 53). Of these, 241 patients reached ESKD: 104 Italian [median time to ESKD = 5 (3-9) years], 134 Norwegian [median time to ESKD = 6 (2-11) years] and 3 Japanese [median time to ESKD = 3 (2-12) years]. We independently trained and validated two cooperating artificial neural networks (ANNs) for predicting first the ESKD status and then the time to ESKD (defined as three categories: ≤ 3 years, between > 3 and 8 years and over 8 years). As inputs we used gender, age, histological grading, serum creatinine, 24-h proteinuria and hypertension at the time of renal biopsy.

RESULTS

The ANNs demonstrated high performance for both the prediction of ESKD (with an AUC of 89.9, 93.3 and 100% in the Italian, Norwegian and Japanese IgAN population, respectively) and its timing (f-measure of 90.7% in the cohort from Italy and 70.8% in the one from Norway). We embedded the two ANNs in a CDSS available online (www.igan.net). Entering the clinical parameters at the time of renal biopsy, the CDSS returns as output the estimated risk and timing of ESKD for the patient.

CONCLUSIONS

This CDSS provides useful additional information for identifying 'high-risk' IgAN patients and may help stratify them in the context of a personalized medicine approach.

The Kidney Transplant Morbidity Index (KTMI): A Simple Prognostic Tool to Help Determine Outcome Risk in Kidney Transplant Candidates

Background

The Kidney Transplant Morbidity Index (KTMI) is a novel prognostic morbidity index to help determine the impact that pretransplant comorbid conditions have on transplant outcome.

Objective

To use national data to validate the KTMI.

Design

Retrospective analysis of the Organ Procurement and Transplant Network/United Network for Organ Sharing database.

Setting and Participants

The study sample consisted of 100 261 adult patients who received a kidney transplant between 2000 and 2008.

Main Outcome Measure

Kaplan-Meier survival curves were used to demonstrate 3-year graft and patient survival for each KTMI score. Cox proportional hazards regression models were created to determine hazards for 3-year graft failure and patient mortality for each KTMI score.

Results

A sequential decrease in graft survival (0 = 91.2%, 1 = 88.2%, 2 = 85.4%, 3 = 81.7%, 4 = 77.8%, 5 = 74.0%, 6 = 69.8%, and ≥7 = 68.7) and patient survival (0 = 98.2%, 1 = 96.6%, 2 = 93.7%, 3 = 89.7%, 4 = 84.8%, 5 = 80.8%, 6 = 76.0%, and ≥7 = 74.7%) is seen as KTMI scores increase. The differences in graft and patient survival between KTMI scores are all significant ( P < .001) except between 6 and ≥7. Multivariate regression analysis reveals that KTMI is an independent predictor of higher graft failure and patient mortality rates and that risk increases as KTMI scores increase.

Conclusion

The KTMI strongly predicts graft and patient survival by using pretransplant comorbid conditions; therefore, this easy-to-use tool can aid in determining outcome risk and transplant candidacy before listing, particularly in candidates with multiple comorbid conditions.

Bayesian modeling of pretransplant variables accurately predicts kidney graft survival

INTRODUCTION

Machine learning can enable the development of predictive models that incorporate multiple variables for a systems approach to organ allocation. We explored the principle of Bayesian Belief Network (BBN) to determine whether a predictive model of graft survival can be derived using pretransplant variables. Our hypothesis was that pretransplant donor and recipient variables, when considered together as a network, add incremental value to the classification of graft survival.

METHODS

We performed a retrospective analysis of 5,144 randomly selected patients (age ≥18, deceased donor kidney only, first-time recipients) from the United States Renal Data System database between 2000 and 2001. Using this dataset, we developed a machine-learned BBN that functions as a pretransplant organ-matching tool.

RESULTS

A network of 48 clinical variables was constructed and externally validated using an additional 2,204 patients of matching demographic characteristics. This model was able to predict graft failure within the first year or within 3 years (sensitivity 40%; specificity 80%; area under the curve, AUC, 0.63). Recipient BMI, gender, race, and donor age were amongst the pretransplant variables with strongest association to outcome. A 10-fold internal cross-validation showed similar results for 1-year (sensitivity 24%; specificity 80%; AUC 0.59) and 3-year (sensitivity 31%; specificity 80%; AUC 0.60) graft failure.

CONCLUSION

We found recipient BMI, gender, race, and donor age to be influential predictors of outcome, while wait time and human leukocyte antigen matching were much less associated with outcome. BBN enabled us to examine variables from a large database to develop a robust predictive model.

Pretransplant prediction of posttransplant survival for liver recipients with benign end-stage liver diseases: a nonlinear model

Background

The scarcity of grafts available necessitates a system that considers expected posttransplant survival, in addition to pretransplant mortality as estimated by the MELD. So far, however, conventional linear techniques have failed to achieve sufficient accuracy in posttransplant outcome prediction. In this study, we aim to develop a pretransplant predictive model for liver recipients' survival with benign end-stage liver diseases (BESLD) by a nonlinear method based on pretransplant characteristics, and compare its performance with a BESLD-specific prognostic model (MELD) and a general-illness severity model (the sequential organ failure assessment score, or SOFA score).

Methodology/Principal Findings

With retrospectively collected data on 360 recipients receiving deceased-donor transplantation for BESLD between February 1999 and August 2009 in the west China hospital of Sichuan university, we developed a multi-layer perceptron (MLP) network to predict one-year and two-year survival probability after transplantation. The performances of the MLP, SOFA, and MELD were assessed by measuring both calibration ability and discriminative power, with Hosmer-Lemeshow test and receiver operating characteristic analysis, respectively. By the forward stepwise selection, donor age and BMI; serum concentration of HB, Crea, ALB, TB, ALT, INR, Na⁺; presence of pretransplant diabetes; dialysis prior to transplantation, and microbiologically proven sepsis were identified to be the optimal input features. The MLP, employing 18 input neurons and 12 hidden neurons, yielded high predictive accuracy, with c-statistic of 0.91 (P<0.001) in one-year and 0.88 (P<0.001) in two-year prediction. The performances of SOFA and MELD were fairly poor in prognostic assessment, with c-statistics of 0.70 and 0.66, respectively, in one-year prediction, and 0.67 and 0.65 in two-year prediction.

Conclusions/Significance

The posttransplant prognosis is a multidimensional nonlinear problem, and the MLP can achieve significantly high accuracy than SOFA and MELD scores in posttransplant survival prediction. The pattern recognition methodologies like MLP hold promise for solving posttransplant outcome prediction.

Candidacy for kidney transplantation of older adults

OBJECTIVES

To develop a prediction model for kidney transplantation (KT) outcomes specific to older adults with end-stage renal disease (ESRD) and to use this model to estimate the number of excellent older KT candidates who lack access to KT.

DESIGN

Secondary analysis of data collected by the United Network for Organ Sharing and U.S. Renal Disease System.

SETTING

Retrospective analysis of national registry data.

PARTICIPANTS

Model development: Medicare-primary older recipients (aged ≥ 65) of a first KT between 1999 and 2006 (N = 6,988). Model application: incident Medicare-primary older adults with ESRD between 1999 and 2006 without an absolute or relative contraindication to transplantation (N = 128,850).

MEASUREMENTS

Comorbid conditions were extracted from U.S. Renal Disease System Form 2728 data and Medicare claims.

RESULTS

The prediction model used 19 variables to estimate post-KT outcome and showed good calibration (Hosmer-Lemeshow P = .44) and better prediction than previous population-average models (P < .001). Application of the model to the population with incident ESRD identified 11,756 excellent older transplant candidates (defined as >87% predicted 3-year post-KT survival, corresponding to the top 20% of transplanted older adults used in model development), of whom 76.3% (n = 8,966) lacked access. It was estimated that 11% of these candidates would have identified a suitable live donor had they been referred for KT.

CONCLUSION

A risk-prediction model specific to older adults can identify excellent KT candidates. Appropriate referral could result in significantly greater rates of KT in older adults.

Predicting the outcome of renal transplantation

OBJECTIVE

Renal transplantation has dramatically improved the survival rate of hemodialysis patients. However, with a growing proportion of marginal organs and improved immunosuppression, it is necessary to verify that the established allocation system, mostly based on human leukocyte antigen matching, still meets today's needs. The authors turn to machine-learning techniques to predict, from donor-recipient data, the estimated glomerular filtration rate (eGFR) of the recipient 1 year after transplantation.

DESIGN

The patient's eGFR was predicted using donor-recipient characteristics available at the time of transplantation. Donors' data were obtained from Eurotransplant's database, while recipients' details were retrieved from Charité Campus Virchow-Klinikum's database. A total of 707 renal transplantations from cadaveric donors were included.

MEASUREMENTS

Two separate datasets were created, taking features with <10% missing values for one and <50% missing values for the other. Four established regressors were run on both datasets, with and without feature selection.

RESULTS

The authors obtained a Pearson correlation coefficient between predicted and real eGFR (COR) of 0.48. The best model for the dataset was a Gaussian support vector machine with recursive feature elimination on the more inclusive dataset. All results are available at http://transplant.molgen.mpg.de/.

LIMITATIONS

For now, missing values in the data must be predicted and filled in. The performance is not as high as hoped, but the dataset seems to be the main cause.

CONCLUSIONS

Predicting the outcome is possible with the dataset at hand (COR=0.48). Valuable features include age and creatinine levels of the donor, as well as sex and weight of the recipient.

[Study on the findings of an immediate renal gammagraphy and its effect on the survival of a kidney graft]

INTRODUCTION

We assessed the effect of the findings of the renal gammagraphy (99mTc-DTPA) taken in the first 24 hours after the transplant in the survival of the kidney transplant.

MATERIALS AND METHOD

We retrospectively studied 413 kidney transplants carried out between January 1994 and December 2008, with emphasis on normal gammagraphic findings or alterations in the vascular, parenchymal and excretory stages, as well as their effect on the survival of the graft.

RESULTS

Of the 413 transplants, 44 (10.7%) presented alterations in the vascular stage, 256 (62%) in the parenchymal stage and 269 (65.1%) in the excretory stage. The mean follow-up of the entire group was 72.5 months (± 54.1 DE). The univariate analysis shows that the survival of the graft is significantly less in patients with alterations in the vascular stage (OR: 3; IC 95% 1.9 - 4.9 p<0.001), in the excretory stage (OR: 2.5; IC 95% 1.5 - 4; p=<0.001) in the parenchymal stage (OR: 2.21; IC 95% 1.3-3.36; p=0.001). The multivariate studies of the gammagraphic variables that affect the survival of the graft show that the presence of alterations in the vascular stage (OR: 3; IC 95% 1.9-4.9; p<0.001) in the parenchymal stage (OR: 2; IC 95% 1.2-3.3; p=0.005) are directly related to survival. This data is also confirmed by means of the actuarial survival analysis of the graft at 3 and 5 years.

CONCLUSIONS

The presence of alterations in the vascular stage and in the parenchymal stage of the renal gammagraphy immediately after the transplant are variables that affect the survival of the graft.

Assessment of kidney organ quality and prediction of outcome at time of transplantation

The critical importance of donor organ quality, i.e., number of surviving nephrons, ability to withstand injury, and capacity for repair in determining short- and long-term outcomes is becoming increasingly clear. This review provides an overview of studies to assess donor kidney quality and subsequent transplant outcomes based on clinical pathology and transcriptome-based variables available at time of transplantation. Prediction scores using clinical variables function when applied to large data sets but perform poorly for the individual patient. Histopathology findings in pre-implantation or post-reperfusion biopsies help to assess structural integrity of the donor kidney, provide information on pre-existing donor disease, and can serve as a baseline for tracking changes over time. However, more validated approaches of analysis and prospective studies are needed to reduce the number of discarded organs, improve allocation, and allow prediction of outcomes. Molecular profiling detects changes not seen by morphology or captured by clinical markers. In particular, molecular profiles provide a quantitative measurement of inflammatory burden or immune activation and reflect coordinated changes in pathways associated with injury and repair. However, description of transcriptome patterns is not an end in itself. The identification of predictive gene sets and the application to an individualized patient management needs the integration of clinical and pathology-based variables, as well as more objective reference markers of transplant function, post-transplant events, and long-term outcomes.

Decisional trees in renal transplant follow-up

INTRODUCTION

The predictive potentialities of application of data mining algorithms to medical research are well known. In this article, we have applied to a transplant population classification trees to build predictive models of graft failure, evaluating the interactions between body mass index (BMI) and other risk factors. The decision trees have been widely used to represent classification rules in a population by a hierarchical sequential structure.

PATIENTS AND METHODS

We retrospectively studied 194 renal transplant patients with 5 years of follow-up (128 males, 66 females, mean age at time of transplant of 43.9 +/- 12.5 years). Exclusion criteria were: age < 18 years, multiorgan transplant, and retransplant. The BMI was calculated at the time of transplantation. In the classification algorithm, we considered the following parameters: age, sex, time on dialysis, donor type, donor age, HLA mismatches, delayed graft function (DGF), acute rejection episode (ARE), and chronic allograft nephropathy (CAN). The primary endpoint was graft loss within 5-years follow-up.

RESULTS

The classification algorithm produced a decision tree that allowed us to evaluate the interactions between ARE, DGF, CAN, and BMI on graft outcomes, producing a validation set with 88.2% sensitivity and 73.8% specificity. Our model was able to highlight that subjects at risk of graft loss experienced one or more events of ARE, developed DGF and CAN, or has a BMI > 24.8 kg/m(2) and CAN.

CONCLUSIONS

The use of decision trees in clinical practice may be a suitable alternative to the traditional statistical methods, since it may allow one to analyze interactions between various risk factors beyond the previous knowledge.

Prediction of chronic allograft nephropathy using classification trees

INTRODUCTION

For its intrinsic potential to mine causal relations, machine learning techniques are useful to identify new risk indicators. In this work, we have shown two classification trees to predict chronic allograft nephropathy (CAN), through an evaluation of routine blood and urine tests.

METHODS

We retrospectively analyzed 80 renal transplant patients with 60-month follow-up (mean = 55.20 +/- 12.74) including 52 males and 28 females of overall average age of 41.65 +/- 12.52 years. The primary endpoint was biopsy-proven CAN within 5 years from transplantation (n = 16). Exclusion criteria were multiorgan transplantations, patients aged less than 18 years, graft failure, or patient death in the first 6 months posttransplantation. Classification trees based on the C 4.8 algorithm were used to predict CAN development starting from patient features at transplantation and biochemical test at 6-month follow-up. Model performance was showed as sensitivity (S), false-positive rate (FPR), and area under the receiver operating characteristic curve (AUC).

RESULTS

The two class of patients (no CAN versus CAN) showed significant differences in serum creatinine, estimated Glomerular Filtration Rate with Modification of Diet in Renal Disease study formula (MDRD), serum hemoglobin, hematocrit, blood urea nitrogen, and 24-hour urine protein excretion. Among the 23 evaluated variables, the first model selected six predictors of CAN, showing S = 62.5%, TFP = 7.2%, and AUC = 0.847 (confidence interval [CI] 0.749-0.945). The second model selected four variables, showing S = 81.3%, TFP = 25%, and AUC = 0.824 (CI 0.713-0.934).

CONCLUSIONS

Identification models have predicted the onset of multifactorial, complex pathology, like CAN. The use of classification trees represent a valid alternative to traditional statistical models, especially for the evaluation of interactions of risk factors.

For an always promising transplant prediction, call ANN

With apologies to Sherlock Holmes, "You can never foretell when any one man's kidney transplant will fail, but you can say with precision when an average number will fail. ... So says the statistician."