Machine learning-based prediction of health outcomes in pediatric organ transplantation recipients

Elaboration and validation of a novelty nomogram for the prognostication of anxiety susceptibility in individuals suffering from low back pain

Low back pain (LBP) constitutes a distressing emotional ordeal and serves as a potent catalyst for adverse emotional states, notably anxiety. We dedicated to discerning methodologies for identifying patients who are predisposed to heightened levels of anxiety and pain. A self-assessment questionnaire was administered to patients afflicted with LBP. The pain scores were subjected to analysis in conjunction with anxiety scores, and a clustering procedure was executed using the scientific k-means methodology. Subsequently, six machine learning algorithms, including Logistics Regression (LR), K-Nearest Neighbor (KNN), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGB), were employed. Next, five pertinent variables were identified, namely Age, Course, Body Mass Index (BMI), Education, and Marital status. Furthermore, a LR model was utilized to construct a nomogram, which was subsequently subjected to assessment for discrimination, calibration, and evaluation of its clinical utility. As a result, 599 questionnaires were valid (effective rate: 99 %). The correlation analysis revealed a significant association between anxiety and pain scores (r = 0.31, P < 0.001). LBP patients could be divided into two clusters, Cluster1 had higher pain scores (P < 0.05) and SAS scores (P < 0.001). The proposed nomogram demonstrated an area under the receiver operating characteristics curve (ROC) of 0.841 (95 %CI: 0.804-0.878) and 0.800 (95 %CI: 0.733-0.867) in the training and test groups, respectively. Briefly, the established nomogram has demonstrated remarkable proficiency in discerning individuals afflicted with LBP who are at a heightened risk of experiencing anxiety.

Demographic Factors, Medication Adherence, and Post-transplant Health Outcomes: A Longitudinal Multilevel Modeling Approach

Few studies in pediatric solid organ transplantation have examined non-adherence to immunosuppressive medication over time and its associations with demographic factors and post-transplant outcomes including late acute rejection and hospitalizations. We examined longitudinal variation in patient Medication Level Variability Index (MLVI) adherence data from pediatric kidney, liver, and heart transplant recipients. Patient and administrative data from the United Network for Organ Sharing were linked with electronic health records and MLVI values for 332 patients. Multilevel mediation modeling indicated comparatively more variation in MLVI values between patients than within patients, longitudinally, over 10 years post transplant. MLVI values significantly predicted late acute rejection and hospitalization. MLVI partially mediated patient factors and post-transplant outcomes for patient age indicating adolescents may benefit most from intervention efforts. Results demonstrate the importance of longitudinal assessment of adherence and differences among patients. Efforts to promote medication adherence should be adapted to high-risk patients to increase likelihood of adherence.

Distinct clinical profiles and post-transplant outcomes among kidney transplant recipients with lower education levels: uncovering patterns through machine learning clustering

BACKGROUND

Educational attainment significantly influences post-transplant outcomes in kidney transplant patients. However, research on specific attributes of lower-educated subgroups remains underexplored. This study utilized unsupervised machine learning to segment kidney transplant recipients based on education, further analyzing the relationship between these segments and post-transplant results.

METHODS

Using the OPTN/UNOS 2017-2019 data, consensus clustering was applied to 20,474 kidney transplant recipients, all below a college/university educational threshold. The analysis concentrated on recipient, donor, and transplant features, aiming to discern pivotal attributes for each cluster and compare post-transplant results.

RESULTS

Four distinct clusters emerged. Cluster 1 comprised younger, non-diabetic, first-time recipients from non-hypertensive younger donors. Cluster 2 predominantly included white patients receiving their first-time kidney transplant either preemptively or within three years, mainly from living donors. Cluster 3 included younger re-transplant recipients, marked by elevated PRA, fewer HLA mismatches. In contrast, Cluster 4 captured older, diabetic patients transplanted after prolonged dialysis duration, primarily from lower-grade donors. Interestingly, Cluster 2 showcased the most favorable post-transplant outcomes. Conversely, Clusters 1, 3, and 4 revealed heightened risks for graft failure and mortality in comparison.

CONCLUSIONS

Through unsupervised machine learning, this study proficiently categorized kidney recipients with lesser education into four distinct clusters. Notably, the standout performance of Cluster 2 provides invaluable insights, underscoring the necessity for adept risk assessment and tailored transplant strategies, potentially elevating care standards for this patient cohort.

The use of artificial intelligence for delivery of essential health services across WHO regions: a scoping review

Background

Artificial intelligence (AI) is a broad outlet of computer science aimed at constructing machines capable of simulating and performing tasks usually done by human beings. The aim of this scoping review is to map existing evidence on the use of AI in the delivery of medical care.

Methods

We searched PubMed and Scopus in March 2022, screened identified records for eligibility, assessed full texts of potentially eligible publications, and extracted data from included studies in duplicate, resolving differences through discussion, arbitration, and consensus. We then conducted a narrative synthesis of extracted data.

Results

Several AI methods have been used to detect, diagnose, classify, manage, treat, and monitor the prognosis of various health issues. These AI models have been used in various health conditions, including communicable diseases, non-communicable diseases, and mental health.

Conclusions

Presently available evidence shows that AI models, predominantly deep learning, and machine learning, can significantly advance medical care delivery regarding the detection, diagnosis, management, and monitoring the prognosis of different illnesses.

Prediction of Outcomes After Heart Transplantation in Pediatric Patients Using National Registry Data: Evaluation of Machine Learning Approaches

BACKGROUND

The prediction of posttransplant health outcomes for pediatric heart transplantation is critical for risk stratification and high-quality posttransplant care.

OBJECTIVE

The purpose of this study was to examine the use of machine learning (ML) models to predict rejection and mortality for pediatric heart transplant recipients.

METHODS

Various ML models were used to predict rejection and mortality at 1, 3, and 5 years after transplantation in pediatric heart transplant recipients using United Network for Organ Sharing data from 1987 to 2019. The variables used for predicting posttransplant outcomes included donor and recipient as well as medical and social factors. We evaluated 7 ML models-extreme gradient boosting (XGBoost), logistic regression, support vector machine, random forest (RF), stochastic gradient descent, multilayer perceptron, and adaptive boosting (AdaBoost)-as well as a deep learning model with 2 hidden layers with 100 neurons and a rectified linear unit (ReLU) activation function followed by batch normalization for each and a classification head with a softmax activation function. We used 10-fold cross-validation to evaluate model performance. Shapley additive explanations (SHAP) values were calculated to estimate the importance of each variable for prediction.

RESULTS

RF and AdaBoost models were the best-performing algorithms for different prediction windows across outcomes. RF outperformed other ML algorithms in predicting 5 of the 6 outcomes (area under the receiver operating characteristic curve [AUROC] 0.664 and 0.706 for 1-year and 3-year rejection, respectively, and AUROC 0.697, 0.758, and 0.763 for 1-year, 3-year, and 5-year mortality, respectively). AdaBoost achieved the best performance for prediction of 5-year rejection (AUROC 0.705).

CONCLUSIONS

This study demonstrates the comparative utility of ML approaches for modeling posttransplant health outcomes using registry data. ML approaches can identify unique risk factors and their complex relationship with outcomes, thereby identifying patients considered to be at risk and informing the transplant community about the potential of these innovative approaches to improve pediatric care after heart transplantation. Future studies are required to translate the information derived from prediction models to optimize counseling, clinical care, and decision-making within pediatric organ transplant centers.

Artificial intelligence, big data and heart transplantation: Actualities

BACKGROUND

As diagnostic and prognostic models developed by traditional statistics perform poorly in real-world, artificial intelligence (AI) and Big Data (BD) may improve the supply chain of heart transplantation (HTx), allocation opportunities, correct treatments, and finally optimize HTx outcome. We explored available studies, and discussed opportunities and limits of medical application of AI to the field of HTx.

METHOD

A systematic overview of studies published up to December 31st, 2022, in English on peer-revied journals, have been identified through PUBMED-MEDLINE-WEB of Science, referring to HTx, AI, BD. Studies were grouped in 4 domains based on main studies' objectives and results: etiology, diagnosis, prognosis, treatment. A systematic attempt was made to evaluate studies by the Prediction model Risk Of Bias ASsessment Tool (PROBAST) and the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD).

RESULTS

Among the 27 publications selected, none used AI applied to BD. Of the selected studies, 4 fell in the domain of etiology, 6 in the domain of diagnosis, 3 in the domain of treatment, and 17 in that of prognosis, as AI was most frequently used for algorithmic prediction and discrimination of survival, but in retrospective cohorts and registries. AI-based algorithms appeared superior to probabilistic functions to predict patterns, but external validation was rarely employed. Indeed, based on PROBAST, selected studies showed, to some extent, significant risk of bias (especially in the domain of predictors and analysis). In addition, as example of applicability in the real-world, a free-use prediction algorithm developed through AI failed to predict 1-year mortality post-HTx in cases from our center.

CONCLUSIONS

While AI-based prognostic and diagnostic functions performed better than those developed by traditional statistics, risk of bias, lack of external validation, and relatively poor applicability, may affect AI-based tools. More unbiased research with high quality BD meant for AI, transparency and external validations, are needed to have medical AI as a systematic aid to clinical decision making in HTx.

Differences between Very Highly Sensitized Kidney Transplant Recipients as Identified by Machine Learning Consensus Clustering

Background and Objectives: The aim of our study was to categorize very highly sensitized kidney transplant recipients with pre-transplant panel reactive antibody (PRA) ≥ 98% using an unsupervised machine learning approach as clinical outcomes for this population are inferior, despite receiving increased allocation priority. Identifying subgroups with higher risks for inferior outcomes is essential to guide individualized management strategies for these vulnerable recipients. Materials and Methods: To achieve this, we analyzed the Organ Procurement and Transplantation Network (OPTN)/United Network for Organ Sharing (UNOS) database from 2010 to 2019 and performed consensus cluster analysis based on the recipient-, donor-, and transplant-related characteristics in 7458 kidney transplant patients with pre-transplant PRA ≥ 98%. The key characteristics of each cluster were identified by calculating the standardized mean difference. The post-transplant outcomes were compared between the assigned clusters. Results: We identified two distinct clusters and compared the post-transplant outcomes among the assigned clusters of very highly sensitized kidney transplant patients. Cluster 1 patients were younger (median age 45 years), male predominant, and more likely to have previously undergone a kidney transplant, but had less diabetic kidney disease. Cluster 2 recipients were older (median 54 years), female predominant, and more likely to be undergoing a first-time transplant. While patient survival was comparable between the two clusters, cluster 1 had lower death-censored graft survival and higher acute rejection compared to cluster 2. Conclusions: The unsupervised machine learning approach categorized very highly sensitized kidney transplant patients into two clinically distinct clusters with differing post-transplant outcomes. A better understanding of these clinically distinct subgroups may assist the transplant community in developing individualized care strategies and improving the outcomes for very highly sensitized kidney transplant patients.

Distinct Phenotypes of Non-Citizen Kidney Transplant Recipients in the United States by Machine Learning Consensus Clustering

BACKGROUND

Better understanding of the different phenotypes/subgroups of non-U.S. citizen kidney transplant recipients may help the transplant community to identify strategies that improve outcomes among non-U.S. citizen kidney transplant recipients. This study aimed to cluster non-U.S. citizen kidney transplant recipients using an unsupervised machine learning approach; Methods: We conducted a consensus cluster analysis based on recipient-, donor-, and transplant- related characteristics in non-U.S. citizen kidney transplant recipients in the United States from 2010 to 2019 in the OPTN/UNOS database using recipient, donor, and transplant-related characteristics. Each cluster's key characteristics were identified using the standardized mean difference. Post-transplant outcomes were compared among the clusters; Results: Consensus cluster analysis was performed in 11,300 non-U.S. citizen kidney transplant recipients and identified two distinct clusters best representing clinical characteristics. Cluster 1 patients were notable for young age, preemptive kidney transplant or dialysis duration of less than 1 year, working income, private insurance, non-hypertensive donors, and Hispanic living donors with a low number of HLA mismatch. In contrast, cluster 2 patients were characterized by non-ECD deceased donors with KDPI <85%. Consequently, cluster 1 patients had reduced cold ischemia time, lower proportion of machine-perfused kidneys, and lower incidence of delayed graft function after kidney transplant. Cluster 2 had higher 5-year death-censored graft failure (5.2% vs. 9.8%; p < 0.001), patient death (3.4% vs. 11.4%; p < 0.001), but similar one-year acute rejection (4.7% vs. 4.9%; p = 0.63), compared to cluster 1; Conclusions: Machine learning clustering approach successfully identified two clusters among non-U.S. citizen kidney transplant recipients with distinct phenotypes that were associated with different outcomes, including allograft loss and patient survival. These findings underscore the need for individualized care for non-U.S. citizen kidney transplant recipients.

Distinct phenotypes of kidney transplant recipients aged 80 years or older in the USA by machine learning consensus clustering

Objectives

This study aimed to identify distinct clusters of very elderly kidney transplant recipients aged ≥80 and assess clinical outcomes among these unique clusters.

Design

Cohort study with machine learning (ML) consensus clustering approach.

Setting and participants

All very elderly (age ≥80 at time of transplant) kidney transplant recipients in the Organ Procurement and Transplantation Network/United Network for Organ Sharing database database from 2010 to 2019.

Main outcome measures

Distinct clusters of very elderly kidney transplant recipients and their post-transplant outcomes including death-censored graft failure, overall mortality and acute allograft rejection among the assigned clusters.

Results

Consensus cluster analysis was performed in 419 very elderly kidney transplant and identified three distinct clusters that best represented the clinical characteristics of very elderly kidney transplant recipients. Recipients in cluster 1 received standard Kidney Donor Profile Index (KDPI) non-extended criteria donor (ECD) kidneys from deceased donors. Recipients in cluster 2 received kidneys from older, hypertensive ECD deceased donors with a KDPI score ≥85%. Kidneys for cluster 2 patients had longer cold ischaemia time and the highest use of machine perfusion. Recipients in clusters 1 and 2 were more likely to be on dialysis at the time of transplant (88.3%, 89.4%). Recipients in cluster 3 were more likely to be preemptive (39%) or had a dialysis duration less than 1 year (24%). These recipients received living donor kidney transplants. Cluster 3 had the most favourable post-transplant outcomes. Compared with cluster 3, cluster 1 had comparable survival but higher death-censored graft failure, while cluster 2 had lower patient survival, higher death-censored graft failure and more acute rejection.

Conclusions

Our study used an unsupervised ML approach to cluster very elderly kidney transplant recipients into three clinically unique clusters with distinct post-transplant outcomes. These findings from an ML clustering approach provide additional understanding towards individualised medicine and opportunities to improve care for very elderly kidney transplant recipients.

Differences between kidney retransplant recipients as identified by machine learning consensus clustering

BACKGROUND

Our study aimed to characterize kidney retransplant recipients using an unsupervised machine-learning approach.

METHODS

We performed consensus cluster analysis based on the recipient-, donor-, and transplant-related characteristics in 17 443 kidney retransplant recipients in the OPTN/UNOS database from 2010 to 2019. We identified each cluster's key characteristics using the standardized mean difference of >.3. We compared the posttransplant outcomes, including death-censored graft failure and patient death among the assigned clusters RESULTS: Consensus cluster analysis identified three distinct clusters of kidney retransplant recipients. Cluster 1 recipients were predominantly white and were less sensitized. They were most likely to receive a living donor kidney transplant and more likely to be preemptive (30%) or need ≤1 year of dialysis (32%). In contrast, cluster 2 recipients were the most sensitized (median PRA 95%). They were more likely to have been on dialysis >1 year, and receive a nationally allocated, low HLA mismatch, standard KDPI deceased donor kidney. Recipients in cluster 3 were more likely to be minorities (37% Black; 15% Hispanic). They were moderately sensitized with a median PRA of 87% and were also most likely to have been on dialysis >1 year. They received locally allocated high HLA mismatch kidneys from standard KDPI deceased donors. Thymoglobulin was the most commonly used induction agent for all three clusters. Cluster 1 had the most favorable patient and graft survival, while cluster 3 had the worst patient and graft survival.

CONCLUSION

The use of an unsupervised machine learning approach characterized kidney retransplant recipients into three clinically distinct clusters with differing posttransplant outcomes. Recipients with moderate allosensitization, such as those represented in cluster 3, are perhaps more disadvantaged in the kidney retransplantation process. Potential opportunities for improvement specific to these re-transplant recipients include working to improve opportunities to improve access to living donor kidney transplantation, living donor paired exchange and identifying strategies for better HLA matching.

Use of machine learning in pediatric surgical clinical prediction tools: A systematic review

PURPOSE

Clinical prediction tools (CPTs) are decision-making instruments utilizing patient data to predict specific clinical outcomes, risk-stratify patients, or suggest personalized diagnostic or therapeutic options. Recent advancements in artificial intelligence have resulted in a proliferation of CPTs created using machine learning (ML)-yet the clinical applicability of ML-based CPTs and their validation in clinical settings remain unclear. This systematic review aims to compare the validity and clinical efficacy of ML-based to traditional CPTs in pediatric surgery.

METHODS

Nine databases were searched from 2000 until July 9, 2021 to retrieve articles reporting on CPTs and ML for pediatric surgical conditions. PRISMA standards were followed, and screening was performed by two independent reviewers in Rayyan, with a third reviewer resolving conflicts. Risk of bias was assessed using the PROBAST.

RESULTS

Out of 8300 studies, 48 met the inclusion criteria. The most represented surgical specialties were pediatric general (14), neurosurgery (13) and cardiac surgery (12). Prognostic (26) CPTs were the most represented type of surgical pediatric CPTs followed by diagnostic (10), interventional (9), and risk stratifying (2). One study included a CPT for diagnostic, interventional and prognostic purposes. 81% of studies compared their CPT to ML-based CPTs, statistical CPTs, or the unaided clinician, but lacked external validation and/or evidence of clinical implementation.

CONCLUSIONS

While most studies claim significant potential improvements by incorporating ML-based CPTs in pediatric surgical decision-making, both external validation and clinical application remains limited. Further studies must focus on validating existing instruments or developing validated tools, and incorporating them in the clinical workflow.

TYPE OF STUDY

Systematic Review LEVEL OF EVIDENCE: Level III.

Machine learning-based prediction of mortality after heart transplantation in adults with congenital heart disease: A UNOS database analysis

BACKGROUND

Machine learning (ML) is increasingly being applied in Cardiology to predict outcomes and assist in clinical decision-making. We sought to develop and validate an ML model for the prediction of mortality after heart transplantation (HT) in adults with congenital heart disease (ACHD).

METHODS

The United Network for Organ Sharing (UNOS) database was queried from 2000 to 2020 for ACHD patients who underwent isolated HT. The study cohort was randomly split into derivation (70%) and validation (30%) datasets that were used to train and test a CatBoost ML model. Feature selection was performed using SHapley Additive exPlanations (SHAP). Recipient, donor, procedural, and post-transplant characteristics were tested for their ability to predict mortality. We additionally used SHAP for explainability analysis, as well as individualized mortality risk assessment.

RESULTS

The study cohort included 1033 recipients (median age 34 years, 61% male). At 1 year after HT, there were 205 deaths (19.9%). Out of a total of 49 variables, 10 were selected as highly predictive of 1-year mortality and were used to train the ML model. Area under the curve (AUC) and predictive accuracy for the 1-year ML model were .80 and 75.2%, respectively, and .69 and 74.2% for the 3-year model, respectively. Based on SHAP analysis, hemodialysis of the recipient post-HT had overall the strongest relative impact on 1-year mortality after HΤ, followed by recipient-estimated glomerular filtration rate, age and ischemic time.

CONCLUSIONS

ML models showed satisfactory predictive accuracy of mortality after HT in ACHD and allowed for individualized mortality risk assessment.

Use of Machine Learning Consensus Clustering to Identify Distinct Subtypes of Kidney Transplant Recipients With DGF and Associated Outcomes

Data and transplant community opinion on delayed graft function (DGF), and its impact on outcomes, remains varied. An unsupervised machine learning consensus clustering approach was applied to categorize the clinical phenotypes of kidney transplant (KT) recipients with DGF using OPTN/UNOS data. DGF was observed in 20.9% (n = 17,073) of KT and most kidneys had a KDPI score <85%. Four distinct clusters were identified. Cluster 1 recipients were young, high PRA re-transplants. Cluster 2 recipients were older diabetics and more likely to receive higher KDPI kidneys. Cluster 3 recipients were young, black, and non-diabetic; they received lower KDPI kidneys. Cluster 4 recipients were middle-aged, had diabetes or hypertension and received well-matched standard KDPI kidneys. By cluster, one-year patient survival was 95.7%, 92.5%, 97.2% and 94.3% (p < 0.001); one-year graft survival was 89.7%, 87.1%, 91.6%, and 88.7% (p < 0.001). There were no differences between clusters after accounting for death-censored graft loss (p = 0.08). Clinically meaningful differences in recipient characteristics were noted between clusters, however, after accounting for death and return to dialysis, there were no differences in death-censored graft loss. Greater emphasis on recipient comorbidities as contributors to DGF and outcomes may help improve utilization of DGF at-risk kidneys.

Digital Technologies: Advancing Individualized Treatments through Gene and Cell Therapies, Pharmacogenetics, and Disease Detection and Diagnostics

Digital technologies are shifting the paradigm of medicine in a way that will transform the healthcare industry. Conventional medical approaches focus on treating symptoms and ailments for large groups of people. These approaches can elicit differences in treatment responses and adverse reactions based on population variations, and are often incapable of treating the inherent pathophysiology of the medical conditions. Advances in genetics and engineering are improving healthcare via individualized treatments that include gene and cell therapies, pharmacogenetics, disease detection, and diagnostics. This paper highlights ways that artificial intelligence can help usher in an age of personalized medicine.

Pre-operative Machine Learning for Heart Transplant Patients Bridged with Temporary Mechanical Circulatory Support

Background: Existing prediction models for post-transplant mortality in patients bridged to heart transplantation with temporary mechanical circulatory support (tMCS) perform poorly. A more reliable model would allow clinicians to provide better pre-operative risk assessment and develop more targeted therapies for high-risk patients. Methods: We identified adult patients in the United Network for Organ Sharing database undergoing isolated heart transplantation between 01/2009 and 12/2017 who were supported with tMCS at the time of transplant. We constructed a machine learning model using extreme gradient boosting (XGBoost) with a 70:30 train:test split to predict 1-year post-operative mortality. All pre-transplant variables available in the UNOS database were included to train the model. Shapley Additive Explanations was used to identify and interpret the most important features for XGBoost predictions. Results: A total of 1584 patients were included, with a median age of 56 (interquartile range: 46-62) and 74% male. Actual 1-year mortality was 12.1%. Out of 498 available variables, 43 were selected for the final model. The area under the receiver operator characteristics curve (AUC) for the XGBoost model was 0.71 (95% CI: 0.62-0.78). The most important variables predictive of 1-year mortality included recipient functional status, age, pulmonary capillary wedge pressure (PCWP), cardiac output, ECMO usage, and serum creatinine. Conclusions: An interpretable machine learning model trained on a large clinical database demonstrated good performance in predicting 1-year mortality for patients bridged to heart transplantation with tMCS. Machine learning may be used to enhance clinician judgement in the care of markedly high-risk transplant recipients.

Machine Learning Consensus Clustering of Morbidly Obese Kidney Transplant Recipients in the United States

Background: This study aimed to better characterize morbidly obese kidney transplant recipients, their clinical characteristics, and outcomes by using an unsupervised machine learning approach. Methods: Consensus cluster analysis was applied to OPTN/UNOS data from 2010 to 2019 based on recipient, donor, and transplant characteristics in kidney transplant recipients with a pre-transplant BMI ≥ 40 kg/m2. Key cluster characteristics were identified using the standardized mean difference. Post-transplant outcomes, including death-censored graft failure, patient death, and acute allograft rejection, were compared among the clusters. Results: Consensus clustering analysis identified 3204 kidney transplant recipients with a BMI ≥ 40 kg/m2. In this cohort, five clinically distinct clusters were identified. Cluster 1 recipients were predominantly white and non-sensitized, had a short dialysis time or were preemptive, and were more likely to receive living donor kidney transplants. Cluster 2 recipients were older and diabetic. They were likely to have been on dialysis >3 years and receive a standard KDPI deceased donor kidney. Cluster 3 recipients were young, black, and had kidney disease secondary to hypertension or glomerular disease. Cluster 3 recipients had >3 years of dialysis and received non-ECD, young, deceased donor kidney transplants with a KDPI < 85%. Cluster 4 recipients were diabetic with variable dialysis duration who either received non-ECD standard KDPI kidneys or living donor kidney transplants. Cluster 5 recipients were young retransplants that were sensitized. One-year patient survival in clusters 1, 2, 3, 4, and 5 was 98.0%, 94.4%, 98.5%, 98.7%, and 97%, and one-year death-censored graft survival was 98.1%, 93.0%, 96.1%, 98.8%, and 93.0%, respectively. Cluster 2 had the worst one-year patient survival. Clusters 2 and 5 had the worst one-year death-censored graft survival. Conclusions: With the application of unsupervised machine learning, variable post-transplant outcomes are observed among morbidly obese kidney transplant recipients. Recipients with earlier access to transplant and living donation show superior outcomes. Unexpectedly, reduced graft survival in cluster 3 recipients perhaps underscores socioeconomic access to post-transplant support and minorities being disadvantaged in access to preemptive and living donor transplants. Despite obesity-related concerns, one-year patient and graft survival were favorable in all clusters, and obesity itself should be reconsidered as a hard barrier to kidney transplantation.

Distinct Phenotypes of Kidney Transplant Recipients in the United States with Limited Functional Status as Identified through Machine Learning Consensus Clustering

Background: There have been concerns regarding increased perioperative mortality, length of hospital stay, and rates of graft loss in kidney transplant recipients with functional limitations. The application of machine learning consensus clustering approach may provide a novel understanding of unique phenotypes of functionally limited kidney transplant recipients with distinct outcomes in order to identify strategies to improve outcomes. Methods: Consensus cluster analysis was performed based on recipient-, donor-, and transplant-related characteristics in 3205 functionally limited kidney transplant recipients (Karnofsky Performance Scale (KPS) < 40% at transplant) in the OPTN/UNOS database from 2010 to 2019. Each cluster’s key characteristics were identified using the standardized mean difference. Posttransplant outcomes, including death-censored graft failure, patient death, and acute allograft rejection were compared among the clusters Results: Consensus cluster analysis identified two distinct clusters that best represented the clinical characteristics of kidney transplant recipients with limited functional status prior to transplant. Cluster 1 patients were older in age and were more likely to receive deceased donor kidney transplant with a higher number of HLA mismatches. In contrast, cluster 2 patients were younger, had shorter dialysis duration, were more likely to be retransplants, and were more likely to receive living donor kidney transplants from HLA mismatched donors. As such, cluster 2 recipients had a higher PRA, less cold ischemia time, and lower proportion of machine-perfused kidneys. Despite having a low KPS, 5-year patient survival was 79.1 and 83.9% for clusters 1 and 2; 5-year death-censored graft survival was 86.9 and 91.9%. Cluster 1 had lower death-censored graft survival and patient survival but higher acute rejection, compared to cluster 2. Conclusion: Our study used an unsupervised machine learning approach to characterize kidney transplant recipients with limited functional status into two clinically distinct clusters with differing posttransplant outcomes.

Use of Machine Learning Consensus Clustering to Identify Distinct Subtypes of Black Kidney Transplant Recipients and Associated Outcomes

Importance

Among kidney transplant recipients, Black patients continue to have worse graft function and reduced patient and graft survival. Better understanding of different phenotypes and subgroups of Black kidney transplant recipients may help the transplant community to identify individualized strategies to improve outcomes among these vulnerable groups.

Objective

To cluster Black kidney transplant recipients in the US using an unsupervised machine learning approach.

Design, Setting, and Participants

This cohort study performed consensus cluster analysis based on recipient-, donor-, and transplant-related characteristics in Black kidney transplant recipients in the US from January 1, 2015, to December 31, 2019, in the Organ Procurement and Transplantation Network/United Network for Organ Sharing database. Each cluster's key characteristics were identified using the standardized mean difference, and subsequently the posttransplant outcomes were compared among the clusters. Data were analyzed from June 9 to July 17, 2021.

Exposure

Machine learning consensus clustering approach.

Main Outcomes and Measures

Death-censored graft failure, patient death within 3 years after kidney transplant, and allograft rejection within 1 year after kidney transplant.

Results

Consensus cluster analysis was performed for 22 687 Black kidney transplant recipients (mean [SD] age, 51.4 [12.6] years; 13 635 men [60%]), and 4 distinct clusters that best represented their clinical characteristics were identified. Cluster 1 was characterized by highly sensitized recipients of deceased donor kidney retransplants; cluster 2, by recipients of living donor kidney transplants with no or short prior dialysis; cluster 3, by young recipients with hypertension and without diabetes who received young deceased donor transplants with low kidney donor profile index scores; and cluster 4, by older recipients with diabetes who received kidneys from older donors with high kidney donor profile index scores and extended criteria donors. Cluster 2 had the most favorable outcomes in terms of death-censored graft failure, patient death, and allograft rejection. Compared with cluster 2, all other clusters had a higher risk of death-censored graft failure and death. Higher risk for rejection was found in clusters 1 and 3, but not cluster 4.

Conclusions and Relevance

In this cohort study using an unsupervised machine learning approach, the identification of clinically distinct clusters among Black kidney transplant recipients underscores the need for individualized care strategies to improve outcomes among vulnerable patient groups.