Differences between Kidney Transplant Recipients from Deceased Donors with Diabetes Mellitus as Identified by Machine Learning Consensus Clustering

Clinical outcomes of deceased donor kidney transplants coming from diabetic donors currently remain inconsistent, possibly due to high heterogeneities in this population. Our study aimed to cluster recipients of diabetic deceased donor kidney transplants using an unsupervised machine learning approach in order to identify subgroups with high risk of inferior outcomes and potential variables associated with these outcomes. Consensus cluster analysis was performed based on recipient-, donor-, and transplant-related characteristics in 7876 recipients of diabetic deceased donor kidney transplants from 2010 to 2019 in the OPTN/UNOS database. We determined the important characteristics of each assigned cluster and compared the post-transplant outcomes between the clusters. Consensus cluster analysis identified three clinically distinct clusters. Recipients in cluster 1 (n = 2903) were characterized by oldest age (64 ± 8 years), highest rate of comorbid diabetes mellitus (55%). They were more likely to receive kidney allografts from donors that were older (58 ± 6.3 years), had hypertension (89%), met expanded criteria donor (ECD) status (78%), had a high rate of cerebrovascular death (63%), and carried a high kidney donor profile index (KDPI). Recipients in cluster 2 (n = 687) were younger (49 ± 13 years) and all were re-transplant patients with higher panel reactive antibodies (PRA) (88 [IQR 46, 98]) who received kidneys from younger (44 ± 11 years), non-ECD deceased donors (88%) with low numbers of HLA mismatch (4 [IQR 2, 5]). The cluster 3 cohort was characterized by first-time kidney transplant recipients (100%) who received kidney allografts from younger (42 ± 11 years), non-ECD deceased donors (98%). Compared to cluster 3, cluster 1 had higher incidence of primary non-function, delayed graft function, patient death and death-censored graft failure, whereas cluster 2 had higher incidence of delayed graft function and death-censored graft failure but comparable primary non-function and patient death. An unsupervised machine learning approach characterized diabetic donor kidney transplant patients into three clinically distinct clusters with differing outcomes. Our data highlight opportunities to improve utilization of high KDPI kidneys coming from diabetic donors in recipients with survival-limiting comorbidities such as those observed in cluster 1.

[1]  C. Thongprayoon,et al.  Differences between Very Highly Sensitized Kidney Transplant Recipients as Identified by Machine Learning Consensus Clustering , 2023, Medicina.

[2]  M. Cooper,et al.  Distinct Phenotypes of Non-Citizen Kidney Transplant Recipients in the United States by Machine Learning Consensus Clustering , 2023, Medicines.

[3]  M. Cooper,et al.  Differences between kidney retransplant recipients as identified by machine learning consensus clustering , 2023, Clinical transplantation.

[4]  L. Biancone,et al.  Relationship between Cytomegalovirus Viremia and Long-Term Outcomes in Kidney Transplant Recipients with Different Donor Ages , 2023, Microorganisms.

[5]  M. Cooper,et al.  Distinct phenotypes of kidney transplant recipients aged 80 years or older in the USA by machine learning consensus clustering , 2023, BMJ surgery, interventions, & health technologies.

[6]  V. Garovic,et al.  Use of Machine Learning Consensus Clustering to Identify Distinct Subtypes of Black Kidney Transplant Recipients and Associated Outcomes. , 2022, JAMA surgery.

[7]  D. Axelrod,et al.  Technology-Enabled Care and Artificial Intelligence in Kidney Transplantation , 2021, Current Transplantation Reports.

[8]  L. Biancone,et al.  Non-adherence assessment to immunosuppressant therapy with a self-report questionnaire and intra-patient variability in renal transplantation: risk factors and clinical correlations. , 2021, Minerva urology and nephrology.

[9]  K. Woo,et al.  Epidemiology of end-stage kidney disease. , 2021, Seminars in vascular surgery.

[10]  A. Israni,et al.  OPTN/SRTR 2019 Annual Data Report: Kidney , 2021, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[11]  S. Waikar,et al.  Subtyping CKD Patients by Consensus Clustering: The Chronic Renal Insufficiency Cohort (CRIC) Study. , 2021, Journal of the American Society of Nephrology : JASN.

[12]  L. Biancone,et al.  Impact of type 2 diabetes mellitus on kidney transplant rates and clinical outcomes among waitlisted candidates in a single center European experience , 2020, Scientific Reports.

[13]  N. Forkert,et al.  Machine Learning for Precision Medicine. , 2020, Genome.

[14]  A. Rajab,et al.  The impact of donor and recipient diabetes on renal transplant outcomes , 2020, Clinical transplantation.

[15]  C. Thongprayoon,et al.  Promises of Big Data and Artificial Intelligence in Nephrology and Transplantation , 2020, Journal of clinical medicine.

[16]  Ming-Ju Wu,et al.  Ongoing donor-transmitted diabetic kidney disease in kidney transplant recipients with fair sugar control: a single center retrospective study , 2020, BMC Nephrology.

[17]  A. Evans,et al.  Treating loss-to-follow-up as a missing data problem: a case study using a longitudinal cohort of HIV-infected patients in Haiti , 2018, BMC Public Health.

[18]  J. Gill,et al.  Association of Kidney Transplantation with Survival in Patients with Long Dialysis Exposure. , 2017, Clinical journal of the American Society of Nephrology : CJASN.

[19]  Kevin C. Eddinger,et al.  Survival Benefit of Transplantation with a Deceased Diabetic Donor Kidney Compared with Remaining on the Waitlist. , 2017, Clinical journal of the American Society of Nephrology : CJASN.

[20]  J M Smith,et al.  OPTN/SRTR 2015 Annual Data Report: Kidney , 2017, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[21]  B. Kaplan,et al.  Increasing the Use of Kidneys From Unconventional and High‐Risk Deceased Donors , 2016, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[22]  P. Reese,et al.  National outcomes of kidney transplantation from deceased diabetic donors , 2015, Kidney international.

[23]  George Michailidis,et al.  Critical limitations of consensus clustering in class discovery , 2014, Scientific Reports.

[24]  L. Ratner,et al.  Availability, Utilization and Outcomes of Deceased Diabetic Donor Kidneys; Analysis Based on the UNOS Registry , 2012, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[25]  Martin Vingron,et al.  Predicting the outcome of renal transplantation , 2012, J. Am. Medical Informatics Assoc..

[26]  Stef van Buuren,et al.  MICE: Multivariate Imputation by Chained Equations in R , 2011 .

[27]  Patrick Royston,et al.  Multiple imputation using chained equations: Issues and guidance for practice , 2011, Statistics in medicine.

[28]  John B. Carlin,et al.  Bias and efficiency of multiple imputation compared with complete‐case analysis for missing covariate values , 2010, Statistics in medicine.

[29]  A Rogier T Donders,et al.  Unpredictable bias when using the missing indicator method or complete case analysis for missing confounder values: an empirical example. , 2010, Journal of clinical epidemiology.

[30]  Matthew D. Wilkerson,et al.  ConsensusClusterPlus: a class discovery tool with confidence assessments and item tracking , 2010, Bioinform..

[31]  C. Cardella,et al.  Impact of Deceased Donor Diabetes Mellitus on Kidney Transplant Outcomes: A Propensity Score-Matched Study , 2009, Transplantation.

[32]  R. Woolson,et al.  The impact of loss to follow-up on hypothesis tests of the treatment effect for several statistical methods in substance abuse clinical trials. , 2009, Journal of substance abuse treatment.

[33]  Alan B Leichtman,et al.  Kidney transplantation as primary therapy for end-stage renal disease: a National Kidney Foundation/Kidney Disease Outcomes Quality Initiative (NKF/KDOQITM) conference. , 2008, Clinical journal of the American Society of Nephrology : CJASN.

[34]  T. Stijnen,et al.  Review: a gentle introduction to imputation of missing values. , 2006, Journal of clinical epidemiology.

[35]  R. Wolfe,et al.  Deceased-donor characteristics and the survival benefit of kidney transplantation. , 2005, JAMA.

[36]  Jill P. Mesirov,et al.  Consensus Clustering: A Resampling-Based Method for Class Discovery and Visualization of Gene Expression Microarray Data , 2003, Machine Learning.

[37]  Robert M. Merion,et al.  Donor characteristics associated with reduced graft survival: an approach to expanding the pool of kidney donors1 , 2002, Transplantation.

[38]  S. Solodushkin,et al.  Influence of Factors Associated With the Deceased-Donor on Kidney Transplant Outcomes. , 2015, Experimental and clinical transplantation : official journal of the Middle East Society for Organ Transplantation.