Characteristics of Kidney Recipients of High Kidney Donor Profile Index Kidneys as Identified by Machine Learning Consensus Clustering

Charat Thongprayoon; Yeshwanter Radhakrishnan; Caroline C. Jadlowiec; Shennen A. Mao; Michael A. Mao; Pradeep Vaitla; Prakrati C. Acharya; Napat Leeaphorn; Wisit Kaewput; Pattharawin Pattharanitima; Supawit Tangpanithandee; Pajaree Krisanapan; Pitchaphon Nissaisorakarn; Matthew Cooper; Wisit Cheungpasitporn

doi:10.3390/jpm12121992

Characteristics of Kidney Recipients of High Kidney Donor Profile Index Kidneys as Identified by Machine Learning Consensus Clustering

Charat Thongprayoon, Yeshwanter Radhakrishnan, Caroline C. Jadlowiec, Shennen A. Mao, Michael A. Mao, Pradeep Vaitla, Prakrati C. Acharya, Napat Leeaphorn, Wisit Kaewput, Pattharawin Pattharanitima, Supawit Tangpanithandee, Pajaree Krisanapan, Pitchaphon Nissaisorakarn, Matthew Cooper, Wisit Cheungpasitporn

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

Background: Our study aimed to characterize kidney transplant recipients who received high kidney donor profile index (KDPI) kidneys using unsupervised machine learning approach. Methods: We used the OPTN/UNOS database from 2010 to 2019 to perform consensus cluster analysis based on recipient-, donor-, and transplant-related characteristics in 8935 kidney transplant recipients from deceased donors with KDPI ≥ 85%. We identified each cluster’s key characteristics using the standardized mean difference of >0.3. We compared the posttransplant outcomes among the assigned clusters. Results: Consensus cluster analysis identified 6 clinically distinct clusters of kidney transplant recipients from donors with high KDPI. Cluster 1 was characterized by young, black, hypertensive, non-diabetic patients who were on dialysis for more than 3 years before receiving kidney transplant from black donors; cluster 2 by elderly, white, non-diabetic patients who had preemptive kidney transplant or were on dialysis less than 3 years before receiving kidney transplant from older white donors; cluster 3 by young, non-diabetic, retransplant patients; cluster 4 by young, non-obese, non-diabetic patients who received dual kidney transplant from pediatric, black, non-hypertensive non-ECD deceased donors; cluster 5 by low number of HLA mismatch; cluster 6 by diabetes mellitus. Cluster 4 had the best patient survival, whereas cluster 3 had the worst patient survival. Cluster 2 had the best death-censored graft survival, whereas cluster 4 and cluster 3 had the worst death-censored graft survival at 1 and 5 years, respectively. Cluster 2 and cluster 4 had the best overall graft survival at 1 and 5 years, respectively, whereas cluster 3 had the worst overall graft survival. Conclusions: Unsupervised machine learning approach kidney transplant recipients from donors with high KDPI based on their pattern of clinical characteristics into 6 clinically distinct clusters.

Original language	English
Article number	1992
Journal	Journal of Personalized Medicine
Volume	12
Issue number	12
DOIs	https://doi.org/10.3390/jpm12121992
State	Published - Dec 2022
Externally published	Yes

Keywords

clustering
kidney donor profile index
kidney transplant
kidney transplantation
transplantation

Access to Document

10.3390/jpm12121992

Cite this

Thongprayoon, C., Radhakrishnan, Y., Jadlowiec, C. C., Mao, S. A., Mao, M. A., Vaitla, P., Acharya, P. C., Leeaphorn, N., Kaewput, W., Pattharanitima, P., Tangpanithandee, S., Krisanapan, P., Nissaisorakarn, P., Cooper, M., & Cheungpasitporn, W. (2022). Characteristics of Kidney Recipients of High Kidney Donor Profile Index Kidneys as Identified by Machine Learning Consensus Clustering. Journal of Personalized Medicine, 12(12), Article 1992. https://doi.org/10.3390/jpm12121992

@article{8d3a48230ad04fd9b29fd3cf21be33c0,

title = "Characteristics of Kidney Recipients of High Kidney Donor Profile Index Kidneys as Identified by Machine Learning Consensus Clustering",

abstract = "Background: Our study aimed to characterize kidney transplant recipients who received high kidney donor profile index (KDPI) kidneys using unsupervised machine learning approach. Methods: We used the OPTN/UNOS database from 2010 to 2019 to perform consensus cluster analysis based on recipient-, donor-, and transplant-related characteristics in 8935 kidney transplant recipients from deceased donors with KDPI ≥ 85%. We identified each cluster{\textquoteright}s key characteristics using the standardized mean difference of >0.3. We compared the posttransplant outcomes among the assigned clusters. Results: Consensus cluster analysis identified 6 clinically distinct clusters of kidney transplant recipients from donors with high KDPI. Cluster 1 was characterized by young, black, hypertensive, non-diabetic patients who were on dialysis for more than 3 years before receiving kidney transplant from black donors; cluster 2 by elderly, white, non-diabetic patients who had preemptive kidney transplant or were on dialysis less than 3 years before receiving kidney transplant from older white donors; cluster 3 by young, non-diabetic, retransplant patients; cluster 4 by young, non-obese, non-diabetic patients who received dual kidney transplant from pediatric, black, non-hypertensive non-ECD deceased donors; cluster 5 by low number of HLA mismatch; cluster 6 by diabetes mellitus. Cluster 4 had the best patient survival, whereas cluster 3 had the worst patient survival. Cluster 2 had the best death-censored graft survival, whereas cluster 4 and cluster 3 had the worst death-censored graft survival at 1 and 5 years, respectively. Cluster 2 and cluster 4 had the best overall graft survival at 1 and 5 years, respectively, whereas cluster 3 had the worst overall graft survival. Conclusions: Unsupervised machine learning approach kidney transplant recipients from donors with high KDPI based on their pattern of clinical characteristics into 6 clinically distinct clusters.",

keywords = "clustering, kidney donor profile index, kidney transplant, kidney transplantation, transplantation",

author = "Charat Thongprayoon and Yeshwanter Radhakrishnan and Jadlowiec, {Caroline C.} and Mao, {Shennen A.} and Mao, {Michael A.} and Pradeep Vaitla and Acharya, {Prakrati C.} and Napat Leeaphorn and Wisit Kaewput and Pattharawin Pattharanitima and Supawit Tangpanithandee and Pajaree Krisanapan and Pitchaphon Nissaisorakarn and Matthew Cooper and Wisit Cheungpasitporn",

note = "Publisher Copyright: {\textcopyright} 2022 by the authors.",

year = "2022",

month = dec,

doi = "10.3390/jpm12121992",

language = "English",

volume = "12",

journal = "Journal of Personalized Medicine",

issn = "2075-4426",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "12",

}

Thongprayoon, C, Radhakrishnan, Y, Jadlowiec, CC, Mao, SA, Mao, MA, Vaitla, P, Acharya, PC, Leeaphorn, N, Kaewput, W, Pattharanitima, P, Tangpanithandee, S, Krisanapan, P, Nissaisorakarn, P, Cooper, M & Cheungpasitporn, W 2022, 'Characteristics of Kidney Recipients of High Kidney Donor Profile Index Kidneys as Identified by Machine Learning Consensus Clustering', Journal of Personalized Medicine, vol. 12, no. 12, 1992. https://doi.org/10.3390/jpm12121992

TY - JOUR

T1 - Characteristics of Kidney Recipients of High Kidney Donor Profile Index Kidneys as Identified by Machine Learning Consensus Clustering

AU - Thongprayoon, Charat

AU - Radhakrishnan, Yeshwanter

AU - Jadlowiec, Caroline C.

AU - Mao, Shennen A.

AU - Mao, Michael A.

AU - Vaitla, Pradeep

AU - Acharya, Prakrati C.

AU - Leeaphorn, Napat

AU - Kaewput, Wisit

AU - Pattharanitima, Pattharawin

AU - Tangpanithandee, Supawit

AU - Krisanapan, Pajaree

AU - Nissaisorakarn, Pitchaphon

AU - Cooper, Matthew

AU - Cheungpasitporn, Wisit

PY - 2022/12

Y1 - 2022/12

N2 - Background: Our study aimed to characterize kidney transplant recipients who received high kidney donor profile index (KDPI) kidneys using unsupervised machine learning approach. Methods: We used the OPTN/UNOS database from 2010 to 2019 to perform consensus cluster analysis based on recipient-, donor-, and transplant-related characteristics in 8935 kidney transplant recipients from deceased donors with KDPI ≥ 85%. We identified each cluster’s key characteristics using the standardized mean difference of >0.3. We compared the posttransplant outcomes among the assigned clusters. Results: Consensus cluster analysis identified 6 clinically distinct clusters of kidney transplant recipients from donors with high KDPI. Cluster 1 was characterized by young, black, hypertensive, non-diabetic patients who were on dialysis for more than 3 years before receiving kidney transplant from black donors; cluster 2 by elderly, white, non-diabetic patients who had preemptive kidney transplant or were on dialysis less than 3 years before receiving kidney transplant from older white donors; cluster 3 by young, non-diabetic, retransplant patients; cluster 4 by young, non-obese, non-diabetic patients who received dual kidney transplant from pediatric, black, non-hypertensive non-ECD deceased donors; cluster 5 by low number of HLA mismatch; cluster 6 by diabetes mellitus. Cluster 4 had the best patient survival, whereas cluster 3 had the worst patient survival. Cluster 2 had the best death-censored graft survival, whereas cluster 4 and cluster 3 had the worst death-censored graft survival at 1 and 5 years, respectively. Cluster 2 and cluster 4 had the best overall graft survival at 1 and 5 years, respectively, whereas cluster 3 had the worst overall graft survival. Conclusions: Unsupervised machine learning approach kidney transplant recipients from donors with high KDPI based on their pattern of clinical characteristics into 6 clinically distinct clusters.

AB - Background: Our study aimed to characterize kidney transplant recipients who received high kidney donor profile index (KDPI) kidneys using unsupervised machine learning approach. Methods: We used the OPTN/UNOS database from 2010 to 2019 to perform consensus cluster analysis based on recipient-, donor-, and transplant-related characteristics in 8935 kidney transplant recipients from deceased donors with KDPI ≥ 85%. We identified each cluster’s key characteristics using the standardized mean difference of >0.3. We compared the posttransplant outcomes among the assigned clusters. Results: Consensus cluster analysis identified 6 clinically distinct clusters of kidney transplant recipients from donors with high KDPI. Cluster 1 was characterized by young, black, hypertensive, non-diabetic patients who were on dialysis for more than 3 years before receiving kidney transplant from black donors; cluster 2 by elderly, white, non-diabetic patients who had preemptive kidney transplant or were on dialysis less than 3 years before receiving kidney transplant from older white donors; cluster 3 by young, non-diabetic, retransplant patients; cluster 4 by young, non-obese, non-diabetic patients who received dual kidney transplant from pediatric, black, non-hypertensive non-ECD deceased donors; cluster 5 by low number of HLA mismatch; cluster 6 by diabetes mellitus. Cluster 4 had the best patient survival, whereas cluster 3 had the worst patient survival. Cluster 2 had the best death-censored graft survival, whereas cluster 4 and cluster 3 had the worst death-censored graft survival at 1 and 5 years, respectively. Cluster 2 and cluster 4 had the best overall graft survival at 1 and 5 years, respectively, whereas cluster 3 had the worst overall graft survival. Conclusions: Unsupervised machine learning approach kidney transplant recipients from donors with high KDPI based on their pattern of clinical characteristics into 6 clinically distinct clusters.

KW - clustering

KW - kidney donor profile index

KW - kidney transplant

KW - kidney transplantation

KW - transplantation

UR - http://www.scopus.com/inward/record.url?scp=85144642943&partnerID=8YFLogxK

U2 - 10.3390/jpm12121992

DO - 10.3390/jpm12121992

M3 - Article

AN - SCOPUS:85144642943

SN - 2075-4426

VL - 12

JO - Journal of Personalized Medicine

JF - Journal of Personalized Medicine

IS - 12

M1 - 1992

ER -

Characteristics of Kidney Recipients of High Kidney Donor Profile Index Kidneys as Identified by Machine Learning Consensus Clustering

Abstract

Keywords

Access to Document

Fingerprint

Cite this