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 uniqu...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/12/6/859 |
| _version_ | 1797485592332730368 |
|---|---|
| author | Charat Thongprayoon Caroline C. Jadlowiec Wisit Kaewput Pradeep Vaitla Shennen A. Mao Michael A. Mao Napat Leeaphorn Fawad Qureshi Pattharawin Pattharanitima Fahad Qureshi Prakrati C. Acharya Pitchaphon Nissaisorakarn Matthew Cooper Wisit Cheungpasitporn |
| author_facet | Charat Thongprayoon Caroline C. Jadlowiec Wisit Kaewput Pradeep Vaitla Shennen A. Mao Michael A. Mao Napat Leeaphorn Fawad Qureshi Pattharawin Pattharanitima Fahad Qureshi Prakrati C. Acharya Pitchaphon Nissaisorakarn Matthew Cooper Wisit Cheungpasitporn |
| author_sort | Charat Thongprayoon |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T23:21:53Z |
| format | Article |
| id | doaj.art-f629db86a66f46e3881c11959a1f164a |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-09T23:21:53Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-f629db86a66f46e3881c11959a1f164a2023-11-23T17:26:41ZengMDPI AGJournal of Personalized Medicine2075-44262022-05-0112685910.3390/jpm12060859Distinct Phenotypes of Kidney Transplant Recipients in the United States with Limited Functional Status as Identified through Machine Learning Consensus ClusteringCharat Thongprayoon0Caroline C. Jadlowiec1Wisit Kaewput2Pradeep Vaitla3Shennen A. Mao4Michael A. Mao5Napat Leeaphorn6Fawad Qureshi7Pattharawin Pattharanitima8Fahad Qureshi9Prakrati C. Acharya10Pitchaphon Nissaisorakarn11Matthew Cooper12Wisit Cheungpasitporn13Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USADivision of Transplant Surgery, Mayo Clinic, Phoenix, AZ 85054, USADepartment of Military and Community Medicine, Phramongkutklao College of Medicine, Bangkok 10400, ThailandDivision of Nephrology, University of Mississippi Medical Center, Jackson, MS 39216, USADivision of Transplant Surgery, Mayo Clinic, Jacksonville, FL 32224, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Jacksonville, FL 32224, USARenal Transplant Program, University of Missouri-Kansas City School of Medicine/Saint Luke’s Health System, Kansas City, MO 64108, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USADepartment of Internal Medicine, Faculty of Medicine, Thammasat University, Pathum Thani 12120, ThailandSchool of Medicine, University of Missouri-Kansas City, Kansas City, MO 64108, USADivision of Nephrology, Texas Tech Health Sciences Center El Paso, El Paso, TX 79905, USADepartment of Medicine, Division of Nephrology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USAMedstar Georgetown Transplant Institute, Georgetown University School of Medicine, Washington, DC 21042, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USABackground: 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.https://www.mdpi.com/2075-4426/12/6/859functional statusdisabilitydisabledkidney transplanttransplantationclustering |
| spellingShingle | Charat Thongprayoon Caroline C. Jadlowiec Wisit Kaewput Pradeep Vaitla Shennen A. Mao Michael A. Mao Napat Leeaphorn Fawad Qureshi Pattharawin Pattharanitima Fahad Qureshi Prakrati C. Acharya Pitchaphon Nissaisorakarn Matthew Cooper Wisit Cheungpasitporn Distinct Phenotypes of Kidney Transplant Recipients in the United States with Limited Functional Status as Identified through Machine Learning Consensus Clustering Journal of Personalized Medicine functional status disability disabled kidney transplant transplantation clustering |
| title | Distinct Phenotypes of Kidney Transplant Recipients in the United States with Limited Functional Status as Identified through Machine Learning Consensus Clustering |
| title_full | Distinct Phenotypes of Kidney Transplant Recipients in the United States with Limited Functional Status as Identified through Machine Learning Consensus Clustering |
| title_fullStr | Distinct Phenotypes of Kidney Transplant Recipients in the United States with Limited Functional Status as Identified through Machine Learning Consensus Clustering |
| title_full_unstemmed | Distinct Phenotypes of Kidney Transplant Recipients in the United States with Limited Functional Status as Identified through Machine Learning Consensus Clustering |
| title_short | Distinct Phenotypes of Kidney Transplant Recipients in the United States with Limited Functional Status as Identified through Machine Learning Consensus Clustering |
| title_sort | distinct phenotypes of kidney transplant recipients in the united states with limited functional status as identified through machine learning consensus clustering |
| topic | functional status disability disabled kidney transplant transplantation clustering |
| url | https://www.mdpi.com/2075-4426/12/6/859 |
| work_keys_str_mv | AT charatthongprayoon distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT carolinecjadlowiec distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT wisitkaewput distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT pradeepvaitla distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT shennenamao distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT michaelamao distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT napatleeaphorn distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT fawadqureshi distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT pattharawinpattharanitima distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT fahadqureshi distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT prakraticacharya distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT pitchaphonnissaisorakarn distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT matthewcooper distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering AT wisitcheungpasitporn distinctphenotypesofkidneytransplantrecipientsintheunitedstateswithlimitedfunctionalstatusasidentifiedthroughmachinelearningconsensusclustering |