A Machine Learning Approach Using Survival Statistics to Predict Graft Survival in Kidney Transplant Recipients: A Multicenter Cohort Study
Abstract Accurate prediction of graft survival after kidney transplant is limited by the complexity and heterogeneity of risk factors influencing allograft survival. In this study, we applied machine learning methods, in combination with survival statistics, to build new prediction models of graft s...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2017-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-017-08008-8 |
| _version_ | 1818840541815635968 |
|---|---|
| author | Kyung Don Yoo Junhyug Noh Hajeong Lee Dong Ki Kim Chun Soo Lim Young Hoon Kim Jung Pyo Lee Gunhee Kim Yon Su Kim |
| author_facet | Kyung Don Yoo Junhyug Noh Hajeong Lee Dong Ki Kim Chun Soo Lim Young Hoon Kim Jung Pyo Lee Gunhee Kim Yon Su Kim |
| author_sort | Kyung Don Yoo |
| collection | DOAJ |
| description | Abstract Accurate prediction of graft survival after kidney transplant is limited by the complexity and heterogeneity of risk factors influencing allograft survival. In this study, we applied machine learning methods, in combination with survival statistics, to build new prediction models of graft survival that included immunological factors, as well as known recipient and donor variables. Graft survival was estimated from a retrospective analysis of the data from a multicenter cohort of 3,117 kidney transplant recipients. We evaluated the predictive power of ensemble learning algorithms (survival decision tree, bagging, random forest, and ridge and lasso) and compared outcomes to those of conventional models (decision tree and Cox regression). Using a conventional decision tree model, the 3-month serum creatinine level post-transplant (cut-off, 1.65 mg/dl) predicted a graft failure rate of 77.8% (index of concordance, 0.71). Using a survival decision tree model increased the index of concordance to 0.80, with the episode of acute rejection during the first year post-transplant being associated with a 4.27-fold increase in the risk of graft failure. Our study revealed that early acute rejection in the first year is associated with a substantially increased risk of graft failure. Machine learning methods may provide versatile and feasible tools for forecasting graft survival. |
| first_indexed | 2024-12-19T04:11:50Z |
| format | Article |
| id | doaj.art-5c2ccde16bb4430ba399edceb12e297c |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-19T04:11:50Z |
| publishDate | 2017-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-5c2ccde16bb4430ba399edceb12e297c2022-12-21T20:36:24ZengNature PortfolioScientific Reports2045-23222017-08-017111210.1038/s41598-017-08008-8A Machine Learning Approach Using Survival Statistics to Predict Graft Survival in Kidney Transplant Recipients: A Multicenter Cohort StudyKyung Don Yoo0Junhyug Noh1Hajeong Lee2Dong Ki Kim3Chun Soo Lim4Young Hoon Kim5Jung Pyo Lee6Gunhee Kim7Yon Su Kim8Department of Internal Medicine, Dongguk University College of MedicineDepartment of Computer Science and Engineering, College of Engineering, Seoul National UniversityDepartment of Internal Medicine, Seoul National University College of MedicineDepartment of Internal Medicine, Seoul National University College of MedicineDepartment of Internal Medicine, Seoul National University Boramae Medical CenterDepartment of Surgery, College of Medicine, Ulsan University, Asan Medical CenterDepartment of Internal Medicine, Seoul National University Boramae Medical CenterDepartment of Computer Science and Engineering, College of Engineering, Seoul National UniversityDepartment of Internal Medicine, Seoul National University College of MedicineAbstract Accurate prediction of graft survival after kidney transplant is limited by the complexity and heterogeneity of risk factors influencing allograft survival. In this study, we applied machine learning methods, in combination with survival statistics, to build new prediction models of graft survival that included immunological factors, as well as known recipient and donor variables. Graft survival was estimated from a retrospective analysis of the data from a multicenter cohort of 3,117 kidney transplant recipients. We evaluated the predictive power of ensemble learning algorithms (survival decision tree, bagging, random forest, and ridge and lasso) and compared outcomes to those of conventional models (decision tree and Cox regression). Using a conventional decision tree model, the 3-month serum creatinine level post-transplant (cut-off, 1.65 mg/dl) predicted a graft failure rate of 77.8% (index of concordance, 0.71). Using a survival decision tree model increased the index of concordance to 0.80, with the episode of acute rejection during the first year post-transplant being associated with a 4.27-fold increase in the risk of graft failure. Our study revealed that early acute rejection in the first year is associated with a substantially increased risk of graft failure. Machine learning methods may provide versatile and feasible tools for forecasting graft survival.https://doi.org/10.1038/s41598-017-08008-8 |
| spellingShingle | Kyung Don Yoo Junhyug Noh Hajeong Lee Dong Ki Kim Chun Soo Lim Young Hoon Kim Jung Pyo Lee Gunhee Kim Yon Su Kim A Machine Learning Approach Using Survival Statistics to Predict Graft Survival in Kidney Transplant Recipients: A Multicenter Cohort Study Scientific Reports |
| title | A Machine Learning Approach Using Survival Statistics to Predict Graft Survival in Kidney Transplant Recipients: A Multicenter Cohort Study |
| title_full | A Machine Learning Approach Using Survival Statistics to Predict Graft Survival in Kidney Transplant Recipients: A Multicenter Cohort Study |
| title_fullStr | A Machine Learning Approach Using Survival Statistics to Predict Graft Survival in Kidney Transplant Recipients: A Multicenter Cohort Study |
| title_full_unstemmed | A Machine Learning Approach Using Survival Statistics to Predict Graft Survival in Kidney Transplant Recipients: A Multicenter Cohort Study |
| title_short | A Machine Learning Approach Using Survival Statistics to Predict Graft Survival in Kidney Transplant Recipients: A Multicenter Cohort Study |
| title_sort | machine learning approach using survival statistics to predict graft survival in kidney transplant recipients a multicenter cohort study |
| url | https://doi.org/10.1038/s41598-017-08008-8 |
| work_keys_str_mv | AT kyungdonyoo amachinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT junhyugnoh amachinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT hajeonglee amachinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT dongkikim amachinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT chunsoolim amachinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT younghoonkim amachinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT jungpyolee amachinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT gunheekim amachinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT yonsukim amachinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT kyungdonyoo machinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT junhyugnoh machinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT hajeonglee machinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT dongkikim machinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT chunsoolim machinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT younghoonkim machinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT jungpyolee machinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT gunheekim machinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy AT yonsukim machinelearningapproachusingsurvivalstatisticstopredictgraftsurvivalinkidneytransplantrecipientsamulticentercohortstudy |