Identifying Factors Predicting Kidney Graft Survival in Chile Using Elastic-Net-Regularized Cox’s Regression
<i>Background and Objectives</i>: We developed a predictive statistical model to identify donor–recipient characteristics related to kidney graft survival in the Chilean population. Given the large number of potential predictors relative to the sample size, we implemented an automated va...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Medicina |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1648-9144/58/10/1348 |
| _version_ | 1797471641616252928 |
|---|---|
| author | Leandro Magga Simón Maturana Marcelo Olivares Martín Valdevenito Josefa Cabezas Javier Chapochnick Fernando González Alvaro Kompatzki Hans Müller Jacqueline Pefaur Camilo Ulloa Ricardo Valjalo |
| author_facet | Leandro Magga Simón Maturana Marcelo Olivares Martín Valdevenito Josefa Cabezas Javier Chapochnick Fernando González Alvaro Kompatzki Hans Müller Jacqueline Pefaur Camilo Ulloa Ricardo Valjalo |
| author_sort | Leandro Magga |
| collection | DOAJ |
| description | <i>Background and Objectives</i>: We developed a predictive statistical model to identify donor–recipient characteristics related to kidney graft survival in the Chilean population. Given the large number of potential predictors relative to the sample size, we implemented an automated variable selection mechanism that could be revised in future studies as more national data is collected. <i>Materials and Methods</i>: A retrospective multicenter study was conducted to analyze data from 822 adult kidney transplant recipients from adult donors between 1998 and 2018. To the best of our knowledge, this is the largest kidney transplant database to date in Chile. A procedure based on a cross-validated regularized Cox regression using the Elastic Net penalty was applied to objectively identify predictors of death-censored graft failure. Hazard ratios were estimated by adjusting a multivariate Cox regression with the selected predictors. <i>Results</i>: Seven variables were associated with the risk of death-censored graft failure; four from the donor: age (HR = 1.02, 95% CI: 1.00–1.03), male sex (HR = 0.64, 95% CI: 0.46–0.90), history of hypertension (HR = 1.49, 95% CI: 0.98–2.28), and history of diabetes (HR = 2.04, 95% CI: 0.97–4.29); two from the recipient: years on dialysis log-transformation (HR = 1.29, 95% CI: 0.99–1.67) and history of previous solid organ transplantation (HR = 2.02, 95% CI: 1.18–3.47); and one from the transplant: number of HLA mismatches (HR = 1.13, 95% CI: 0.99–1.28). Only the latter is considered for patient prioritization in deceased kidney allocation in Chile. <i>Conclusions</i>: A risk model for kidney graft failure was developed and trained for the Chilean population, providing objective criteria which can be used to improve efficiency in deceased kidney allocation. |
| first_indexed | 2024-03-09T19:51:04Z |
| format | Article |
| id | doaj.art-45f111a3e67a4e0f9e22f86c995263c5 |
| institution | Directory Open Access Journal |
| issn | 1010-660X 1648-9144 |
| language | English |
| last_indexed | 2024-03-09T19:51:04Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Medicina |
| spelling | doaj.art-45f111a3e67a4e0f9e22f86c995263c52023-11-24T01:09:36ZengMDPI AGMedicina1010-660X1648-91442022-09-015810134810.3390/medicina58101348Identifying Factors Predicting Kidney Graft Survival in Chile Using Elastic-Net-Regularized Cox’s RegressionLeandro Magga0Simón Maturana1Marcelo Olivares2Martín Valdevenito3Josefa Cabezas4Javier Chapochnick5Fernando González6Alvaro Kompatzki7Hans Müller8Jacqueline Pefaur9Camilo Ulloa10Ricardo Valjalo11Department of Industrial Engineering, University of Chile, Santiago 8370456, ChileDepartment of Industrial Engineering, University of Chile, Santiago 8370456, ChileDepartment of Industrial Engineering, University of Chile, Santiago 8370456, ChileDepartment of Industrial Engineering, University of Chile, Santiago 8370456, ChileDepartment of Industrial Engineering, University of Chile, Santiago 8370456, ChileClínica Santa María, Santiago 7520378, ChileHospital del Salvador, Santiago 7500922, ChileHospital Sótero del Río, Santiago 8207257, ChileHospital Las Higueras, Talcahuano 4270918, ChileHospital Barros Luco Trudeau, Santiago 8900085, ChileClínica Alemana de Santiago, Santiago 8320000, ChileHospital del Salvador, Santiago 7500922, Chile<i>Background and Objectives</i>: We developed a predictive statistical model to identify donor–recipient characteristics related to kidney graft survival in the Chilean population. Given the large number of potential predictors relative to the sample size, we implemented an automated variable selection mechanism that could be revised in future studies as more national data is collected. <i>Materials and Methods</i>: A retrospective multicenter study was conducted to analyze data from 822 adult kidney transplant recipients from adult donors between 1998 and 2018. To the best of our knowledge, this is the largest kidney transplant database to date in Chile. A procedure based on a cross-validated regularized Cox regression using the Elastic Net penalty was applied to objectively identify predictors of death-censored graft failure. Hazard ratios were estimated by adjusting a multivariate Cox regression with the selected predictors. <i>Results</i>: Seven variables were associated with the risk of death-censored graft failure; four from the donor: age (HR = 1.02, 95% CI: 1.00–1.03), male sex (HR = 0.64, 95% CI: 0.46–0.90), history of hypertension (HR = 1.49, 95% CI: 0.98–2.28), and history of diabetes (HR = 2.04, 95% CI: 0.97–4.29); two from the recipient: years on dialysis log-transformation (HR = 1.29, 95% CI: 0.99–1.67) and history of previous solid organ transplantation (HR = 2.02, 95% CI: 1.18–3.47); and one from the transplant: number of HLA mismatches (HR = 1.13, 95% CI: 0.99–1.28). Only the latter is considered for patient prioritization in deceased kidney allocation in Chile. <i>Conclusions</i>: A risk model for kidney graft failure was developed and trained for the Chilean population, providing objective criteria which can be used to improve efficiency in deceased kidney allocation.https://www.mdpi.com/1648-9144/58/10/1348kidney transplantationrisk predictiongraft survivalregularized modelsElastic Net |
| spellingShingle | Leandro Magga Simón Maturana Marcelo Olivares Martín Valdevenito Josefa Cabezas Javier Chapochnick Fernando González Alvaro Kompatzki Hans Müller Jacqueline Pefaur Camilo Ulloa Ricardo Valjalo Identifying Factors Predicting Kidney Graft Survival in Chile Using Elastic-Net-Regularized Cox’s Regression Medicina kidney transplantation risk prediction graft survival regularized models Elastic Net |
| title | Identifying Factors Predicting Kidney Graft Survival in Chile Using Elastic-Net-Regularized Cox’s Regression |
| title_full | Identifying Factors Predicting Kidney Graft Survival in Chile Using Elastic-Net-Regularized Cox’s Regression |
| title_fullStr | Identifying Factors Predicting Kidney Graft Survival in Chile Using Elastic-Net-Regularized Cox’s Regression |
| title_full_unstemmed | Identifying Factors Predicting Kidney Graft Survival in Chile Using Elastic-Net-Regularized Cox’s Regression |
| title_short | Identifying Factors Predicting Kidney Graft Survival in Chile Using Elastic-Net-Regularized Cox’s Regression |
| title_sort | identifying factors predicting kidney graft survival in chile using elastic net regularized cox s regression |
| topic | kidney transplantation risk prediction graft survival regularized models Elastic Net |
| url | https://www.mdpi.com/1648-9144/58/10/1348 |
| work_keys_str_mv | AT leandromagga identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT simonmaturana identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT marceloolivares identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT martinvaldevenito identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT josefacabezas identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT javierchapochnick identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT fernandogonzalez identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT alvarokompatzki identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT hansmuller identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT jacquelinepefaur identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT camiloulloa identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression AT ricardovaljalo identifyingfactorspredictingkidneygraftsurvivalinchileusingelasticnetregularizedcoxsregression |