Developing clinical prognostic models to predict graft survival after renal transplantation: comparison of statistical and machine learning models
Abstract Introduction Renal transplantation is a critical treatment for end-stage renal disease, but graft failure remains a significant concern. Accurate prediction of graft survival is crucial to identify high-risk patients. This study aimed to develop prognostic models for predicting renal graft...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-025-02906-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861974613622784 |
|---|---|
| author | Getahun Mulugeta Temesgen Zewotir Awoke Seyoum Tegegne Mahteme Bekele Muleta Leja Hamza Juhar |
| author_facet | Getahun Mulugeta Temesgen Zewotir Awoke Seyoum Tegegne Mahteme Bekele Muleta Leja Hamza Juhar |
| author_sort | Getahun Mulugeta |
| collection | DOAJ |
| description | Abstract Introduction Renal transplantation is a critical treatment for end-stage renal disease, but graft failure remains a significant concern. Accurate prediction of graft survival is crucial to identify high-risk patients. This study aimed to develop prognostic models for predicting renal graft survival and compare the performance of statistical and machine learning models. Methodology The study utilized data from 278 renal transplant recipients at the Ethiopian National Kidney Transplantation Center between September 2015 and February 2022. To address the class imbalance of the data, SMOTE resampling was applied. Various models were evaluated, including Standard and penalized Cox models, Random Survival Forest, and Stochastic Gradient Boosting. Prognostic predictors were selected based on statistical significance and variable importance. Results The median graft survival time was 33 months, and the mean hazard of graft failure was 0.0755. The 3-month, 1-year, and 3-year graft survival rates were found to be 0.979, 0.953, and 0.911, respectively. The Stochastic Gradient Boosting (SGB) model demonstrated the best discrimination and calibration performance, with a C-index of 0.943 and a Brier score of 0.000351. The Ridge-based Cox model closely followed the SGB model’s prediction performance with better interpretability. The key prognostic predictors of graft survival included an episode of acute and chronic rejections, post-transplant urological complications, post-transplant nonadherence, blood urea nitrogen level, post-transplant regular exercise, and marital status. Conclusions The Stochastic Gradient Boosting model demonstrated the highest predictive performance, while the Ridge-Cox model offered better interpretability with a comparable performance. Clinicians should consider the trade-off between prediction accuracy and interpretability when selecting a model. Incorporating these findings into the clinical practice can improve risk stratification and personalized management strategies for kidney transplant recipients. |
| format | Article |
| id | doaj-art-7df5c88d8c1346258006646b875b9af7 |
| institution | Kabale University |
| issn | 1472-6947 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj-art-7df5c88d8c1346258006646b875b9af72025-02-09T12:40:17ZengBMCBMC Medical Informatics and Decision Making1472-69472025-02-0125111310.1186/s12911-025-02906-yDeveloping clinical prognostic models to predict graft survival after renal transplantation: comparison of statistical and machine learning modelsGetahun Mulugeta0Temesgen Zewotir1Awoke Seyoum Tegegne2Mahteme Bekele Muleta3Leja Hamza Juhar4Department of Statistics, Bahir Dar UniversitySchool of Mathematics, Statistics & Computer Science, KwaZulu Natal UniversityDepartment of Statistics, Bahir Dar UniversityKidney Transplant Center, St. Paul’s Hospital Millennium Medical CollegeKidney Transplant Center, St. Paul’s Hospital Millennium Medical CollegeAbstract Introduction Renal transplantation is a critical treatment for end-stage renal disease, but graft failure remains a significant concern. Accurate prediction of graft survival is crucial to identify high-risk patients. This study aimed to develop prognostic models for predicting renal graft survival and compare the performance of statistical and machine learning models. Methodology The study utilized data from 278 renal transplant recipients at the Ethiopian National Kidney Transplantation Center between September 2015 and February 2022. To address the class imbalance of the data, SMOTE resampling was applied. Various models were evaluated, including Standard and penalized Cox models, Random Survival Forest, and Stochastic Gradient Boosting. Prognostic predictors were selected based on statistical significance and variable importance. Results The median graft survival time was 33 months, and the mean hazard of graft failure was 0.0755. The 3-month, 1-year, and 3-year graft survival rates were found to be 0.979, 0.953, and 0.911, respectively. The Stochastic Gradient Boosting (SGB) model demonstrated the best discrimination and calibration performance, with a C-index of 0.943 and a Brier score of 0.000351. The Ridge-based Cox model closely followed the SGB model’s prediction performance with better interpretability. The key prognostic predictors of graft survival included an episode of acute and chronic rejections, post-transplant urological complications, post-transplant nonadherence, blood urea nitrogen level, post-transplant regular exercise, and marital status. Conclusions The Stochastic Gradient Boosting model demonstrated the highest predictive performance, while the Ridge-Cox model offered better interpretability with a comparable performance. Clinicians should consider the trade-off between prediction accuracy and interpretability when selecting a model. Incorporating these findings into the clinical practice can improve risk stratification and personalized management strategies for kidney transplant recipients.https://doi.org/10.1186/s12911-025-02906-yRenal transplantGraft survivalSMOT oversamplingPrognostic modelsStatistical modelsMachine learning models |
| spellingShingle | Getahun Mulugeta Temesgen Zewotir Awoke Seyoum Tegegne Mahteme Bekele Muleta Leja Hamza Juhar Developing clinical prognostic models to predict graft survival after renal transplantation: comparison of statistical and machine learning models BMC Medical Informatics and Decision Making Renal transplant Graft survival SMOT oversampling Prognostic models Statistical models Machine learning models |
| title | Developing clinical prognostic models to predict graft survival after renal transplantation: comparison of statistical and machine learning models |
| title_full | Developing clinical prognostic models to predict graft survival after renal transplantation: comparison of statistical and machine learning models |
| title_fullStr | Developing clinical prognostic models to predict graft survival after renal transplantation: comparison of statistical and machine learning models |
| title_full_unstemmed | Developing clinical prognostic models to predict graft survival after renal transplantation: comparison of statistical and machine learning models |
| title_short | Developing clinical prognostic models to predict graft survival after renal transplantation: comparison of statistical and machine learning models |
| title_sort | developing clinical prognostic models to predict graft survival after renal transplantation comparison of statistical and machine learning models |
| topic | Renal transplant Graft survival SMOT oversampling Prognostic models Statistical models Machine learning models |
| url | https://doi.org/10.1186/s12911-025-02906-y |
| work_keys_str_mv | AT getahunmulugeta developingclinicalprognosticmodelstopredictgraftsurvivalafterrenaltransplantationcomparisonofstatisticalandmachinelearningmodels AT temesgenzewotir developingclinicalprognosticmodelstopredictgraftsurvivalafterrenaltransplantationcomparisonofstatisticalandmachinelearningmodels AT awokeseyoumtegegne developingclinicalprognosticmodelstopredictgraftsurvivalafterrenaltransplantationcomparisonofstatisticalandmachinelearningmodels AT mahtemebekelemuleta developingclinicalprognosticmodelstopredictgraftsurvivalafterrenaltransplantationcomparisonofstatisticalandmachinelearningmodels AT lejahamzajuhar developingclinicalprognosticmodelstopredictgraftsurvivalafterrenaltransplantationcomparisonofstatisticalandmachinelearningmodels |