Personalized Prediction of Kidney Function Decline and Network Analysis of the Risk Factors after Kidney Transplantation Using Nationwide Cohort Data
We developed a machine-learning-based model that could predict a decrease in one-year graft function after kidney transplantation, and investigated the risk factors of the decreased function. A total of 4317 cases were included from the Korean Organ Transplant Registry (2014–2019). An XGBoost model...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/11/5/1259 |
| _version_ | 1797474775648436224 |
|---|---|
| author | Moongi Simon Hong Yu-Ho Lee Jin-Min Kong Oh-Jung Kwon Cheol-Woong Jung Jaeseok Yang Myoung-Soo Kim Hyun-Wook Han Sang-Min Nam Korean Organ Transplantation Registry Study Group |
| author_facet | Moongi Simon Hong Yu-Ho Lee Jin-Min Kong Oh-Jung Kwon Cheol-Woong Jung Jaeseok Yang Myoung-Soo Kim Hyun-Wook Han Sang-Min Nam Korean Organ Transplantation Registry Study Group |
| author_sort | Moongi Simon Hong |
| collection | DOAJ |
| description | We developed a machine-learning-based model that could predict a decrease in one-year graft function after kidney transplantation, and investigated the risk factors of the decreased function. A total of 4317 cases were included from the Korean Organ Transplant Registry (2014–2019). An XGBoost model was trained to predict the recipient’s one-year estimated glomerular filtration rate (eGFR) below 45 mL/min/1.73 m<sup>2</sup> using 112 pre- and peri-transplantation variables. The network of model factors was drawn using inter-factor partial correlations and the statistical significance of each factor. The model with seven features achieved an area under the curve of 0.82, sensitivity of 0.73, and specificity of 0.79. The model prediction was associated with five-year graft and rejection-free survival. Post-transplantation hospitalization >25 days and eGFR ≥ 88.0 were the prominent risk and preventive factors, respectively. Donor age and post-transplantation eGFR < 59.8 were connected to multiple risk factors on the network. Therefore, careful donor–recipient matching in older donors, and avoiding pre-transplantation risk factors, would reduce the risk of graft dysfunction. The model might improve long-term graft outcomes by supporting early detection of graft dysfunction, and proactive risk factor control. |
| first_indexed | 2024-03-09T20:34:53Z |
| format | Article |
| id | doaj.art-50910ae82dd04f4e990e08e3b150a672 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-09T20:34:53Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-50910ae82dd04f4e990e08e3b150a6722023-11-23T23:13:14ZengMDPI AGJournal of Clinical Medicine2077-03832022-02-01115125910.3390/jcm11051259Personalized Prediction of Kidney Function Decline and Network Analysis of the Risk Factors after Kidney Transplantation Using Nationwide Cohort DataMoongi Simon Hong0Yu-Ho Lee1Jin-Min Kong2Oh-Jung Kwon3Cheol-Woong Jung4Jaeseok Yang5Myoung-Soo Kim6Hyun-Wook Han7Sang-Min Nam8Korean Organ Transplantation Registry Study GroupDepartment of Biomedical Informatics, CHA University School of Medicine, CHA University, Seongnam 13488, KoreaDivision of Nephrology, Department of Internal Medicine, CHA Bundang Medical Center, CHA University, Seongnam 13496, KoreaDepartment of Nephrology, BHS Hanseo Hospital, Busan 48253, KoreaDepartment of Surgery, College of Medicine, Han Yang University, Seoul 04763, KoreaDepartment of Surgery, Korea University Anam Hospital, Seoul 02841, KoreaDepartment of Internal Medicine, Yonsei University College of Medicine, Seoul 03722, KoreaDepartment of Surgery, Yonsei University College of Medicine, Seoul 03722, KoreaDepartment of Biomedical Informatics, CHA University School of Medicine, CHA University, Seongnam 13488, KoreaDepartment of Biomedical Informatics, CHA University School of Medicine, CHA University, Seongnam 13488, KoreaWe developed a machine-learning-based model that could predict a decrease in one-year graft function after kidney transplantation, and investigated the risk factors of the decreased function. A total of 4317 cases were included from the Korean Organ Transplant Registry (2014–2019). An XGBoost model was trained to predict the recipient’s one-year estimated glomerular filtration rate (eGFR) below 45 mL/min/1.73 m<sup>2</sup> using 112 pre- and peri-transplantation variables. The network of model factors was drawn using inter-factor partial correlations and the statistical significance of each factor. The model with seven features achieved an area under the curve of 0.82, sensitivity of 0.73, and specificity of 0.79. The model prediction was associated with five-year graft and rejection-free survival. Post-transplantation hospitalization >25 days and eGFR ≥ 88.0 were the prominent risk and preventive factors, respectively. Donor age and post-transplantation eGFR < 59.8 were connected to multiple risk factors on the network. Therefore, careful donor–recipient matching in older donors, and avoiding pre-transplantation risk factors, would reduce the risk of graft dysfunction. The model might improve long-term graft outcomes by supporting early detection of graft dysfunction, and proactive risk factor control.https://www.mdpi.com/2077-0383/11/5/1259kidney transplantationmachine learningrisk factorsgraft survival |
| spellingShingle | Moongi Simon Hong Yu-Ho Lee Jin-Min Kong Oh-Jung Kwon Cheol-Woong Jung Jaeseok Yang Myoung-Soo Kim Hyun-Wook Han Sang-Min Nam Korean Organ Transplantation Registry Study Group Personalized Prediction of Kidney Function Decline and Network Analysis of the Risk Factors after Kidney Transplantation Using Nationwide Cohort Data Journal of Clinical Medicine kidney transplantation machine learning risk factors graft survival |
| title | Personalized Prediction of Kidney Function Decline and Network Analysis of the Risk Factors after Kidney Transplantation Using Nationwide Cohort Data |
| title_full | Personalized Prediction of Kidney Function Decline and Network Analysis of the Risk Factors after Kidney Transplantation Using Nationwide Cohort Data |
| title_fullStr | Personalized Prediction of Kidney Function Decline and Network Analysis of the Risk Factors after Kidney Transplantation Using Nationwide Cohort Data |
| title_full_unstemmed | Personalized Prediction of Kidney Function Decline and Network Analysis of the Risk Factors after Kidney Transplantation Using Nationwide Cohort Data |
| title_short | Personalized Prediction of Kidney Function Decline and Network Analysis of the Risk Factors after Kidney Transplantation Using Nationwide Cohort Data |
| title_sort | personalized prediction of kidney function decline and network analysis of the risk factors after kidney transplantation using nationwide cohort data |
| topic | kidney transplantation machine learning risk factors graft survival |
| url | https://www.mdpi.com/2077-0383/11/5/1259 |
| work_keys_str_mv | AT moongisimonhong personalizedpredictionofkidneyfunctiondeclineandnetworkanalysisoftheriskfactorsafterkidneytransplantationusingnationwidecohortdata AT yuholee personalizedpredictionofkidneyfunctiondeclineandnetworkanalysisoftheriskfactorsafterkidneytransplantationusingnationwidecohortdata AT jinminkong personalizedpredictionofkidneyfunctiondeclineandnetworkanalysisoftheriskfactorsafterkidneytransplantationusingnationwidecohortdata AT ohjungkwon personalizedpredictionofkidneyfunctiondeclineandnetworkanalysisoftheriskfactorsafterkidneytransplantationusingnationwidecohortdata AT cheolwoongjung personalizedpredictionofkidneyfunctiondeclineandnetworkanalysisoftheriskfactorsafterkidneytransplantationusingnationwidecohortdata AT jaeseokyang personalizedpredictionofkidneyfunctiondeclineandnetworkanalysisoftheriskfactorsafterkidneytransplantationusingnationwidecohortdata AT myoungsookim personalizedpredictionofkidneyfunctiondeclineandnetworkanalysisoftheriskfactorsafterkidneytransplantationusingnationwidecohortdata AT hyunwookhan personalizedpredictionofkidneyfunctiondeclineandnetworkanalysisoftheriskfactorsafterkidneytransplantationusingnationwidecohortdata AT sangminnam personalizedpredictionofkidneyfunctiondeclineandnetworkanalysisoftheriskfactorsafterkidneytransplantationusingnationwidecohortdata AT koreanorgantransplantationregistrystudygroup personalizedpredictionofkidneyfunctiondeclineandnetworkanalysisoftheriskfactorsafterkidneytransplantationusingnationwidecohortdata |