1
|
Jeon J, Song Y, Yu JY, Jung W, Lee K, Lee JE, Huh W, Cha WC, Jang HR. Prediction of post-donation renal function using machine learning techniques and conventional regression models in living kidney donors. J Nephrol 2024:10.1007/s40620-024-02027-1. [PMID: 39073700 DOI: 10.1007/s40620-024-02027-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2024] [Accepted: 06/30/2024] [Indexed: 07/30/2024]
Abstract
BACKGROUND Accurate prediction of renal function following kidney donation and careful selection of living donors are essential for living-kidney donation programs. We aimed to develop a prediction model for post-donation renal function following living kidney donation using machine learning. METHODS This retrospective cohort study was conducted with 823 living kidney donors between 2009 and 2020. The dataset was randomly split into training (80%) and test sets (20%). The main outcome was the post-donation estimated glomerular filtration rate (eGFR) 12 months after nephrectomy. We compared the performance of machine learning techniques, traditional regression models, and models from previous studies. The best-performing model was selected based on the mean absolute error (MAE) and root mean square error (RMSE). RESULTS The mean age of the participants was 45.2 ± 12.3 years, and 48.4% were males. The mean pre-donation and post-donation eGFRs were 101.3 ± 13.0 and 68.8 ± 12.7 mL/min/1.73 m2, respectively. The XGBoost model with the eGFR, age, serum creatinine, 24-h urine creatinine, 24-h urine sodium, creatinine clearance, cystatin C, cystatin C-based eGFR, computed tomography volume of the remaining kidney/body weight, normalized GFR of the remaining kidney measured through a diethylenetriaminepentaacetic acid scan, and sex, showed the best performance with a mean absolute error of 6.23 and root mean square error of 8.06. An easy-to-use web application titled Kidney Donation with Nephrologic Intelligence (KDNI) was developed. CONCLUSIONS The prediction model using XGBoost accurately predicted the post-donation eGFR after living kidney donation. This model can be applied in clinical practice using KDNI, the developed web application.
Collapse
Affiliation(s)
- Junseok Jeon
- Division of Nephrology, Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea
| | - Yeejun Song
- Department of Digital Health, Samsung Advanced Institute for Health Sciences and Technology (SAIHST), Sungkyunkwan University, Seoul, South Korea
- Smart Health Lab, Research Institute of Future Medicine, Samsung Medical Center, Seoul, South Korea
| | - Jae Yong Yu
- Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, South Korea
| | - Weon Jung
- Smart Health Lab, Research Institute of Future Medicine, Samsung Medical Center, Seoul, South Korea
| | - Kyungho Lee
- Division of Nephrology, Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea
| | - Jung Eun Lee
- Division of Nephrology, Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea
| | - Wooseong Huh
- Division of Nephrology, Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea
| | - Won Chul Cha
- Department of Digital Health, Samsung Advanced Institute for Health Sciences and Technology (SAIHST), Sungkyunkwan University, Seoul, South Korea.
- Smart Health Lab, Research Institute of Future Medicine, Samsung Medical Center, Seoul, South Korea.
- Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea.
| | - Hye Ryoun Jang
- Division of Nephrology, Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea.
| |
Collapse
|
2
|
López-Abad A, Pecoraro A, Boissier R, Piana A, Prudhomme T, Hevia V, Catucci CL, Dönmez MI, Breda A, Serni S, Territo A, Campi R. Prediction models for postoperative renal function after living donor nephrectomy: a systematic review. Minerva Urol Nephrol 2024; 76:148-156. [PMID: 38742550 DOI: 10.23736/s2724-6051.24.05556-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/16/2024]
Abstract
INTRODUCTION Living-donor nephrectomy (LDN) is the most valuable source of organs for kidney transplantation worldwide. The current preoperative evaluation of a potential living donor candidate does not take into account formal estimation of postoperative renal function decline after surgery using validated prediction models. The aim of this study was to summarize the available models to predict the mid- to long-term renal function following LDN, aiming to support both clinicians and patients during the decision-making process. EVIDENCE ACQUISITION A systematic review of the English-language literature was conducted following the principles highlighted by the European Association of Urology (EAU) guidelines and following the PRISMA 2020 recommendations. The protocol was registered in PROSPERO on December 10, 2022 (registration ID: CRD42022380198). In the qualitative analysis we selected the models including only preoperative variables. EVIDENCE SYNTHESIS After screening and eligibility assessment, six models from six studies met the inclusion criteria. All of them relied on retrospective patient cohorts. According to PROBAST, all studies were evaluated as high risk of bias. The models included different combinations of variables (ranging between two to four), including donor-/kidney-related factors, and preoperative laboratory tests. Donor age was the variable more often included in the models (83%), followed by history of hypertension (17%), Body Mass Index (33%), renal volume adjusted by body weight (33%) and body surface area (33%). There was significant heterogeneity in the model building strategy, the main outcome measures and the model's performance metrics. Three models were externally validated. CONCLUSIONS Few models using preoperative variables have been developed and externally validated to predict renal function after LDN. As such, the evidence is premature to recommend their use in routine clinical practice. Future research should be focused on the development and validation of user-friendly, robust prediction models, relying on granular large multicenter datasets, to support clinicians and patients during the decision-making process.
Collapse
Affiliation(s)
- Alicia López-Abad
- Department of Urology, Virgen de la Arrixaca University Hospital, Murcia, Spain
- Unit of Urological Robotic Surgery and Renal Transplantation, Careggi Hospital, University of Florence, Florence, Italy
| | - Alessio Pecoraro
- Unit of Urological Robotic Surgery and Renal Transplantation, Careggi Hospital, University of Florence, Florence, Italy
| | - Romain Boissier
- Department of Urology and Renal Transplantation, La Conception University Hospital, Marseille, France
| | - Alberto Piana
- Division of Urology, Department of Oncology, University of Turin, Turin, Italy
| | - Thomas Prudhomme
- Department of Urology, Kidney Transplantation and Andrology, Toulouse Rangueil University Hospital, Toulouse, France
| | - Vital Hevia
- Urology Department, Hospital Universitario Ramón y Cajal, Alcalá University, Madrid, Spain
| | - Claudia L Catucci
- Unit of Urological Robotic Surgery and Renal Transplantation, Careggi Hospital, University of Florence, Florence, Italy
| | - Muhammet I Dönmez
- Division of Pediatric Urology, Department of Urology, Istanbul Faculty of Medicine, University of Istanbul, Istanbul, Türkiye
| | - Alberto Breda
- Department of Urology, Puigvert Foundation, Autonomous University of Barcelona, Barcelona, Spain
| | - Sergio Serni
- Unit of Urological Robotic Surgery and Renal Transplantation, Careggi Hospital, University of Florence, Florence, Italy
- Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy
| | - Angelo Territo
- Department of Urology, Puigvert Foundation, Autonomous University of Barcelona, Barcelona, Spain
| | - Riccardo Campi
- Unit of Urological Robotic Surgery and Renal Transplantation, Careggi Hospital, University of Florence, Florence, Italy -
- Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy
| |
Collapse
|
3
|
Patel SS, Lonze BE, Chiang TPY, Al Ammary F, Segev DL, Massie AB. External Validation of Toulouse-Rangueil eGFR12 Prediction Model After Living Donor Nephrectomy. Transpl Int 2023; 36:11619. [PMID: 37745642 PMCID: PMC10511758 DOI: 10.3389/ti.2023.11619] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2023] [Accepted: 08/18/2023] [Indexed: 09/26/2023]
Abstract
Decreased postdonation eGFR is associated with a higher risk of ESRD after living kidney donation, even when accounting for predonation characteristics. The Toulouse-Rangueil model (TRM) estimates 12 month postdonation eGFR (eGFR12) to inform counseling of candidates for living donation. The TRM was validated in several single-center European cohorts but has not been validated in US donors. We assessed the TRM in living kidney donors in the US using SRTR data 1/2000-6/2021. We compared the 2021 CKD-EPI equation eGFR12 observed estimates to the TRM eGFR12 predictions. Median (IQR) bias was -3.4 (-9.3, 3.4) mL/min/1.73 m2. Bias was higher for males vs. females (bias [IQR] -4.4 [-9.9, 1.8] vs. -2.9 [-8.8, 4.1]) and younger (31-40) vs. older donors (>50) (bias -4.9 [-10.6, 3.0] vs. -2.1 [-7.5, 4.0]). Bias was also larger for Black vs. White donors (bias (-6.7 [-12.1, -0.3], p < 0.001) vs. (-3.4 [-9.1, 3.1], p < 0.001)). Overall correlation was 0.71. In a sensitivity analysis using the 2009 CKD-EPI equation, results were generally consistent with exception to a higher overall bias (bias -4.2 [-9.8, 2.4]). The TRM overestimates postdonation renal function among US donors. Overestimation was greatest for those at higher risk for postdonation ESRD including male, Black, and younger donors. A new equation is needed to estimate postdonation renal function.
Collapse
Affiliation(s)
- Suhani S. Patel
- Department of Surgery, Transplant Institute, NYU Langone Health, New York, NY, United States
| | - Bonnie E. Lonze
- Department of Surgery, Transplant Institute, NYU Langone Health, New York, NY, United States
| | - Teresa Po-Yu Chiang
- Department of Surgery, Transplant Institute, NYU Langone Health, New York, NY, United States
| | - Fawaz Al Ammary
- School of Medicine, University of California, Irvine, Irvine, CA, United States
| | - Dorry L. Segev
- Department of Surgery, Transplant Institute, NYU Langone Health, New York, NY, United States
- Scientific Registry of Transplant Recipients, Minneapolis, MN, United States
| | - Allan B. Massie
- Department of Surgery, Transplant Institute, NYU Langone Health, New York, NY, United States
| |
Collapse
|
4
|
Prudhomme T, Roumiguie M, Timsit MO. Estimation of Donor Renal Function After Living Donor Nephrectomy: The Value of the Toulouse-Rangueil Predictive Model. Transpl Int 2023; 36:11393. [PMID: 37275463 PMCID: PMC10235441 DOI: 10.3389/ti.2023.11393] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2023] [Accepted: 05/11/2023] [Indexed: 06/07/2023]
Affiliation(s)
- Thomas Prudhomme
- Department of Urology and Kidney Transplantation, Toulouse-Rangueil University Hospital, Toulouse, France
- Center for Research in Transplantation and Translational Immunology, Nantes University, INSERM, UMR 1064, Nantes, France
| | - Mathieu Roumiguie
- Department of Urology and Kidney Transplantation, Toulouse-Rangueil University Hospital, Toulouse, France
| | - Marc Olivier Timsit
- Department of Urology and Transplant Surgery, AP-HP, Necker Hospital and European Hospital Georges Pompidou, Paris, France
| |
Collapse
|
5
|
Almeida M, Calheiros Cruz G, Sousa C, Figueiredo C, Ventura S, Silvano J, Pedroso S, Martins LS, Ramos M, Malheiro J. External Validation of the Toulouse-Rangueil Predictive Model to Estimate Donor Renal Function After Living Donor Nephrectomy. Transpl Int 2023; 36:11151. [PMID: 37008717 PMCID: PMC10065159 DOI: 10.3389/ti.2023.11151] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2022] [Accepted: 03/07/2023] [Indexed: 03/19/2023]
Abstract
A predictive model to estimate post-donation glomerular filtration rate (eGFR) and risk of CKD at 1-year was developed from a Toulouse-Rangueil cohort in 2017 and showed an excellent correlation to the observed 1-year post-donation eGFR. We retrospectively analyzed all living donor kidney transplants performed at a single center from 1998 to 2020. Observed eGFR using CKD-EPI formula at 1-year post-donation was compared to the predicted eGFR using the formula eGFR (CKD-EPI, mL/min/1.73 m2) = 31.71+ (0.521 × preoperative eGFR) − (0.314 × age). 333 donors were evaluated. A good correlation (Pearson r = 0.67; p < 0.001) and concordance (Bland-Altman plot with 95% limits of agreement −21.41–26.47 mL/min/1.73 m2; p < 0.001) between predicted and observed 1-year post-donation eGFR were observed. The area under the ROC curve showed a good discriminative ability of the formula in predicting observed CKD at 1-year post-donation (AUC = 0.83; 95% CI: 0.78–0.88; p < 0.001) with optimal cutoff corresponding to a predicted eGFR of 65.25 mL/min/1.73 m2 in which the sensibility and specificity to predict CKD were respectively 77% and 75%. The model was successfully validated in our cohort, a different European population. It represents a simple and accurate tool to assist in evaluating potential donors.
Collapse
Affiliation(s)
- Manuela Almeida
- Nephrology Department, Centro Hospitalar Universitário do Porto, Porto, Portugal
- Unit for Multidisciplinary Research in Biomedicine, Abel Salazar Institute of Biomedical Sciences, University of Porto, Porto, Portugal
- *Correspondence: Manuela Almeida,
| | | | - Círia Sousa
- Centro Hospitalar de Trás os Montes e Alto Douro, Vila Real, Portugal
| | | | - Sofia Ventura
- Nephrology Department, Centro Hospitalar Universitário do Porto, Porto, Portugal
| | - José Silvano
- Nephrology Department, Centro Hospitalar Universitário do Porto, Porto, Portugal
- Unit for Multidisciplinary Research in Biomedicine, Abel Salazar Institute of Biomedical Sciences, University of Porto, Porto, Portugal
| | - Sofia Pedroso
- Nephrology Department, Centro Hospitalar Universitário do Porto, Porto, Portugal
- Unit for Multidisciplinary Research in Biomedicine, Abel Salazar Institute of Biomedical Sciences, University of Porto, Porto, Portugal
| | - La Salete Martins
- Nephrology Department, Centro Hospitalar Universitário do Porto, Porto, Portugal
- Unit for Multidisciplinary Research in Biomedicine, Abel Salazar Institute of Biomedical Sciences, University of Porto, Porto, Portugal
| | - Miguel Ramos
- Departamento de Cirurgia, Centro Hospitalar Universitário do Porto, Porto, Portugal
| | - Jorge Malheiro
- Nephrology Department, Centro Hospitalar Universitário do Porto, Porto, Portugal
- Unit for Multidisciplinary Research in Biomedicine, Abel Salazar Institute of Biomedical Sciences, University of Porto, Porto, Portugal
| |
Collapse
|
6
|
Predicting Kidney Function One Year After Nephrectomy in Living Kidney Donor Candidates. Transplantation 2021; 105:2350-2351. [PMID: 33496560 DOI: 10.1097/tp.0000000000003644] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|