Abstract
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 m2 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.
Highlights
Kidney transplantation is the treatment of choice for patients with end-stage kidney disease, and offers improved survival compared with dialysis [1]
Clinical factors associated with estimated glomerular filtration rate (eGFR) < 65 mL/min/1.73 m2 at one-year post-transplantation included an advanced age of the donor and recipient, acute rejection within one year, delayed graft function, deceased donor, and the number of human leukocyte antigen (HLA) mismatches [10]
The mean one-year eGFR was 70 (SD 20) mL/min/1.73 m2, and the
Summary
Kidney transplantation is the treatment of choice for patients with end-stage kidney disease, and offers improved survival compared with dialysis [1]. Various factors are associated with late allograft failures, and the serum creatinine level at one year after transplantation can predict long-term renal allograft survival [6–8]. Clinical factors associated with eGFR < 65 mL/min/1.73 m2 at one-year post-transplantation included an advanced age of the donor and recipient, acute rejection within one year, delayed graft function, deceased donor, and the number of human leukocyte antigen (HLA) mismatches [10]. Prediction of the one-year post-transplant eGFR decrease may help to improve long-term graft function and survival. Machine learning has been used to predict acute rejection, delayed graft function, graft survival, and chronic allograft nephropathy in kidney transplantation, and has advantages over conventional statistics in terms of better performance and the identification of complex associations among predictive factors [12]. A factor network was constructed using model-chosen factors, and risk-control targets were explored
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
