Donor Kidney Evaluation

Artificial Intelligence-A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant

Delayed-graft function (DGF) might be responsible for shorter graft survival. Therefore, a clinical tool predicting its occurrence is vital for the risk assessment of transplant outcomes. In a single-center study, we conducted data mining and machine learning experiments, resulting in DGF predictive models based on random forest classifiers (RF) and an artificial neural network called multi-layer perceptron (MLP). All designed models had four common input parameters, determining the best accuracy and discriminant ability: donor’s eGFR, recipient’s BMI, donor’s BMI, and recipient–donor weight difference. RF and MLP designs, using these parameters, achieved an accuracy of 84.38% and an area under curve (AUC) 0.84. The model additionally implementing a donor’s age, gender, and Kidney Donor Profile Index (KDPI) accomplished an accuracy of 93.75% and an AUC of 0.91. The other configuration with the estimated post-transplant survival (EPTS) and the kidney donor risk profile (KDRI) achieved an accuracy of 93.75% and an AUC of 0.92. Using machine learning, we were able to assess the risk of DGF in recipients after kidney transplant from a deceased donor. Our solution is scalable and can be improved during subsequent transplants. Based on the new data, the models can achieve better outcomes.

Comprehensive assessment of deceased donor kidneys with clinical characteristics, pre-implant biopsy histopathology and hypothermic mechanical perfusion parameters is highly predictive of delayed graft function

Background: Due to the current high demand for transplant tissue, an increasing proportion of kidney donors are considered extended criteria donors, which results in a higher incidence of delayed graft function (DGF) in organ recipients. Therefore, it is important to fully investigate the risk factors of DGF, and establish a prediction system to assess donor kidney quality before transplantation.Methods: A total of 333 donation after cardiac death kidney transplant recipients were included in this retrospective study. Both univariate and multivariate analyses were used to analyze the risk factors of DGF occurrence. Receiver operating characteristic (ROC) curves were used to analyze the predictive value of variables on DGF posttransplant.Results: The donor clinical scores, kidney histopathologic Remuzzi scores and hypothermic mechanical perfusion (HMP) parameters (flow and resistance index) were all correlated. 46 recipients developed DGF postoperatively, with an incidence of 13.8% (46/333). Multivariate logistic regression analysis of the kidney transplants revealed that the independent risk factors of DGF occurrence post-transplantation included donor score (OR = 1.12, 95% CI 1.06-1.19, p < 0.001), Remuzzi score (OR = 1.21, 95% CI 1.02-1.43, p = 0.029) and acute tubular injury (ATI) score (OR = 4.72, 95% CI 2.32-9.60, p < 0.001). Prediction of DGF with ROC curve showed that the area under the curve was increased to 0.89 when all variables (donor score, Remuzzi score, ATI score and HMP resistance index) were considered together.Conclusions: Combination of donor clinical information, kidney pre-implant histopathology and HMP parameters provide a more accurate prediction of DGF occurrence post-transplantation than any of the measures alone.

Procurement Biopsies Can Predict Unfavorable Outcomes in Kidneys With Low MAPI Score Values

BACKGROUND

There are few reports about the usefulness of Maryland Aggregate Pathology Index (MAPI) score in procurement biopsies. This study aimed to evaluate the association between histopathological analysis according to MAPI and unfavorable outcomes in the first year after kidney transplantation (KT).

METHODS

This retrospective study included deceased-donor KT patients whose grafts were biopsied before transplantation and had low MAPI scores (<8) in frozen sections (FSs). Paraffin sections (PSs) were analyzed after KT. MAPI parameters were global glomerulosclerosis in more than 15% (2 patients), periglomerular fibrosis (4 patients), wall-lumen ratio of arteries >0.5 (2 patients), arteriolar hyalinosis (4 patients), and interstitial scar (3 patients). Multivariable models were used to analyze risk factors for delayed graft function (DGF), prolonged DGF, inferior renal function, and graft loss (P < .05).

RESULTS

One hundred fifty-nine KTs were included. Donors (n = 120) were predominantly men (70%) and young adults (37.68 ± 12.50 years old) who suffered a traumatic death (55.8%). Recipients were predominantly men (62.26%) and adults (45.70 ± 15.80 years old) with kidney disease of unknown etiology (39.6%). Low rates of agreement between FS and PS were observed for all MAPI criteria, with kappa values ranging from 0.28 to 0.51. Using FS, no histologic parameter was independently associated with outcomes. After adjustment, glomerulosclerosis was an independent risk factor for prolonged DGF (odds ratio = 6.18: 95% confidence interval, 1.27-30.18) and wall-lumen ratio >0.5 for inferior renal function at 1 year (odds ratio = 4.08; 95% confidence interval, 1.21-13.76).

CONCLUSION

Procurement biopsies can be useful to predict inferior outcomes even in kidneys with low MAPI scores.

Application of Nonlinear Optical Microscopic Imaging Technology for Quality Assessment of Donor Kidneys

BACKGROUND

Nonlinear optical microscopic (NLOM) imaging technique shows its high resolution imaging features in histocytology. The purpose of this study was to investigate NLOM imaging technique as a useful tool for a donor kidney quality assessment.

MATERIALS AND METHODS

Eighty-three pretransplant kidney biopsies from adult donors were analyzed retrospectively. Each specimen was paraffin-embedded and sectioned into 2 consecutive 5-μm thick sections. One section was stained with Masson trichrome, and the other was left unstained for NLOM imaging using second harmonic generation combined with two-photon excited fluorescence (SHG/TPEF). The pretransplant kidney quality was assessed by an experienced pathologist using the Remuzzi scoring system, which characterizes renal tissue morphology into 4 aspects: tubular atrophy, interstitial fibrosis, glomerulosclerosis, and vascular injury. The K coefficient was used to measure the consistency of the Remuzzi scores between conventional Masson trichrome stained images and SHG/TPEF images.

RESULTS

NLOM imaging technology can capture high-resolution tissue images from unstained renal tissue, is easy to operate, and shortens time-consuming histological processing procedures. No significant differences (P > .05) were found between the Remuzzi scores of the SHG/TPEF images and the Masson trichrome stained images. The high κ coefficients (0.804-0.895) showed a good consistency between these 2 techniques.

CONCLUSION

The NLOM technique is suitable for renal tissue imaging and could potentially be used for routine pretransplant kidney evaluation in clinical settings.