A prediction model of delayed graft function in deceased donor for renal transplant: a multi-center study from China

Evaluation of split renal dysfunction using radiomics based on magnetic resonance diffusion-weighted imaging

BACKGROUND

Accurate and noninvasive assessment of split renal dysfunction is crucial, while there is lack of corresponding method clinically.

PURPOSE

To investigate the feasibility of using diffusion-weighted imaging (DWI)-based radiomics models to evaluate split renal dysfunction.

METHODS

We enrolled patients with impaired and normal renal function undergoing renal DWI examination. Glomerular filtration rate (GFR, mL/min) was measured using 99mTc-DTPA scintigraphy, which is reference standard of GFR measurement. The kidneys were classified into normal (GFR ≥40), mildly impaired (20≤ GFR < 40), moderately impaired (10≤ GFR < 20), and severely impaired (GFR < 10) renal function groups. Optimized subsets of radiomics features were selected from renal DWI images and radiomics scores (Rad-score) calculated to discriminate groups with different renal function. The radiomics model (Rad-score based) was developed in a training cohort and validated in a test cohort. Evaluations were conducted on the discrimination, calibration, and clinical application of the method.

RESULTS

The final analysis included 330 kidneys. Logistic regression was used to develop three radiomics models, model A, B, and C, which were used to distinguish normal from impaired, mild from moderate, and moderate from severe renal function, respectively. The area under the curve of the three models were 0.822, 0.704, and 0.887 in the training cohort and 0.843, 0.717, and 0.897 in the test cohort, respectively, indicating efficient discrimination performance.

CONCLUSIONS

DWI-based radiomics models have potential for evaluating split renal dysfunction and discriminating between normal and impaired renal function groups and their subgroups.

Cherry on Top or Real Need? A Review of Explainable Machine Learning in Kidney Transplantation

Research on solid organ transplantation has taken advantage of the substantial acquisition of medical data and the use of artificial intelligence (AI) and machine learning (ML) to answer diagnostic, prognostic, and therapeutic questions for many years. Nevertheless, despite the question of whether AI models add value to traditional modeling approaches, such as regression models, their "black box" nature is one of the factors that have hindered the translation from research to clinical practice. Several techniques that make such models understandable to humans were developed with the promise of increasing transparency in the support of medical decision-making. These techniques should help AI to close the gap between theory and practice by yielding trust in the model by doctors and patients, allowing model auditing, and facilitating compliance with emergent AI regulations. But is this also happening in the field of kidney transplantation? This review reports the use and explanation of "black box" models to diagnose and predict kidney allograft rejection, delayed graft function, graft failure, and other related outcomes after kidney transplantation. In particular, we emphasize the discussion on the need (or not) to explain ML models for biological discovery and clinical implementation in kidney transplantation. We also discuss promising future research paths for these computational tools.

Dynamic changes of neutrophil-to-lymphocyte ratio in brain-dead donors and delayed graft function in kidney transplant recipients

Objectives

Neutrophil-to-lymphocyte ratio (NLR) is a simple parameter implying the inflammatory status. We aimed to explore the association of brain-dead donor NLR change with delayed graft function (DGF) in kidney transplant recipients.

Methods

We retrospectively analyzed the data on 102 adult brain-dead donors and their corresponding 199 kidney transplant recipients (2018 − 2021). We calculated ΔNLR by subtracting the NLR before evaluating brain death from the preoperative NLR. Increasing donor NLR was defined as ΔNLR > 0.

Results

Forty-four (22%) recipients developed DGF after transplantation. Increasing donor NLR was significantly associated with the development of DGF in recipients (OR 2.8, 95% CI 1.2 − 6.6; p = .018), and remained significant (OR 2.6, 95% CI 1.0 − 6.4; p = .040) after adjustment of confounders including BMI, hypertension, diabetes, and the occurrence of cardiac arrest. When acute kidney injury (AKI) was included in the multivariable analysis, increasing donor NLR lost its independent correlation with DGF, while AKI remained an independent risk factor of recipient DGF (OR 4.5, 95% CI 2.7 − 7.6; p < .001). The area under the curve of combined increasing NLR and AKI in donors (0.873) for predicting DGF was superior to increasing donor NLR (0.625, p = .015) and AKI alone (0.859, p < .001).

Conclusions

Dynamic changes of donor NLR are promising in predicting post-transplant DGF. It will assist clinicians in the early recognition and management of renal graft dysfunction. Validation of this new biomarker in a large study is needed.

Effect of Perioperative Dexmedetomidine on Delayed Graft Function Following a Donation-After-Cardiac-Death Kidney Transplant: A Randomized Clinical Trial

IMPORTANCE

Delayed graft function (DGF) is a risk factor for acute rejection and graft failure after kidney transplant. Previous studies have suggested that dexmedetomidine may be renoprotective, but whether the use of dexmedetomidine would improve kidney allograft function is unknown.

OBJECTIVE

To investigate the effects of perioperative dexmedetomidine on DGF following a donation-after-cardiac-death (DCD) kidney transplant.

DESIGN, SETTING, AND PARTICIPANTS

This single-center, double-blind, placebo-controlled randomized clinical trial was conducted at The First Affiliated Hospital of Soochow University in Suzhou, China. Adults (18 years or older) who were scheduled for DCD kidney transplant were enrolled between September 1, 2019, and January 28, 2021, and then randomized to receive either dexmedetomidine or normal saline (placebo). One-year postoperative outcomes were recorded. All analyses were based on the modified intention-to-treat population.

INTERVENTIONS

Patients who were randomized to the dexmedetomidine group received a 24-hour perioperative dexmedetomidine intravenous infusion (0.4 μg/kg/h intraoperatively and 0.1 μg/kg/h postoperatively). Patients who were randomized to the normal saline group received an intravenous infusion of the placebo with the same dose regimen as the dexmedetomidine.

MAIN OUTCOMES AND MEASURES

The primary outcome was the incidence of DGF, defined as the need for dialysis in the first posttransplant week. The prespecified secondary outcomes were in-hospital repeated dialysis in the first posttransplant week, in-hospital acute rejection, and serum creatinine, serum cystatin C, estimated glomerular filtration rate, need for dialysis, and patient survival on posttransplant day 30.

RESULTS

Of the 114 patients enrolled, 111 completed the study (mean [SD] age, 43.4 [10.8] years; 64 male patients [57.7%]), of whom 56 were randomized to the dexmedetomidine group and 55 to the normal saline group. Dexmedetomidine infusion compared with normal saline reduced the incidence of DGF (17.9% vs 34.5%; odds ratio [OR], 0.41; 95% CI, 0.17-0.98; P = .04) and repeated dialysis (12.5% vs 30.9%; OR, 0.32; 95% CI, 0.13-0.88; P = .02, which was not statistically significant after multiple testing corrections), without significant effect on other secondary outcomes. Dexmedetomidine vs normal saline infusion led to a higher median (IQR) creatinine clearance rate on postoperative days 1 (9.9 [4.9-21.2] mL/min vs 7.9 [2.0-10.4] mL/min) and 2 (29.6 [9.7-67.4] mL/min vs 14.6 [3.8-45.1] mL/min) as well as increased median (IQR) urine output on postoperative days 2 (106.5 [66.3-175.6] mL/h vs 82.9 [27.1-141.9] mL/h) and 7 (126.1 [98.0-151.3] mL/h vs 107.0 [82.5-137.5] mL/h) and at hospital discharge discharge (110.4 [92.8-121.9] mL/h vs 97.1 [77.5-113.8] mL/h). Three patients (5.5%) from the normal saline group developed allograft failure by the post hoc 1-year follow-up visit.

CONCLUSIONS AND RELEVANCE

This randomized clinical trial found that 24-hour perioperative dexmedetomidine decreased the incidence of DGF after DCD kidney transplant. The findings support the use of dexmedetomidine in kidney transplants.

TRIAL REGISTRATION

Chinese Clinical Trial Registry Identifier: ChiCTR1900025493.