Skip to main content
PLOS One logoLink to PLOS One
. 2020 Feb 6;15(2):e0228597. doi: 10.1371/journal.pone.0228597

The impact of deceased donor maintenance on delayed kidney allograft function: A machine learning analysis

Silvana Daher Costa 1,2,3, Luis Gustavo Modelli de Andrade 4, Francisco Victor Carvalho Barroso 1, Cláudia Maria Costa de Oliveira 2,3, Elizabeth De Francesco Daher 1, Paula Frassinetti Castelo Branco Camurça Fernandes 2, Ronaldo de Matos Esmeraldo 3, Tainá Veras de Sandes-Freitas 1,3,*
Editor: Frank JMF Dor5
PMCID: PMC7004552  PMID: 32027717

Abstract

Background

This study evaluated the risk factors for delayed graft function (DGF) in a country where its incidence is high, detailing donor maintenance-related (DMR) variables and using machine learning (ML) methods beyond the traditional regression-based models.

Methods

A total of 443 brain dead deceased donor kidney transplants (KT) from two Brazilian centers were retrospectively analyzed and the following DMR were evaluated using predictive modeling: arterial blood gas pH, serum sodium, blood glucose, urine output, mean arterial pressure, vasopressors use, and reversed cardiac arrest.

Results

Most patients (95.7%) received kidneys from standard criteria donors. The incidence of DGF was 53%. In multivariable logistic regression analysis, DMR variables did not impact on DGF occurrence. In post-hoc analysis including only KT with cold ischemia time<21h (n = 220), urine output in 24h prior to recovery surgery (OR = 0.639, 95%CI 0.444–0.919) and serum sodium (OR = 1.030, 95%CI 1.052–1.379) were risk factors for DGF. Using elastic net regularized regression model and ML analysis (decision tree, neural network and support vector machine), urine output and other DMR variables emerged as DGF predictors: mean arterial pressure, ≥ 1 or high dose vasopressors and blood glucose.

Conclusions

Some DMR variables were associated with DGF, suggesting a potential impact of variables reflecting poor clinical and hemodynamic status on the incidence of DGF.

Introduction

Brazilian studies have reported incidences of delayed graft function (DGF) between 50 and 70%, 2 to 3-fold higher than the rates described by American and European cohorts, despite similar or more favorable recipient and donor demographics [16]. A Brazilian study reported 22.7% incidence of delayed kidney function in a cohort of simultaneous pancreas-kidney transplants, despite a short mean cold ischemia time of 14h and the use of ideal donors [7]. With similar demographics, international cohorts reported incidences of 4–5% [8, 9]. Notable, similar to demonstrated in American and European cohorts, DGF in Brazilian transplant recipients has negative impact on short and long-term outcomes [4, 6, 10].

There is no robust evidence explaining the high DGF incidence in our country, but it is likely that the suboptimal maintenance care of potential donors before organ recovery has an important role. Of note, recent studies have shown that achieving optimal donor maintenance parameters is associated with significant decrease in DGF occurrence [11, 12].

Traditionally, studies evaluating risk factors for DGF adopt standard statistical approaches, such as logistic regression. These models are useful in analysis using few independent variables, mainly when the effect of the predictor on the outcome is linear and homogeneous. The assumptions required to regression-based models are often not reached in clinical research and important predictor variables may be obscured. Machine learning (ML) methods can improve precision and accuracy in predicting events, by using more sensitive statistical methods, with data mining techniques and complex data interactions modeling non-linear interactions [1315]. As an example, Decruyenaere et al. demonstrated that logistic regression was not the ideal method for DGF prediction in a Belgian cohort and ML methods performed better discriminative capacity [16]. Additionally, other regression-based models are useful and present better performance, depending on the number of events, number of predictors, variables characteristic and distribution [17].

This study aimed to evaluate the risk factors for DGF, including in the analysis donor maintenance-related (DMR) variables, which were thoroughly investigated from multidisciplinary records. To increase the analysis accuracy and properly investigate the impact of donor maintenance on DGF occurrence, we selected a cohort of brain dead donor (DBD) kidney transplants (KT) performed in a Brazilian region where DGF incidence is high despite the predominance of ideal donors. In addition, we used ML methods for data analysis beyond regression models.

Materials and methods

Study design

This study is a retrospective analysis from all deceased donor KT recipients older than 16 years of age, performed between January 1st 2015 and December 31st 2017 at two Brazilian transplant centers, located in a region with locally predominant use of standard criteria donors [18]. Preemptive, multiorgan transplants, recipients of machine perfused grafts and those who lost their grafts or died within 7 days after KT were excluded. In compliance with Brazilian law, all donors were brain dead.

Data were retrospectively collected by systematic review of medical charts and electronic database. Patient records and information was anonymized and de-identified prior to analysis. Due to the observational and retrospective nature of the study, with data anonymously analyzed, informed consent was not obtained.

The study was performed in accordance with ethical standards of National Health Council Resolution 466/12 and Declaration of Helsinki, and was approved by Institutional Review Board (IRB) of the Federal University of Ceará (Ethics Committee approval number: 2.004.286) and by the IRBs of all hospitals involved in the donation and transplantation processes: Walter Cantídio University Hospital (2.183.661), Instituto José Frota (2.183.661) and Hospital Geral de Fortaleza (2.059.876).

Definitions

Delayed graft function was defined as the requirement for at least one dialysis session during the first week after KT, regardless of the clinical indication [19]. DGF duration was assessed by the time until the last dialysis session, and by the number of sessions performed in this period.

To better test the hypothesis that variables not included in traditional DGF predictive models could explain the high incidence in our country, we opted to calculate the expected incidence of DGF using the nomogram described by Irish et al [1] as a starting point of the study. Among all available DGF predictive models, Irish nomogram has demonstrated the best predictive power in validation studies including non-American patients [20, 21]. This nomogram was developed using United Network for Organ Sharing / Organ Procurement and Transplantation Network (UNOS/OPTN) database and include the following variables: recipient ethnicity, gender, body mass index (BMI), and history of previous KT, diabetes or blood transfusion; time on dialysis, peak panel reactive antibodies (PRA), human leucocyte antigens mismatches (HLA MM); donor age, weight, history of hypertension and terminal serum creatinine (sCr), cause of death, donation after cardiac death, cold ischemia time (CIT), and warm ischemia time [1]. Since Irish nomogram does not allow the inclusion of machine-perfused kidneys, we opted to exclude them.

Donor maintenance parameters were evaluated using the Donor Management Goals (DMG) previously described by US Department of Health and Human Services, Health Resources and Services Administration (HRSA) [11, 22], with adaptations considering local peculiarities and the retrospective nature of the study: the lowest arterial blood gas pH during hospitalization was captured and patients who presented values between 7.3 and 7.45 were considered in the goal; the highest serum sodium (Na+) during hospital stay was recorded and patients who presented values between 135 and 155 mEq/L were considered in the goal; the target for the highest blood glucose was ≤ 150 mg/dL; diuresis in the last 24h prior the recovery surgery was considered adequate when between 0.5 and 3 mL/Kg/h; the lowest mean arterial pressure was in the goal when between 60 and 110 mmHg; and target for vasopressors was the use of ≤ 1 vasoactive drug with norepinephrine <0.5 μg/Kg/min. The highest creatine phosphokinase (CPK), history of reversed cardiac arrest and acute kidney injury during hospitalization were also evaluated.

Statistical analysis

Categorical variables were presented as frequency and percentage and compared using Chi-square or Fisher tests. Normally distributed continuous variables were summarized as mean and standard deviation and compared using Student’s t-test. Median was included in description of non-parametric continuous variables and comparison was performed using Mann Whitney-test. A multivariable logistic regression model was fitted to compute covariate-adjusted odds ratios (OR) for DGF. Twenty-seven variables were included in the model. Collinear variables (“final sCr” and “difference between final and initial sCr”) and those with more than 10% of missing values (“CPK”) were excluded. Diabetic donors were also excluded, since this was a near-zero variance predictor (all patients who received grafts from diabetic donors developed DGF). A p-value of <0.15 in univariable analysis was considered statistically significant for including variables in multivariable analysis. For all other analysis, a p-value of <0.05 was considered statistically significant. Statistical analysis was performed using SPSS v.23.0 software (SPSS, Inc., Chicago, IL, USA).

Predictive models for DGF were constructed using a supervised model, according to the following steps: data acquisition, data processing, model construction, and model evaluation. In data processing step, the outcome category was balanced to achieve equal proportions. In pre-process we perform recursive feature elimination to select the predictable variables with better correlation with the outcome. Variables with moderate / strong correlation with DGF (r > 0.80) were included in the model.

Population was randomly divided into training and testing set with a stratified 70:30 split. Six supervised ML algorithms were developed with this subset of variables in the training set: neural network (NN), support vector machine (SVM), C5 decision tree (DT), CHAID DT, k-nearest neighbors (KNN) and logistic regression with stepwise selection. Area under the receiver operating curve (AUC) was calculated to test the ability of each model to distinguish patients in testing set. SPSS Modeler v.18.1 (IBM, Armonk, NY, USA) was used to construct predictive models.

As an additional sensitivity analysis, we performed Elastic Net regression, a regularization model that mix Lasso and Ridge regressions. While Lasso regression enhances the prediction accuracy and interpretability of the statistical model by variable selection and regularization, Ridge regression improves prediction by shrinking large regression coefficients to reduce overfitting. Elastic net regression also provides a more interpretable model when compared to black-box results of ML methods. For this analysis, numerical predictors were normalized by a Box and Cox transformation and after center and scale. Median were imputed for missing values. Categorical predictors were dummy encoded. We used an alpha of 0.1 and 10-fold cross-validation to search lambda. After an optimal search of a lambda, we perform an elastic net with R package glmnet [23]. Those coefficients inferior or greater than zero are considered relevant predictors. Variables whose coefficient was zero were considered not important for DGF prediction.

Results

Recipient and donor demographics

From 954 KT performed in the period, 30 were living donor transplants, 70 were allocated to patients younger than 16 years, 16 were multiorgan transplants, 8 were preemptive KT, 365 recipients received machine perfused grafts, and 22 lost the graft or died in the first week. The final analysis included 443 DD KT. The incidence of DGF was 53%, the mean time of DGF was 11.8 ± 15.0 days (median 7 days) and mean number of dialysis sessions was 5.0 ± 5.1 (median 4). According to Irish nomogram, the expected incidence of DGF was 19% and this tool showed poor predictive accuracy (AUC 0.685).

Recipient and donor demographic characteristics are detailed in Tables 1 and 2. Patients in DGF group were older (45.6 ± 14.4 vs. 42.6 ± 15.0 years old, p = 0.030), presented higher prevalence of pretransplant diabetes (21.3 vs. 13.5%, p = 0.034), and longer time on dialysis (36 vs. 27 months, p = 0.001). Donors in DGF group showed higher mean age (33.2 ± 12.6 vs. 28.5 ± 12.3 years old, p<0.001), higher body mass index (BMI) (25.7 ± 3.5 vs. 24.9 ± 4.0 Kg/m2, p = 0.038), higher prevalence of hypertension (7.2 vs. 3.4%, p = 0.002), higher terminal sCr (1.2 ± 0.7 vs. 1.0 ± 0.5 mg/dL, p = 0.001), and higher Kidney Donor Profile Index (KDPI) (35.1 ± 23.0 vs. 28.4 ± 19.7%, p = 0.001). Of note, 433 donors (97.7%) presented KDPI ≤ 85%.

Table 1. Recipient demographic and clinical characteristics.

Total N = 443 Without DGF (n = 208) DGF (n = 235) P value
Gender–male 251 (56.7) 121 (58.2) 130 (55.3) 0.545
Age (yo) 44.2 ± 14.7 42.6 ± 15.0 45.6 ± 14.4 0.030
Ethnicity 0.126
  Caucasian / white 35 (7.9) 22 (10.6) 13 (5.5)
  Mixed race / hispanic 374 (84.4) 169 (81.2) 205 (87.2)
  Afro-Brazilian / black 34 (7.7) 17 (8.2) 17 (7.2)
BMI (Kg/m2) 24.3 ± 4.5 23.9 ± 4.3 24.7 ± 4.6 0.054
CKD etiology 0.034
  Unknown 134 (30.2) 63 (30.3) 71 (30.2)
  GN 111 (25.1) 66 (31.7) 45 (19.1)
  Diabetes 73 (16.5) 26 (12.5) 47 (20.0)
  Hypertension 54 (12.2) 24 (11.5) 30 (12.8)
  PKD 31 (7.0) 10 (4.8) 21 (8.9)
  Urological 26 (5.9) 12 (5.8) 14 (6.0)
  Other 14 (3.2) 7 (3.4) 7 (3.0)
History of diabetes 78 (17.6) 28 (13.5) 50 (21.3) 0.034
Time on dialysis (mo) 46.8 ± 45.2 (34) 40.3 ± 40.9 (27) 52.5 ± 48.1 (36) 0.001
Retransplantation 36 (8.1) 15 (7.2) 21 (8.9) 0.602
Class I PRA (%) 9.9 ± 23.4 (0) 9.4 ± 22.6 (0) 10.2 ± 24.0 (0) 0.766
Class II PRA (%) 4.2 ± 14.4 (0) 4.0 ± 14.5 (0) 4.3 ± 14.3 (0) 0.633
HLA MM 3.6 ± 1.2 3.5 ± 1.3 3.6 ± 1.2 0.526
DSA1 27 (6.1) 12 (5.8) 15 (6.4) 0.844

yo; years old; BMI; body mass index; CKD: chronic kidney disease; PKD: polycystic kidney disease; GN: glomerulonephritis; mo: months; PRA: panel reactive antibodies; HLA MM: human leucocyte antigen mismatches; DSA: donor specific anti-HLA antibodies.

1 single-antigen bead assays (LabScreen Single Antigen; One Lambda) on Luminex platform with reactions showing mean intensity fluorescence > 1500.

Table 2. Donor demographic and clinical characteristics.

Total N = 443 Without DGF (n = 208) DGF (n = 235) P value
Age (yo) 31.0 ± 12.7 28.5 ± 12.3 33.2 ± 12.6 < 0.001
BMI (Kg/m2) 25.3 ± 3.8 24.9 ± 4.0 25.7 ± 3.5 0.038
Ethnicity 0.714
  Caucasian / white 51 (11.5) 26 (12.5) 25 (10.6)
  Mixed race / hispanic 377 (85.1) 174 (83.7) 203 (86.4)
  Afro-Brazilian / black 15 (3.4) 8 (3.8) 7 (3.0)
Hypertension 24 (5.4) 7 (3.4) 17 (7.2) 0.002
Diabetes 3 (0.7) 0 (0) 3 (1.3) 0.251
Brain death cause 0.448
  Trauma 314 (70.9) 151 (72.6) 163 (69.4)
  Vascular event 96 (21.7) 40 (19.2) 56 (23.8)
  Anoxia 24 (5.4) 11 (5.3) 13 (5.5)
  Other 9 (2.0) 6 (2.9) 3 (1.3)
HCV 0 (0) 0 (0) 0 (0) NA
Final sCR1 (mg/dL) 1.1 ± 0.6 1.0 ± 0.5 1.2 ± 0.7 0.001
ECD2 19 (4.3) 5 (2.4) 14 (6.0) 0.065
KDPI (%) 31.9 ± 21.8 28.4 ± 19.7 35.1 ± 23.0 0.001
KDRI 0.86 ± 0.2 0.82 ± 0.2 0.89 ± 0.22 0.001

yo: years old; BMI: body mass index; HCV: hepatitis C virus; sCr: serum creatinine; na: not applicable; ECD: expanded criteria donor; KDPI: Kidney Donor Profile Index; KDRI: Kidney Donor Risk Index.

1 last serum creatinine before harvest surgery.

2 United Network for Organ Sharing (UNOS) definition: a) donors >60 yr of age or b) donos 50–59 yr of age with at least two of the following: sCr>1.5 md/dL, history of hypertension or cardiovascular death.

The main perfusion solution was histidine-tryptophan-ketoglutarate (HTK) (83.1%), followed by University of Wisconsin (UW) (13.1%) and Institute Georges Lopez-1 (IGL-1) (3.8%) and this variable did not impact on DGF incidence. There were no differences between groups regarding vascular anastomosis time (36.5 ± 12.3 vs. 35.6 ± 11.1 min, p = 0.440) and anti-thymoglobulin induction therapy (99.1 vs. 96.6%, p = 0.090). However, DGF group presented longer CIT (21.7 ± 3.8 vs. 20.1 ± 4.1h, p<0.001).

Donor maintenance

Donor maintenance parameters data (Table 3) showed the poor clinical and hemodynamic conditions experienced by donors: high need for vasopressors (95.9%), substantial incidence of reversed cardiac arrest episodes (12.2%), high CPK (median 951 UI/L), increased serum Na+ (160.0 ± 13.8 mEq/L) and poor blood glucose control (193.3 ± 77.7 mg/dL). DGF group had lower percentage of donors reaching blood glucose target (26 vs. 37.5%, p = 0.010) and lower urine output in the last 24h prior to recovery surgery (median 0.9 vs. 1.2 mL/Kg/h, p = 0.005).

Table 3. Donor maintenance parameters.

Total N = 443 Without DGF (n = 208) DGF (n = 235) P value
Time to BD (days) 4.3 ± 4.2 (3) 4.3 ± 3.6 (3) 4.2 ± 4.7 (2) 0.219
Reversed cardiac arrest 54 (12.2) 30 (14.4) 24 (10.2) 0.192
Δ sCr (mg/dL) 0.2 ± 0.7 (0) 0.1 ± 0.6 (0) 0.2 ± 0.7 (0.1) 0.135
CPK (IU/L)1 2554 ± 5256 (951) 2161 ± 4876 (880) 2903 ± 5561 (952) 0.470
Arterial blood gas pH 7.33 ± 0.08 7.32 ± 0.08 7.32 ± 0.08 0.210
  Arterial blood gas pH 7.3–7.45 233 (52.6) 114 (54.8) 119 (50.6) 0.392
Serum Na+ (mEq/L) 160.6 ± 13.8 159.6 ± 13.3 161.6 ± 14.2 0.127
  Serum Na+ 135–155 mEq/L 170 (38.4) 82 (39.4) 88 (37.4) 0.696
Blood glucose (mg/dL) 193.3 ± 77.7 189.1 ± 81.0 197.1 ± 74.6 0.282
  Blood glucose ≤150mg/dL 139 (31.4) 78 (37.5) 61 (26.0) 0.010
Urine output (mL/Kg/h) 1.5 ± 1.7 (1.1) 1.7 ± 2.2 (1.2) 1.3 ± 1.0 (0.9) 0.005
  Urine output 0.5–3 mL/Kg/h 363 (81.9) 172 (82.7) 191 (81.3) 0.712
Mean arterial pressure (mmHg) 83.0 ± 14.5 82.1 ± 15.0 83.7 ± 14.0 0.257
  Mean arterial pressure 60–110 mmHg 385 (86.9) 179 (86.1) 206 (87.7) 0.673
Vasopressors 425 (95.9) 202 (97.1) 223 (94.9) 0.335
  ≤ 1 vasopressor and low dose 353 (79.7) 164 (78.8) 189 (80.4) 0.723

time do BD: time since the hospitalization to brain death; Δ sCr: difference between terminal creatinine (immediately prior to recovery surgery) and the initial creatinine (at hospital admission); CPK: creatine phosphokinase; Na+: sodium.

Risk factors for DGF

In logistic regression analysis, variables independently associated with DGF were: recipient history of diabetes (OR 1.922, 95% CI 1.119–3.302, p = 0.018), time on dialysis (OR 1.009, 95% CI 1.004–1.014, p<0.001), donor hypertension (OR 2.331, 95% CI 1.247–4.355, p = 0.008), final sCr (OR 1.947, 95% CI 1.320–2.872, p = 0.001), and CIT (OR 1.115 95% CI 1.058–1.175, p<0.001). However, logistic regression presented poor predictive performance, both in training (AUC 0.686) and testing set (AUC 0.695). To best explore the impact of donor maintenance variables on DGF incidence, logistic regression multivariable analysis was repeated in two subgroups of CIT, based on the median value of the total cohort (21h). The incidences of DGF were 48.2% and 57.8% in CIT<21h and CIT≥21h subgroups, respectively. Of note, in CIT<21h subgroup, in addition to the previously demonstrated variables (time on dialysis, donor hypertension and CIT), urine output (OR 0.639, 95% CI 0.444–0.919, p = 0.016) and serum Na+ (OR 1.030, 95% CI 1.007–1.053, p = 0.010) were also risk factors for DGF (Table 4).

Table 4. Logistic regression analysis of risk factors for DGF, according to CIT groups.

Total N = 443 CIT < 21h N = 220 CIT ≥ 21h N = 223
OR CI 95% P value OR CI 95% P value OR CI 95% P value
Recipient demographics Age (yo) 0.994 0.979–1.010 0.492 NS 1.009 0.988–1.031 0.404
Afro-Brazilian 1.237 0.726–2.109 0.434 NS 1.623 0.753–3.497 0.216
BMI (Kg/m2) 1.020 0.970–1.073 0.433 NS NS
Diabetes 1.922 1.119–3.302 0.018 1.471 0.681–3.178 0.327 1.043 0.977–1.113 0.209
Time on dialysis (mo) 1.009 1.004–1.014 <0.001 1.007 1.001–1.013 0.021 1.012 1.003–1.020 0.008
Retransplantation NS NS NS
Class I PRA (%) NS NS NS
Class II PRA (%) NS NS NS
HLA MM NS NS NS
DSA NS NS NS
Donor demographics Age (yo) 1.016 0.999–1.034 0.066 1.021 0.995–1.048 0.113 1.010 0.983–1.037 0.486
BMI (Kg/m2) 1.041 0.979–1.106 0.204 1.030 0.933–1.137 0.561 NS
Afro-Brazilian NS NS NS
Hypertension 2.331 1.247–4.355 0.008 2.751 1.215–6.232 0.015 2.588 1.112–6.027 0.027
Cerebrovascular death NS NS NS
Final sCr (mg/dL) 1.947 1.320–2.872 0.001 1.714 0.895–3.283 0.104 1.803 1.093–2.972 0.021
Donor maintenance Reversed Cardiac arrest NS NS NS
Urine output (mL/Kg/h) 0.926 0.761–1.126 0.442 0.639 0.444–0.919 0.016 1.054 0.835–1.330 0.660
Serum Na+ (mEq/L) 1.011 0.996–1.026 0.155 1.030 1.007–1.053 0.010 NS
≥ 1 or high dose vasopressor NS NS NS
Blood glucose (mg/dL) NS NS NS
Mean arterial pressure (mmHg) NS NS NS
Arterial blood gas pH NS NS NS
Other Perfusion solution–HTK NS NS NS
CIT (h) 1.115 1.058–1.175 <0.001 1.205 1.052–1.379 0.007 1.179 1.037–1.341 0.012
VAT (min) NS NS NS
rATG induction 3.046 0.536–17.311 0.209 NS NS

DGF: delayed graft function; CIT: cold ischemia time; yo: years old; BMI: body mass index, PRA: panel reactive antibodies; HLA MM: human leucocyte antigen mismatches; D.S.A: donor specific antibodies; sCr: final serum creatinine; Na+: sodium; VAT: vascular anastomosis time; rATG: rabbit anti-thymocyte globulin.

NS: Variables not included in multivariable model since p value >0.15 in univariable analysis.

The results of Elastic Net regression are illustrated in Fig 1. Variables in red were risk factors for DGF and variables in blue were associated with reduced risk of DGF. This model presented better predictive performance when compared to logistic regression (AUC 0.749).

Fig 1. Elastic net regression.

Fig 1

Variable in red (coefficient > zero) are risk factors for DGF and variables in blue (coefficient < zero) are protective. Variables are disposed by importance. DGF: delayed graft function; CIT: cold ischemia time; yo: years old; BMI: body mass index, PRA: panel reactive antibodies; HLA MM: human leucocyte antigen mismatches; sCr: final serum creatinine; Na+: sodium; VAT: vascular anastomosis time.

The three statistical methods of better performance in analyzes using ML techniques were: boosted DT using C5.0 algorithm (AUC 0.791), boosting NN (AUC 0.886), and SVM with polynomial kernel (AUC 0.784). Fig 2 illustrates ML results and predictive performance. Variable are presented using the feature importance graph, in which higher the value of the feature/variable, more important it was to predict DGF. The feature importance was normalized between 0 and 1 by dividing by the sum of all feature importance values. As demonstrated in Fig 2, urine output, mean arterial pressure, and the use of more than one vasoactive drug or high dose vasopressor were predictive of DGF in all models. Blood glucose was predictive of DGF in DT and SVM models.

Fig 2. Figs on the left demonstrate the area under the receiver-operating curve (AUC) for each method in the testing set.

Fig 2

Figs on the right show global variable importance for prediction of delayed graft function. (A) Decision Tree; (B) Support Vector Machine; (C) Neural Network. BMI: body mass index; sCr: final serum creatinine; CIT: cold ischemia time.

Discussion

This study suggest that poor donor clinical and hemodynamic status may impact on DGF occurrence, and this might explain the high incidence of DGF in Brazil, where the incidence is significantly higher than that the predicted by available formulas.

In our cohort, DGF incidence was almost 3-fold higher than the predicted by the nomogram described by Irish et al, suggesting an important role of variables not included in the prediction model. In fact, none of the available predictive models includes in final formula variables reflecting donor maintenance. Except for terminal serum creatinine (that could reflect renal consequences of hypovolemia, shock and other causes of acute kidney injury), only the score developed by Chapal et al analyzed some variable related to donor care (type of vasopressor) [24].

Only 4.3% of patients received kidneys from expanded criteria donors and 97.7% had KDPI below 85%, suggesting good structural quality kidneys. On the other hand, 12.2% had a reversed cardiac arrest episode before organ recovery surgery, 47.4% presented acid-base disorders, 61.6% had hypo- or hypernatremia, and 68.6% showed inadequate glycemic control, reflecting poor clinical and hemodynamic conditions. The impact of poor donor maintenance in our country has previously suggested in a study including simultaneous pancreas-kidney transplants. In this cohort, despite favorable demographics, the incidence of delayed kidney graft function was 22.7% and donor hypernatremia was an independent risk factor for DGF [7].

The challenge of properly maintaining potential deceased donors seems not to be exclusive of our population. Previous American and Canadian studies have reported low adherence to donor-care bundles at the time of consent for donation. Importantly, the early achievement of donor management goals was associated with a reduced risk of DGF in these studies [11, 12].

The high CIT was notable and its contribution to DGF is unequivocal. All statistical analysis demonstrated that each additional hour matters, even in KT with CIT < 21h. The large territorial extension, the allocation model predominantly based on HLA compatibility, and the absence of specific allocation policies for “marginal” donors contribute to the long CIT in our country [25]. However, it is noteworthy that almost half of KT with CIT <21h presented DGF, suggesting the contribution of other factors beyond the CIT.

Due to the high negative impact of CIT on DGF incidence, potentially masking other predictors, we performed a post-hoc analysis including a regression model on a sub-sample of patients with CIT inferior to 21h. As hypothesized, variables reflecting donor maintenance now emerged. Additionally, in ML analysis, donor maintenance related variables, such as blood pressure, use of high dose vasopressors, urine output and blood glucose, were also associated with DGF. To further explore the contribution of other than the traditional variables to DGF incidence using a more interpretable model, we performed a sensitivity analysis using elastic net regression. Again, beyond the traditional conditions associated to DGF occurrence, variables reflecting donor management were risk factors (serum Na+, blood glucose) or protective (high dose vasopressors and diuresis).

Recently published studies demonstrated the impact of donor hemodynamics as a predictor of DGF in transplantation from donors after cardiac death [26, 27]. However, evidences are scarce on transplantation of brain dead donors.

Our study has limitations that should be pointed out. First, it was a retrospective cohort; therefore, the capture of variables was limited to those available on medical records. We cannot assure that our results are generalizable to other transplant centers worldwide. Donor maintenance related variables (and DMGs) are not static and we could not evaluate them dynamically. Since we could not follow variables over time and assess adherence to care bundles, it is possible that some clinical and hemodynamic data reflected the severity of the disease that led to brain death and not the patient care. Besides, it’s possible that some clinical and hemodynamic parameters reflected patient situation before they became a consented donor, and thus may not reflect donor maintenance, but general intensive care. Finally, variables reflecting perioperative care were not available.

In conclusion, DGF incidence in Brazil is significantly higher than that predicted by available models. Although our data do not allow us to draw definitive conclusions, this study suggests that donor illness severity and hemodynamic instability might contribute to this scenario. Prospective studies are needed to robustly conclude how donor management impacts on DGF incidence. Additionally, a cohort including machine-perfused grafts may be useful to explore if pumping might mitigate kidney damage secondary to poor donor clinical and hemodynamic status.

We believe bringing this issue up is crucial in our setting. Scant donor care is probably a reflection of the poor economic conditions of our country. However, some educational actions could be taken, focusing on early recognition of potential donors and training staff who care for brain death patients.

Supporting information

S1 Database

(XLSX)

Abbreviations

AUC

Area under the receiver operating curve

BMI

Body Mass Index

CIT

Cold ischemia time

CPK

Creatine phosphokinase

DGF

Delayed graft function

DMG

Donor maintenance goals

DMR

Donor maintenance-related

DT

Decision tree

HLA

Human leucocyte antigen

HRSA

Health Resources and Services Administration

HTK

Histidine-tryptophan-ketoglutarate

IGL-1

Institut Georges Lopez-1

IRB

Institutional Review Board

KDPI

Kidney Donor Profile Index

KNN

K-nearest neighbors

KT

Kidney transplant

ML

Machine learning

MM

Mismatches

Na+

Sodium

NN

Neural Network

OPTN

Organ Procurement and Transplant Network

OR

Odds-ratio

PRA

Panel reactive antibodies

SCr

Serum creatinine

SVM

Support Vector Machine

UNOS

United Network for Organ Sharing

UW

University of Wiscosin

Data Availability

Data supporting the findings of this study are available as supplementary file

Funding Statement

SDC received support for travel expenses from Fundação Cearense de Apoio ao Desenvolvimento Científico e Tecnológico (Funcap) and Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Other authors received no specific funding for this work.

References

  • 1.Irish WD, Ilsley JN, Schnitzler MA, Feng S, Brennan DC. A risk prediction model for delayed graft function in the current era of deceased donor renal transplantation. Am J Transplant. 2010;10(10):2279–86. 10.1111/j.1600-6143.2010.03179.x . [DOI] [PubMed] [Google Scholar]
  • 2.Fonseca I, Teixeira L, Malheiro J, Martins LS, Dias L, Castro Henriques A, et al. The effect of delayed graft function on graft and patient survival in kidney transplantation: an approach using competing events analysis. Transpl Int. 2015;28(6):738–50. 10.1111/tri.12543 . [DOI] [PubMed] [Google Scholar]
  • 3.Gavela Martinez E, Pallardo Mateu LM, Sancho Calabuig A, Beltran Catalan S, Kanter Berga J, Avila Bernabeu AI, et al. Delayed graft function after renal transplantation: an unresolved problem. Transplant Proc. 2011;43(6):2171–3. 10.1016/j.transproceed.2011.06.051 . [DOI] [PubMed] [Google Scholar]
  • 4.de Sandes-Freitas TV, Felipe CR, Aguiar WF, Cristelli MP, Tedesco-Silva H, Medina-Pestana JO. Prolonged Delayed Graft Function Is Associated with Inferior Patient and Kidney Allograft Survivals. PLoS One. 2015;10(12):e0144188 10.1371/journal.pone.0144188 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 5.Azevedo LS, Castro MC, Monteiro de Carvalho DB, d'Avila DO, Contieri F, Gonçalves RT, et al. Incidence of delayed graft function in cadaveric kidney transplants in Brazil: a multicenter analysis. Transplant Proc. 2005;37(6):2746–7. 10.1016/j.transproceed.2005.05.005 . [DOI] [PubMed] [Google Scholar]
  • 6.Helfer MS, Vicari AR, Spuldaro F, Gonçalves LF, Manfro RC. Incidence, risk factors, and outcomes of delayed graft function in deceased donor kidney transplantation in a Brazilian center. Transplant Proc. 2014;46(6):1727–9. 10.1016/j.transproceed.2014.05.026 . [DOI] [PubMed] [Google Scholar]
  • 7.Rangel EB, Melaragno CS, Gonzalez AM, Linhares MM, de Sá JR, Salzedas A, et al. Delayed kidney allograft function after simultaneous pancreas-kidney transplantation. Transplant Proc. 2010;42(9):3655–9. doi: S0041-1345(10)01308-4 [pii] 10.1016/j.transproceed.2010.06.030 . [DOI] [PubMed] [Google Scholar]
  • 8.Gutierrez P, Marrero D, Hernandez D, Vivancos S, Perez-Tamajon L, Rodriguez de Vera JM, et al. Surgical complications and renal function after kidney alone or simultaneous pancreas-kidney transplantation: a matched comparative study. Nephrol Dial Transplant. 2007;22(5):1451–5. 10.1093/ndt/gfl771 . [DOI] [PubMed] [Google Scholar]
  • 9.Bunnapradist S, Cho YW, Cecka JM, Wilkinson A, Danovitch GM. Kidney allograft and patient survival in type I diabetic recipients of cadaveric kidney alone versus simultaneous pancreas kidney transplants: a multivariate analysis of the UNOS database. J Am Soc Nephrol. 2003;14(1):208–13. 10.1097/01.asn.0000037678.54984.41 . [DOI] [PubMed] [Google Scholar]
  • 10.Butala NM, Reese PP, Doshi MD, Parikh CR. Is Delayed Graft Function Causally Associated With Long-Term Outcomes After Kidney Transplantation? Instrumental Variable Analysis. Transplantation. 2013;95(8):1008–14. 10.1097/TP.0b013e3182855544 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 11.Malinoski DJ, Patel MS, Ahmed O, Daly MC, Mooney S, Graybill CO, et al. The impact of meeting donor management goals on the development of delayed graft function in kidney transplant recipients. Am J Transplant. 2013;13(4):993–1000. 10.1111/ajt.12090 . [DOI] [PubMed] [Google Scholar]
  • 12.Cardinal H, Lamarche F, Grondin S, Marsolais P, Lagace AM, Duca A, et al. Organ donor management and delayed graft function in kidney transplant recipients: A multicenter retrospective cohort study. Am J Transplant. 2019;19(1):277–84. 10.1111/ajt.15127 . [DOI] [PubMed] [Google Scholar]
  • 13.Hannun PGC, Andrade LGM. The future is coming: promising perspectives regarding the use of machine learning in renal transplantation. J Bras Nefrol. 2018. 10.1590/2175-8239-jbn-2018-0047 . [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 14.Goldstein BA, Navar AM, Carter RE. Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges. Eur Heart J. 2017;38(23):1805–14. 10.1093/eurheartj/ehw302 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 15.Yoo KD, Noh J, Lee H, Kim DK, Lim CS, Kim YH, et al. A Machine Learning Approach Using Survival Statistics to Predict Graft Survival in Kidney Transplant Recipients: A Multicenter Cohort Study. Sci Rep. 2017;7(1):8904 10.1038/s41598-017-08008-8 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 16.Decruyenaere A, Decruyenaere P, Peeters P, Vermassen F, Dhaene T, Couckuyt I. Prediction of delayed graft function after kidney transplantation: comparison between logistic regression and machine learning methods. BMC Med Inform Decis Mak. 2015;15:83 10.1186/s12911-015-0206-y [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 17.Zou HH, Trevor. Regularization and variable selection via the elastic net. J R Statist Soc B. 2005;part 2(67):301–20. 10.1111/j.1467-9868.2005.00527.x [DOI] [Google Scholar]
  • 18.Silva SF, Silva SL, Nascimento AC, Parente MM, Albuquerque CA, Rodrigues AA, et al. Profile of organ donors in Ceara, northeastern Brazil, from 1998 to 2012. Transplant Proc. 2014;46(6):1692–4. 10.1016/j.transproceed.2014.05.008 . [DOI] [PubMed] [Google Scholar]
  • 19.Mallon DH, Summers DM, Bradley JA, Pettigrew GJ. Defining delayed graft function after renal transplantation: simplest is best. Transplantation. 2013;96(10):885–9. 10.1097/TP.0b013e3182a19348 . [DOI] [PubMed] [Google Scholar]
  • 20.Rodrigo E, Minambres E, Ruiz JC, Ballesteros A, Pinera C, Quintanar J, et al. Prediction of delayed graft function by means of a novel web-based calculator: a single-center experience. Am J Transplant. 2012;12(1):240–4. 10.1111/j.1600-6143.2011.03810.x . [DOI] [PubMed] [Google Scholar]
  • 21.Kers J, Peters-Sengers H, Heemskerk MBA, Berger SP, Betjes MGH, van Zuilen AD, et al. Predicition models for delayed graft function: external validation on The Dutch Prospective Renal Transplantation Registry. Nephrol Dial Transplant. 2018;33(7):1259–68. 10.1093/ndt/gfy019 . [DOI] [PubMed] [Google Scholar]
  • 22.Franklin GA, Santos AP, Smith JW, Galbraith S, Harbrecht BG, Garrison RN. Optimization of donor management goals yields increased organ use. Am Surg. 2010;76(6):587–94. . [DOI] [PubMed] [Google Scholar]
  • 23.Friedman J, Hastie T, Tibshirani R. Regularization Paths for Generalized Linear Models via Coordinate Descent. J Stat Softw. 2010;33(1):1–22. [PMC free article] [PubMed] [Google Scholar]
  • 24.Chapal M, Le Borgne F, Legendre C, Kreis H, Mourad G, Garrigue V, et al. A useful scoring system for the prediction and management of delayed graft function following kidney transplantation from cadaveric donors. Kidney Int. 2014;86(6):1130–9. 10.1038/ki.2014.188 . [DOI] [PubMed] [Google Scholar]
  • 25.Sandes-Freitas TV. The scenario of delayed graft function in Brazil. J Bras Nefrol. 2019. 10.1590/2175-8239-JBN-2018-0221 . [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 26.Allen MB, Billig E, Reese PP, Shults J, Hasz R, West S, et al. Donor Hemodynamics as a Predictor of Outcomes After Kidney Transplantation From Donors After Cardiac Death. Am J Transplant. 2016;16(1):181–93. 10.1111/ajt.13432 . [DOI] [PubMed] [Google Scholar]
  • 27.Sun Q, Huang Z, Zhou H, Lin M, Hua X, Hong L, et al. New Factors Predicting Delayed Graft Function: a Multi-Center Cohort Study of Kidney Donation After Brain Death Followed by Circulatory Death. Kidney Blood Press Res. 2018;43(3):893–903. 10.1159/000490337 . [DOI] [PubMed] [Google Scholar]

Decision Letter 0

Frank JMF Dor

7 Nov 2019

PONE-D-19-26074

The impact of deceased donor maintenance on delayed kidney allograft function: a machine learning analysis

PLOS ONE

Dear MD, PhS Sandes-Freitas,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

==============================

ACADEMIC EDITOR:

Interesting MS on donor management and the impact on DGF in kidney transplantation. However, quite a few issues were raised by the reviewers on the design of the study and specific results/outcomes, overstated conclusions, etc, that would need to be dealt with in great detail in order for this paper to be publishable. Please be advised that re-submission does not guarantee acceptance.

==============================

We would appreciate receiving your revised manuscript by Dec 22 2019 11:59PM. When you are ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter.

To enhance the reproducibility of your results, we recommend that if applicable you deposit your laboratory protocols in protocols.io, where a protocol can be assigned its own identifier (DOI) such that it can be cited independently in the future. For instructions see: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols

Please include the following items when submitting your revised manuscript:

  • A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). This letter should be uploaded as separate file and labeled 'Response to Reviewers'.

  • A marked-up copy of your manuscript that highlights changes made to the original version. This file should be uploaded as separate file and labeled 'Revised Manuscript with Track Changes'.

  • An unmarked version of your revised paper without tracked changes. This file should be uploaded as separate file and labeled 'Manuscript'.

Please note while forming your response, if your article is accepted, you may have the opportunity to make the peer review history publicly available. The record will include editor decision letters (with reviews) and your responses to reviewer comments. If eligible, we will contact you to opt in or out.

We look forward to receiving your revised manuscript.

Kind regards,

Frank JMF Dor, M.D., Ph.D., FEBS, FRCS

Academic Editor

PLOS ONE

Journal Requirements:

1. When submitting your revision, we need you to address these additional requirements. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at http://www.journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and http://www.journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. We note that you have indicated that data from this study are available upon request. PLOS only allows data to be available upon request if there are legal or ethical restrictions on sharing data publicly. For information on unacceptable data access restrictions, please see http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions.

In your revised cover letter, please address the following prompts:

a) If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially identifying or sensitive patient information) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent.

b) If there are no restrictions, please upload the minimal anonymized data set necessary to replicate your study findings as either Supporting Information files or to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. Please see http://www.bmj.com/content/340/bmj.c181.long for guidelines on how to de-identify and prepare clinical data for publication. For a list of acceptable repositories, please see http://journals.plos.org/plosone/s/data-availability#loc-recommended-repositories.

We will update your Data Availability statement on your behalf to reflect the information you provide.

3. In ethics statement in the manuscript and in the online submission form, please provide additional information about the patient records used in your retrospective study. Specifically, please ensure that you have discussed whether all data were fully anonymized before you accessed them and/or whether the IRB or ethics committee waived the requirement for informed consent. If patients provided informed written consent to have data from their medical records used in research, please include this information.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Partly

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: I Don't Know

Reviewer #2: I Don't Know

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: Costa et al have used machine learning to assess the effects of donor management on DGF and compared that to predictive figures from a multivariate algorithm. The study is clearly written and has a fair sample size. The approach using ML is new and inventive. The evaluation of the exact mathematical analysis is not my expertise.

I have some reservations though on the design of the study.

1. The focus of the study is a bit unclear to me. Since the title and introduction are on machine learning, I dont know why first a predicitive model is used to show the higher than expected incidence of DGF. Even if DGF is in the expected incidence a correlation with donor factors could be found.

2. Data are very specific to countries or situations in which the DGF rate is this exceptionally high (for DBD). The mean KIT is very high and I dont think any European center will accept a KIT >21h for 50% of the transplants.The high DGF rate is cause by the long KIT untill proven otherwise, and not by donor management.

3. Therefore I would like to question how sure you are that you are actually relating to donor management issues, since these donors are brain dead and dying. Are the factors analyzed, e.g. the need for inotropics or urine output, a measure for the quality of donor mamangement or simply a refelection of the severity of the illness of the donor or the phase in the brain dead process the donor is in?

Reviewer #2: General Comments

• The rise of donation after circulatory death – where delayed graft function (DGF) in kidney transplants is common yet long term results are not inferior to donation after brain death, the end point of DGF is now considered much less important. That said, if donor maintenance can prevent DGF then that should of course be explored.

• I am unsure why DGF is so high in Brazil. You suggest because of poor donor management? Is there evidence of this?

• I am not sure your study does show, as you suggest it does, that poor donor maintenance impacts on DGF. You have shown that donors with certain physiological parameters are associated with DGF. But you have not shown that the cause of the poor physiological parameters is a result of poor donor maintenance. They just may be a sicker cohort. One with more hypoxic injury – as evidenced by being more likely to have had a cardiac arrest – probably from out of hospital cardiac arrest. So, I don’t accept your conclusion. To prove your conclusion, you would have to examine adherence to a donor care bundle, or match cohorts between hospitals that manage donors differently.

• Expanding this point, I would consider the following donor parameters may just reflect a sicker patient cohort: donor age, BMI, final sCr, cerebrovascular death, urine output, MAP, > 1 or high dose inotrope. Perhaps only blood glucose might be something the intensivist may have been able to control better.

• You describe in your methods ‘donor maintenance parameters’ but the results for which can be taken from anytime ‘during hospitalization’. So the worst result may be before the patient became a consented donor and thus may not reflect donor maintenance, but general intensive care.

• A shame the machine perfused kidney transplant cohort were not included. That would be interesting to see if machine perfusion can mitigate against poor donor maintenance.

• I was unclear what you hope can be done with your machine learning Figure 1? Is it useful because it describes the problem? Could it become a prediction tool – helping a transplant surgeon decide if a kidney needed machine perfusion?

Specific and Minor Comments

• You should say in your introduction (and ideally abstract) all were donors after brain death.

• ‘Due to the observational and retrospective nature of the study, with data anonymously analyzed, [the] informed consent was not obtained.’ No need for [the].

• Donor Maintenance. ‘poor hemodynamic conditions to which donors were submitted:’. This reads like someone submitted the donor to these problems, whereas they just may reflect the way things are and not negatively on donor maintenance. Example – reversed cardiac arrest. Was that cardiac arrest reversed in ICU. Or cardiac arrest reversed in the community leading to hypoxic brain injury and brain death. The first could represent poor donor maintenance. The second is juts the ways things are.

• Should be ‘The challenge of properly maintaining potential deceased donors seems not to be exclusive of our population.’

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files to be viewed.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email us at figures@plos.org. Please note that Supporting Information files do not need this step.

PLoS One. 2020 Feb 6;15(2):e0228597. doi: 10.1371/journal.pone.0228597.r002

Author response to Decision Letter 0


9 Nov 2019

Dear Editor,

We are resubmitting our manuscript entitled “The impact of deceased donor maintenance on delayed kidney allograft function: a machine learning analysis" addressing all the issues raised by the reviewers (Rebuttal Letter attached). We appreciate all the comments, which contributed to the improvement of our manuscript, and thank you for the opportunity to resubmit this revised version.

Yours sincerely,

Tainá de Sandes-Freitas

Attachment

Submitted filename: Response to Reviewers.docx

Decision Letter 1

Frank JMF Dor

2 Dec 2019

PONE-D-19-26074R1

The impact of deceased donor maintenance on delayed kidney allograft function: a machine learning analysis

PLOS ONE

Dear MD, PhS Sandes-Freitas,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

==============================

ACADEMIC EDITOR:

It would be very important that authors address the comments of reviewer 1 (and reviewer 2) in more detail, as there seems to be interest in the topic and the MS. However, reviewer 1 remains very critical about the explantations given so far. Also, the conclusions should probably be downsized significantly and limitations more clearly recognised by authors.

==============================

We would appreciate receiving your revised manuscript by Jan 16 2020 11:59PM. When you are ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter.

To enhance the reproducibility of your results, we recommend that if applicable you deposit your laboratory protocols in protocols.io, where a protocol can be assigned its own identifier (DOI) such that it can be cited independently in the future. For instructions see: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols

Please include the following items when submitting your revised manuscript:

  • A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). This letter should be uploaded as separate file and labeled 'Response to Reviewers'.

  • A marked-up copy of your manuscript that highlights changes made to the original version. This file should be uploaded as separate file and labeled 'Revised Manuscript with Track Changes'.

  • An unmarked version of your revised paper without tracked changes. This file should be uploaded as separate file and labeled 'Manuscript'.

Please note while forming your response, if your article is accepted, you may have the opportunity to make the peer review history publicly available. The record will include editor decision letters (with reviews) and your responses to reviewer comments. If eligible, we will contact you to opt in or out.

We look forward to receiving your revised manuscript.

Kind regards,

Frank JMF Dor, M.D., Ph.D., FEBS, FRCS

Academic Editor

PLOS ONE

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #1: (No Response)

Reviewer #2: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Partly

Reviewer #2: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: I Don't Know

Reviewer #2: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: I thank the author for the comments and explanations. They added explainig phrases to the manuscript. Unfortunately, the explanations the authors have given are not providing new insights. Moreover, it appears that the conclusions of the article are preliminary. For example, the contribution of KIT was not clarified, except for the statement that <21h was still 50% DGF. The contribution of donor ilness severity was only speculated on. No data were added to test the hypothesis that donor managment or treatment was indeed in a causative relation to DGF.

I think the manuscript has too many uncertainties and speculations to make it acceptable in this form.

Reviewer #2: General Comments

Very much improved paper.

Congratulations.

Specific and Minor Comments

In Statistical analysis, better: ‘Diabetic donors were also excluded, since this was a near-zero variance predictor (all patients who received grafts from diabetic donors developed DGF).’

In Results, better: ‘The mean time of DGF was 11.8 ± 15.0 days’

Conclusion perhaps could be: ‘Additionally, a cohort including machine-perfused grafts may be useful to explore if pumping might mitigate kidney damage secondary to poor clinical and hemodynamic status.’

This is probably enough given you didn’t prove causation to donor management even if suggestive.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files to be viewed.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email us at figures@plos.org. Please note that Supporting Information files do not need this step.

PLoS One. 2020 Feb 6;15(2):e0228597. doi: 10.1371/journal.pone.0228597.r004

Author response to Decision Letter 1


16 Jan 2020

Dear Academic Editor,

We are resubmitting our manuscript entitled “The impact of deceased donor maintenance on delayed kidney allograft function: a machine learning analysis" addressing all the issues raised by the reviewers (attached).

We appreciate all the comments, which contributed to the improvement of our manuscript, and thank you for the opportunity to resubmit this revised version.

Yours sincerely,

Tainá Veras de Sandes-Freitas

Attachment

Submitted filename: Response to Reviewers.docx

Decision Letter 2

Frank JMF Dor

21 Jan 2020

The impact of deceased donor maintenance on delayed kidney allograft function: a machine learning analysis

PONE-D-19-26074R2

Dear Dr. Sandes-Freitas,

We are pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it complies with all outstanding technical requirements.

Within one week, you will receive an e-mail containing information on the amendments required prior to publication. When all required modifications have been addressed, you will receive a formal acceptance letter and your manuscript will proceed to our production department and be scheduled for publication.

Shortly after the formal acceptance letter is sent, an invoice for payment will follow. To ensure an efficient production and billing process, please log into Editorial Manager at https://www.editorialmanager.com/pone/, click the "Update My Information" link at the top of the page, and update your user information. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to enable them to help maximize its impact. If they will be preparing press materials for this manuscript, you must inform our press team as soon as possible and no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

With kind regards,

Frank JMF Dor, M.D., Ph.D., FEBS, FRCS

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

The authors have now addressed all remaining issues raised by the reviewers. Happy to accept the 2nd revision.

Reviewers' comments:

Acceptance letter

Frank JMF Dor

23 Jan 2020

PONE-D-19-26074R2

The impact of deceased donor maintenance on delayed kidney allograft function: a machine learning analysis

Dear Dr. Sandes-Freitas:

I am pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department.

If your institution or institutions have a press office, please notify them about your upcoming paper at this point, to enable them to help maximize its impact. If they will be preparing press materials for this manuscript, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information please contact onepress@plos.org.

For any other questions or concerns, please email plosone@plos.org.

Thank you for submitting your work to PLOS ONE.

With kind regards,

PLOS ONE Editorial Office Staff

on behalf of

Dr. Frank JMF Dor

Academic Editor

PLOS ONE

Associated Data

    This section collects any data citations, data availability statements, or supplementary materials included in this article.

    Supplementary Materials

    S1 Database

    (XLSX)

    Attachment

    Submitted filename: Response to Reviewers.docx

    Attachment

    Submitted filename: Response to Reviewers.docx

    Data Availability Statement

    Data supporting the findings of this study are available as supplementary file


    Articles from PLoS ONE are provided here courtesy of PLOS

    RESOURCES