Background: This study aimed to better characterize morbidly obese kidney transplant recipients, their clinical characteristics, and outcomes by using an unsupervised machine learning approach. Methods: Consensus cluster analysis was applied to OPTN/UNOS data from 2010 to 2019 based on recipient, donor, and transplant characteristics in kidney transplant recipients with a pre-transplant BMI ≥ 40 kg/m2. Key cluster characteristics were identified using the standardized mean difference. Post-transplant outcomes, including death-censored graft failure, patient death, and acute allograft rejection, were compared among the clusters. Results: Consensus clustering analysis identified 3204 kidney transplant recipients with a BMI ≥ 40 kg/m2. In this cohort, five clinically distinct clusters were identified. Cluster 1 recipients were predominantly white and non-sensitized, had a short dialysis time or were preemptive, and were more likely to receive living donor kidney transplants. Cluster 2 recipients were older and diabetic. They were likely to have been on dialysis >3 years and receive a standard KDPI deceased donor kidney. Cluster 3 recipients were young, black, and had kidney disease secondary to hypertension or glomerular disease. Cluster 3 recipients had >3 years of dialysis and received non-ECD, young, deceased donor kidney transplants with a KDPI < 85%. Cluster 4 recipients were diabetic with variable dialysis duration who either received non-ECD standard KDPI kidneys or living donor kidney transplants. Cluster 5 recipients were young retransplants that were sensitized. One-year patient survival in clusters 1, 2, 3, 4, and 5 was 98.0%, 94.4%, 98.5%, 98.7%, and 97%, and one-year death-censored graft survival was 98.1%, 93.0%, 96.1%, 98.8%, and 93.0%, respectively. Cluster 2 had the worst one-year patient survival. Clusters 2 and 5 had the worst one-year death-censored graft survival. Conclusions: With the application of unsupervised machine learning, variable post-transplant outcomes are observed among morbidly obese kidney transplant recipients. Recipients with earlier access to transplant and living donation show superior outcomes. Unexpectedly, reduced graft survival in cluster 3 recipients perhaps underscores socioeconomic access to post-transplant support and minorities being disadvantaged in access to preemptive and living donor transplants. Despite obesity-related concerns, one-year patient and graft survival were favorable in all clusters, and obesity itself should be reconsidered as a hard barrier to kidney transplantation.

Chronic kidney disease (CKD) poses a significant public health challenge, affecting approximately 11% to 13% of the global population [...]

Purpose This study aimed to assess efficacy of extracorporeal plasma therapy (EPT), including plasmapheresis (PE), immunoadsorption (IA), low-density lipoprotein apheresis (LDL-A), and lymphocytapheresis (LCAP) for adult native kidney patients with primary focal segmental glomerulosclerosis (FSGS). Methods A literature search was conducted using MEDLINE, EMBASE and Cochrane Databases through August 2022. Studies that reported outcomes of EPT in adult native kidneys with primary FSGS were enrolled. Results 18 studies with 104 therapy-resistant or refractory primary native FSGS patients were identified. Overall EPT response rate was 56%, with long-term benefit of 46%. Of the 101 non-hemodialysis (HD) patients, 54% achieved remission, with 30% complete remission (CR) and 23% partial remission (PR). Of 31 patients with PE, response rate was 65%; CR and PR rates were 27% and 37% in 30 non-HD patients. Of 61 patients with LDL-A, the response rate was 54%; CR and PR rates were 41% and 3% in 29 non-HD patients. Of 10 patients with IA, response rate was 40%. Of 2 patients with LCAP, 1 achieved CR, and one developed renal failure. All 3 HD patients showed increase in urine output and gradual decrease in urine protein excretion following PE ( n = 1) or LDL-A ( n = 2). 2 of 3 HD patients ultimately discontinued dialysis. Conclusion EPT with immunosuppressive therapy showed benefit in some patients with refractory primary FSGS, and PE appeared to have a higher response rate.

Background: We aimed to develop and validate an automated machine learning (autoML) prediction model for cardiac surgery-associated acute kidney injury (CSA-AKI). Methods: Using 69 preoperative variables, we developed several models to predict post-operative AKI in adult patients undergoing cardiac surgery. Models included autoML and non-autoML types, including decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), and artificial neural network (ANN), as well as a logistic regression prediction model. We then compared model performance using area under the receiver operating characteristic curve (AUROC) and assessed model calibration using Brier score on the independent testing dataset. Results: The incidence of CSA-AKI was 36%. Stacked ensemble autoML had the highest predictive performance among autoML models, and was chosen for comparison with other non-autoML and multivariable logistic regression models. The autoML had the highest AUROC (0.79), followed by RF (0.78), XGBoost (0.77), multivariable logistic regression (0.77), ANN (0.75), and DT (0.64). The autoML had comparable AUROC with RF and outperformed the other models. The autoML was well-calibrated. The Brier score for autoML, RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.18, 0.18, 0.21, 0.19, 0.19, and 0.18, respectively. We applied SHAP and LIME algorithms to our autoML prediction model to extract an explanation of the variables that drive patient-specific predictions of CSA-AKI. Conclusion: We were able to present a preoperative autoML prediction model for CSA-AKI that provided high predictive performance that was comparable to RF and superior to other ML and multivariable logistic regression models. The novel approaches of the proposed explainable preoperative autoML prediction model for CSA-AKI may guide clinicians in advancing individualized medicine plans for patients under cardiac surgery.

Background: The utilization of multi-dimensional patient data to subtype hepatorenal syndrome (HRS) can individualize patient care. Machine learning (ML) consensus clustering may identify HRS subgroups with unique clinical profiles. In this study, we aim to identify clinically meaningful clusters of hospitalized patients for HRS using an unsupervised ML clustering approach. Methods: Consensus clustering analysis was performed based on patient characteristics in 5564 patients primarily admitted for HRS in the National Inpatient Sample from 2003–2014 to identify clinically distinct HRS subgroups. We applied standardized mean difference to evaluate key subgroup features, and compared in-hospital mortality between assigned clusters. Results: The algorithm revealed four best distinct HRS subgroups based on patient characteristics. Cluster 1 patients (n = 1617) were older, and more likely to have non-alcoholic fatty liver disease, cardiovascular comorbidities, hypertension, and diabetes. Cluster 2 patients (n = 1577) were younger and more likely to have hepatitis C, and less likely to have acute liver failure. Cluster 3 patients (n = 642) were younger, and more likely to have non-elective admission, acetaminophen overdose, acute liver failure, to develop in-hospital medical complications and organ system failure, and to require supporting therapies, including renal replacement therapy, and mechanical ventilation. Cluster 4 patients (n = 1728) were younger, and more likely to have alcoholic cirrhosis and to smoke. Thirty-three percent of patients died in hospital. In-hospital mortality was higher in cluster 1 (OR 1.53; 95% CI 1.31–1.79) and cluster 3 (OR 7.03; 95% CI 5.73–8.62), compared to cluster 2, while cluster 4 had comparable in-hospital mortality (OR 1.13; 95% CI 0.97–1.32). Conclusions: Consensus clustering analysis provides the pattern of clinical characteristics and clinically distinct HRS phenotypes with different outcomes.

Antifibrotic treatment has been approved for reducing disease progression in fibrotic interstitial lung disease (ILD). As a result of increased bleeding risk, some experts suggest cessation of antifibrotics prior to lung transplantation (LT). However, extensive knowledge regarding the impact of antifibrotic treatment on postoperative complications remains unclear. We performed a comprehensive search of several databases from their inception through to 30 September 2021. Original studies were included in the final analysis if they compared postoperative complications, including surgical wound dehiscence, anastomosis complication, bleeding complications, and primary graft dysfunction, between those with and without antifibrotic treatment undergoing LT. Of 563 retrieved studies, 6 studies were included in the final analysis. A total of 543 ILD patients completing LT were included, with 161 patients continuing antifibrotic treatment up to the time of LT and 382 without prior treatment. Antifibrotic treatment was not significantly associated with surgical wound dehiscence (RR 1.05; 95% CI, 0.31–3.60; I2 = 0%), anastomotic complications (RR 0.88; 95% CI, 0.37–2.12; I2 = 31%), bleeding complications (RR 0.76; 95% CI, 0.33–1.76; I2 = 0%), or primary graft dysfunction (RR 0.87; 95% CI, 0.59–1.29; I2 = 0%). Finally, continuing antifibrotic treatment prior to LT was not significantly associated with decreased 1-year mortality (RR 0.80; 95% CI, 0.41–1.58; I2 = 0%). Our study suggests a similar risk of postoperative complications in ILD patients undergoing LT who received antifibrotic treatment compared to those not on antifibrotic therapy.

No abstract

Background: The Mediterranean, Dietary Approach to Stop Hypertension (DASH), and plant-based diets may provide cardiovascular benefit to the general population. However, data on their effect on end stage kidney disease (ESKD) patients are limited. This systematic review aims to assess the impact of Mediterranean, DASH, and plant-based diets on outcomes among ESKD patients. Methods: A literature review was conducted in EMBASE, MEDLINE, and Cochrane databases from inception through September 2022 to identify studies that assess the clinical outcomes of Mediterranean, DASH, or plant-based diets on ESKD patients on hemodialysis (HD) or peritoneal dialysis (PD). Effect estimates from the individual studies were derived utilizing the random-effect, generic inverse variance approach of DerSimonian and Laird. Results: Seven studies with 9400 ESKD patients (8395 HD and 1005 PD) met the eligibility criteria and were included in the data analysis. Pooled odds ratios (ORs) of mortality for ESKD patients who adhered to the Mediterranean versus plant-based diet were 0.49 (95% CI: 0.07–3.54; two studies, I2 = 67%) and 0.87 (95% CI: 0.75–1.01; two studies, I2 = 0%), respectively. Data on mortality for ESKD patients on a DASH diet were limited to one study with an OR of 1.00 (95% CI: 0.89–1.12). The pooled OR of cardiovascular mortality among ESKD patients who adhered to a plant-based diet was 0.86 (95% CI: 0.68–1.08; two studies, I2 = 0%), compared to those who did not. Data on cardiovascular mortality among those with Mediterranean and DASH diet were limited to one study with ORs of 1.14 (95% CI: 0.90–1.43) and 1.19 (95% CI: 0.99–1.43), respectively. Mediterranean diet adherence was found to be associated with reduced risk of left ventricular hypertrophy (LVH) with an OR of 0.82 (95% CI: 0.68–0.99) in a study including 127 ESKD patients. The risk of hyperkalemia was not significant among those with a plant-based diet with an OR of 1.00 (95% CI: 0.94–1.07) in a study including 150 ESKD patients. Conclusions: While our systematic review demonstrated no significant associations of Mediterranean, DASH, and plant-based diets with reduced all-cause mortality or cardiovascular mortality, there was also no evidence that suggested harmful effects of these diets to ESKD patients.