The progression and complications of chronic kidney disease should differ depending on the cause (C), glomerular filtration rate category (G), and albuminuria (A). The KNOW-CKD (KoreaN Cohort Study for Outcome in Patients With Chronic Kidney Disease), which is a prospective cohort study, enrolls subjects with chronic kidney disease stages 1 to 5 (predialysis). Nine nephrology centers in major university hospitals throughout Korea will enroll approximately 2,450 adults with chronic kidney disease over a 5-year period from 2011 to 2015. The participating individuals will be monitored for approximately 10 years until death or until end-stage renal disease occurs. The subjects will be classified into subgroups based on the following specific causes of chronic kidney disease: glomerulonephritis, diabetic nephropathy, hypertensive nephropathy, polycystic kidney disease, and others. The eligible subjects will be evaluated at baseline for socio-demographic information, detailed personal/family history, office BP, quality of life, and health behaviors. After enrollment in the study, thorough assessments, including laboratory tests, cardiac evaluation and radiologic imaging, will be performed according to the standardized protocol. The biospecimen samples will be collected regularly. A renal event is defined by >50% decrease in estimated GFR (eGFR) from the baseline values, doubling of serum creatinine, or end-stage renal disease. The primary composite outcome consists of renal events, cardiovascular events, and death. As of September 2013, 1,470 adult chronic kidney disease subjects were enrolled in the study, including 543 subjects with glomerulonephritis, 317 with diabetic nephropathy, 294 with hypertensive nephropathy and 249 with polycystic kidney disease. As the first large-scale chronic kidney disease cohort study to be established and maintained longitudinally for up to 10 years, the KNOW-CKD will help to clarify the natural course, complication profiles, and risk factors of Asian populations with chronic kidney disease. No. NCT01630486 at http://www.clinicaltrials.gov .

Background: Urinary tract infection (UTI) occurs in 30%-50% of individuals with autosomal dominant polycystic kidney disease (ADPKD). However, the clinical relevance of asymptomatic pyuria in ADPKD patients remains unknown. Methods: We retrospectively reviewed medical records of 256 ADPKD patients who registered to the ADPKD clinic at Seoul National University Hospital from Aug 1999 to Aug 2010. We defined the asymptomatic pyuria as more than 5-9 white blood cells in high-power field with no related symptoms or signs of overt UTI. Patients were categorized into 2 groups depending on its duration and frequency: Group A included non-pyuria and transient pyuria patients; Group B included recurrent and persistent pyuria patients. The association between asymptomatic pyuria and both the development of overt UTI and the deterioration of renal function were examined. Results: With a mean follow-up duration of 65.3 months, 176 (68.8%) out of 256 patients experienced 681 episodes of asymptomatic pyuria and 50 episodes of UTI. The annual incidence of asymptomatic pyuria was 0.492 episodes/patient/year. The patients in group B showed female predominance (58.5% vs. 42.0%, P=0.01) and experienced an upper UTI more frequently (hazard ratio: 4.612, 95% confidence interval: 1.735-12.258; P=0.002, adjusted for gender and hypertension). The annual change in estimated glomerular filtration rate (ΔeGFR) was significantly larger in magnitude in group B than in group A (-2.7±4.56 vs. -1.17±5.8, respectively; P=0.01). Age and Group B found to be the independent variables for ΔeGFR and developing end-stage renal disease (16.0% vs. 4.3%, respectively; P=0.001). Conclusions: Chronic asymptomatic pyuria may increase the risk of developing overt UTI and may contribute to declining renal function in ADPKD.

The prevalence of hyperuricemia and chronic kidney disease (CKD) has been steadily increasing. The role of hyperuricemia and efficacy of uric acid-lowering agents against CKD progression remain controversial. This study aimed to evaluate the effect of hyperuricemia and uric acid-lowering agents on the progression of CKD. A total 2042 patients with CKD were analyzed in the KoreaN cohort Study for Outcomes in patients With Chronic Kidney Disease (KNOW-CKD), a prospective cohort study. Patients were classified into quartiles on the basis of their serum uric acid level and the prevalence of advanced CKD was higher in patients with a high uric acid level. A composite renal outcome was defined as one or more of the following: initiation of dialysis or transplantation, a two-fold increase in baseline serum creatinine levels, or a 50% decline in the estimated glomerular filtration rate during the follow-up period. A Cox proportional hazard ratio model was applied to analyze the relationship between composite renal outcome and uric acid levels. The risk of progression to renal failure increased by 28% (hazard ratio [HR], 1.277; 95% confidence interval [CI], 1.212–1.345) for each 1 mg/dl increase in the baseline uric acid level. In multivariate models, an association was found between the highest quartile of uric acid and increased risk of composite renal outcome (HR, 3.590; 95% CI, 2.546–5.063). A propensity score matching analysis was performed to survey the effect of uric acid lowering agent. Both allopurinol and febuxostat did not affect the renal outcome. In conclusion, hyperuricemia appears to be an independent risk factor for composite renal outcome, but allopurinol and febuxostat did not show reno-protective effect.

Background and objectives: Intradialytic hypotension has high clinical significance. However, predicting it using conventional statistical models may be difficult because several factors have interactive and complex effects on the risk. Herein, we applied a deep learning model (recurrent neural network) to predict the risk of intradialytic hypotension using a timestamp-bearing dataset. Design, setting, participants, & measurements: We obtained 261,647 hemodialysis sessions with 1,600,531 independent timestamps (i.e., time-varying vital signs) and randomly divided them into training (70%), validation (5%), calibration (5%), and testing (20%) sets. Intradialytic hypotension was defined when nadir systolic BP was <90 mm Hg (termed intradialytic hypotension 1) or when a decrease in systolic BP ≥20 mm Hg and/or a decrease in mean arterial pressure ≥10 mm Hg on the basis of the initial BPs (termed intradialytic hypotension 2) or prediction time BPs (termed intradialytic hypotension 3) occurred within 1 hour. The area under the receiver operating characteristic curves, the area under the precision-recall curves, and F1 scores obtained using the recurrent neural network model were compared with those obtained using multilayer perceptron, Light Gradient Boosting Machine, and logistic regression models. Results: The recurrent neural network model for predicting intradialytic hypotension 1 achieved an area under the receiver operating characteristic curve of 0.94 (95% confidence intervals, 0.94 to 0.94), which was higher than those obtained using the other models (P<0.001). The recurrent neural network model for predicting intradialytic hypotension 2 and intradialytic hypotension 3 achieved area under the receiver operating characteristic curves of 0.87 (interquartile range, 0.87–0.87) and 0.79 (interquartile range, 0.79–0.79), respectively, which were also higher than those obtained using the other models (P≤0.001). The area under the precision-recall curve and F1 score were higher using the recurrent neural network model than they were using the other models. The recurrent neural network models for intradialytic hypotension were highly calibrated. Conclusions: Our deep learning model can be used to predict the real-time risk of intradialytic hypotension.

Background.In vitro studies of peritoneal dialysis (PD) solutions demonstrated that a biocompatible fluid with neutral-pH and low glucose degradation products (LF) has better biocompatibility than a conventional acidic lactate-buffered fluid (CF). However, few clinical trials have investigated the effects of the biocompatible solution on residual renal function (RRF). We performed a prospective, randomized trial with patients starting continuous ambulatory peritoneal dialysis (CAPD). Methods. Ninety-one incident patients started CAPD for 12-month treatment with either LF (Balance®, Fresenius, n = 48) or CF (CAPD/DPCA®, Fresenius, n = 43). RRF, peritoneal solute transport rate and solute clearance were measured every 6 months. Results. LF had a significant effect on the change of glomerular filtration rate (GFR) ( P = 0.048 by the mixed model). In per-protocol analysis, GFR in the LF group did not decrease over a 12-month period, while GFR in the control group significantly decreased (0.13 ± 33.4 L/ week/1.73 m ² for LF versus −13.6 ± 19.4 L/week/1.73 m ² for CF, P = 0.049). Subgroup analysis for patients with initial GFR of 2 mL/min/1.73 m ² or above showed a significantly higher GFR for the LF group over the 12-month period. At Month 13, serum total CO ₂ levels were higher and serum albumin levels were lower in the LF group. No differences between the two groups were observed for the C-reactive protein. Over the 12-month period, effluent cancer antigen-125 levels significantly increased in the LF group, compared with those of the CF group, while effluent interleukin-6 levels were not different between the two groups. Conclusion. Our study suggests that LF may better preserve RRF over the 12-month treatment period in incident CAPD patients.