These data showed that oral administration of alfacalcidol for predialysis CKD patients was associated with reduced risk for CVD.

Artificial intelligence is increasingly being adopted in medical fields to predict various outcomes. In particular, chronic kidney disease (CKD) is problematic because it often progresses to end-stage kidney disease. However, the trajectories of kidney function depend on individual patients. In this study, we propose a machine learning-based model to predict the rapid decline in kidney function among CKD patients by using a big hospital database constructed from the information of 118,584 patients derived from the electronic medical records system. The database included the estimated glomerular filtration rate (eGFR) of each patient, recorded at least twice over a period of 90 days. The data of 19,894 patients (16.8%) were observed to satisfy the CKD criteria. We characterized the rapid decline of kidney function by a decline of 30% or more in the eGFR within a period of two years and classified the available patients into two groups—those exhibiting rapid eGFR decline and those exhibiting non-rapid eGFR decline. Following this, we constructed predictive models based on two machine learning algorithms. Longitudinal laboratory data including urine protein, blood pressure, and hemoglobin were used as covariates. We used longitudinal statistics with a baseline corresponding to 90-, 180-, and 360-day windows prior to the baseline point. The longitudinal statistics included the exponentially smoothed average (ESA), where the weight was defined to be 0.9*(t/b), where t denotes the number of days prior to the baseline point and b denotes the decay parameter. In this study, b was taken to be 7 (7-day ESA). We used logistic regression (LR) and random forest (RF) algorithms based on Python code with scikit-learn library ( https://scikit-learn.org/ ) for model creation. The areas under the curve for LR and RF were 0.71 and 0.73, respectively. The 7-day ESA of urine protein ranked within the first two places in terms of importance according to both models. Further, other features related to urine protein were likely to rank higher than the rest. The LR and RF models revealed that the degree of urine protein, especially if it exhibited an increasing tendency, served as a prominent risk factor associated with rapid eGFR decline.

No abstract

Abstract Background The detection of leukocyte-derived CD11b (α subunit of integrin Mac-1) and CD163 (scavenger receptor) in urine may reflect renal inflammation in antineutrophil cytoplasmic antibody-associated glomerulonephritis (ANCA-GN). The objective of this study was to evaluate the clinical significance of urinary CD11b (U-CD11b) and CD163 (U-CD163) in ANCA-GN. Methods U-CD11b and U-CD163 were examined using enzyme-linked immunosorbent assay in ANCA-GN urine samples from our institutional cohort (n = 88) and a nationwide cohort (n = 138), and their association with renal histology was subsequently analyzed. Logistic regression analyses were performed on a nationwide ANCA cohort to determine the associations of the two urinary molecules with renal remission failure at 6 months or with yearly estimated glomerular filtration rate (eGFR) slope over a 24-month observation period. Results U-CD11b and U-CD163 were significantly associated with cellular crescent formation and leukocyte accumulation in glomerular crescents. With regard to interstitial inflammation, both levels of U-CD11b and U-CD163 at diagnosis remarkably increased in ANCA-GN compared with the levels observed in nonglomerular kidney disorders including nephrosclerosis, immunoglobulin G4-related disease and tubulointerstitial nephritis; however, the presence of U-CD11b alone was significantly correlated with tubulointerstitial leukocyte infiltrates. Although neither U-CD11b nor U-CD163 at diagnosis was associated with remission failure at 6 months, multivariate analysis demonstrated that the baseline U-CD11b levels were significantly associated with the increase in eGFR following immunosuppressive therapy. Conclusions Although both U-CD11b and U-CD163 reflect renal leukocyte accumulation, U-CD11b at diagnosis provides additional clinical value by predicting the recovery rate after the treatment of ANCA-GN.

Introduction: There are few studies on the association between serum uric acid (UA) level and mortality in incident dialysis patients. We aimed to clarify whether the serum UA level at dialysis initiation is associated with mortality during maintenance dialysis. Methods: We enrolled 1486 incident dialysis patients who participated in a previous multicenter prospective cohort study in Japan. We classified the patients into the following five groups according to their serum UA levels at dialysis initiation: G1 with a serum UA level <6 mg/dL; G2, 6.0-8.0 mg/dL; G3, 8.0-10.0 mg/dL; G4, 10.0-12.0 mg/dL; and G5, !12.0 mg/dL. We created three models (Model 1: adjusted for age and sex, Model 2: adjusted for Model 1 þ 12 variables, and Model 3: stepwise regression adjusted for Model 2 þ 13 variables) and performed a multivariate Cox proportional hazard regression analysis to examine the association between the serum UA level and outcomes, including infection-related mortality. Results: Hazard ratios (HRs) were calculated relative to the G2, because the all-cause mortality rate was the lowest in G2. For Models 1 and 2, the all-cause mortality rate was significantly higher in G5 than in G2 (