Artificial intelligence (AI) is expected to support clinical judgement in medicine. We constructed a new predictive model for diabetic kidney diseases (DKD) using AI, processing natural language and ...longitudinal data with big data machine learning, based on the electronic medical records (EMR) of 64,059 diabetes patients. AI extracted raw features from the previous 6 months as the reference period and selected 24 factors to find time series patterns relating to 6-month DKD aggravation, using a convolutional autoencoder. AI constructed the predictive model with 3,073 features, including time series data using logistic regression analysis. AI could predict DKD aggravation with 71% accuracy. Furthermore, the group with DKD aggravation had a significantly higher incidence of hemodialysis than the non-aggravation group, over 10 years (N = 2,900). The new predictive model by AI could detect progression of DKD and may contribute to more effective and accurate intervention to reduce hemodialysis.
End-stage renal disease (ESRD) is associated with significantly increased morbidity and mortality resulting from cardiovascular disease (CVD) and infections, accounting for 50% and 20%, respectively, ...of the total mortality in ESRD patients. It is possible that these two complications are linked to alterations in the immune system in ESRD, as uremia is associated with a state of immune dysfunction characterized by immunodepression that contributes to the high prevalence of infections among these patients, as well as by immunoactivation resulting in inflammation that may contribute to CVD. This review describes disorders of the innate and adaptive immune systems in ESRD, underlining the specific role of ESRD-associated disturbances of Toll-like receptors. Finally, based on the emerging links between the alterations of immune system, CVD, and infections in ESRD patients, it emphasizes the potential role of the immune dysfunction in ESRD as an underlying cause for the high mortality in this patient population and the need for more studies in this area.
The Oxford Classification of IgA nephropathy does not account for glomerular crescents. However, studies that reported no independent predictive role of crescents on renal outcomes excluded ...individuals with severe renal insufficiency. In a large IgA nephropathy cohort pooled from four retrospective studies, we addressed crescents as a predictor of renal outcomes and determined whether the fraction of crescent-containing glomeruli associates with survival from either a ≥50% decline in eGFR or ESRD (combined event) adjusting for covariates used in the original Oxford study. The 3096 subjects studied had an initial mean±SD eGFR of 78±29 ml/min per 1.73 m
and median (interquartile range) proteinuria of 1.2 (0.7-2.3) g/d, and 36% of subjects had cellular or fibrocellular crescents. Overall, crescents predicted a higher risk of a combined event, although this remained significant only in patients not receiving immunosuppression. Having crescents in at least one sixth or one fourth of glomeruli associated with a hazard ratio (95% confidence interval) for a combined event of 1.63 (1.10 to 2.43) or 2.29 (1.35 to 3.91), respectively, in all individuals. Furthermore, having crescents in at least one fourth of glomeruli independently associated with a combined event in patients receiving and not receiving immunosuppression. We propose adding the following crescent scores to the Oxford Classification: C0 (no crescents); C1 (crescents in less than one fourth of glomeruli), identifying patients at increased risk of poor outcome without immunosuppression; and C2 (crescents in one fourth or more of glomeruli), identifying patients at even greater risk of progression, even with immunosuppression.
Severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) is causing the global coronavirus disease 2019 (COVID‐19) pandemic. Because complete elimination of SARS‐CoV‐2 appears difficult, ...decreasing the risk of transmission is important. Treatment with 0.1 and 0.05 ppm ozone gas for 10 and 20 hr, respectively, decreased SARS‐CoV‐2 infectivity by about 95%. The magnitude of the effect was dependent on humidity. Treatment with 1 and 2 mg/L ozone water for 10 s reduced SARS‐CoV‐2 infectivity by about 2 and 3 logs, respectively. Our results suggest that low‐dose ozone, in the form of gas and water, is effective against SARS‐CoV‐2.
Clinicopathological characteristics, renal prognosis, and mortality in patients with type 2 diabetes and reduced renal function without overt proteinuria are scarce.
We retrospectively assessed 526 ...patients with type 2 diabetes and reduced renal function (estimated glomerular filtration rate eGFR <60 mL/min/1.73 m
), who underwent clinical renal biopsy and had follow-up data, from Japan's nationwide multicenter renal biopsy registry. For comparative analyses, we derived one-to-two cohorts of those without proteinuria versus those with proteinuria using propensity score-matching methods addressing the imbalances of age, sex, diabetes duration, and baseline eGFR. The primary end point was progression of chronic kidney disease (CKD) defined as new-onset end-stage renal disease, decrease of eGFR by ≥50%, or doubling of serum creatinine. The secondary end point was all-cause mortality.
Eighty-two patients with nonproteinuria (urine albumin-to-creatinine ratio UACR <300 mg/g) had lower systolic blood pressure and less severe pathological lesions compared with 164 propensity score-matched patients with proteinuria (UACR ≥300 mg/g). After a median follow-up of 1.9 years (interquartile range 0.9-5.0 years) from the date of renal biopsy, the 5-year CKD progression-free survival was 86.6% (95% CI 72.5-93.8) for the nonproteinuric group and 30.3% (95% CI 22.4-38.6) for the proteinuric group (log-rank test
< 0.001). The lower renal risk was consistent across all subgroup analyses. The all-cause mortality was also lower in the nonproteinuric group (log-rank test
= 0.005).
Patients with nonproteinuric diabetic kidney disease had better-controlled blood pressure and fewer typical morphological changes and were at lower risk of CKD progression and all-cause mortality.
Abstract Background Cardiovascular disease (CVD) is a leading cause of death in end-stage renal disease (ESRD) patients. Protein-energy wasting (PEW) or malnutrition is common in this population, and ...is associated with increasing risk of mortality. The geriatric nutritional risk index (GNRI) has been developed as a tool to assess the nutritional risk, and is associated with mortality not only in elderly patients but also in ESRD patients. However, whether the GNRI could predict the mortality due to CVD remains unclear in this population. We investigated the prognostic value of GNRI at initiation of hemodialysis (HD) therapy for CVD mortality in a large cohort of ESRD patients. Methods Serum albumin, body weight, and height for calculating GNRI were measured in 1568 ESRD patients. Thereafter, the patients were divided into quartiles according to GNRI levels quartile 1 (Q1): <84.9; Q2: 85.0–91.1; Q3: 91.2–97.2; and Q4: >97.3, and were followed up for up to 10 years. Results GNRI levels independently correlated with serum C-reactive-protein levels ( β = −0.126, p < 0.0001). Rates of freedom from CVD mortality for 10 years were 57.9%, 73.3%, 80.8%, and 89.2% in Q1, Q2, Q3, and Q4, respectively ( p < 0.0001). The GNRI was an independent predictor of CVD mortality (hazard ratio 3.42, 95% confidence interval 2.05–5.70, p < 0.0001 for Q1 vs. Q4). C-index was also greater in an established CVD risk model with GNRI (0.749) compared to that with albumin (0.730), body mass index (0.732), and alone (0.710). Similar results were observed for all-cause mortality. Conclusion GNRI at initiation of HD therapy could predict CVD mortality with incremental value of the predictability compared to serum albumin and body mass index in ESRD patients.
A common renal disease, immunoglobulin A (IgA) nephropathy (IgAN), is associated with glomerular deposition of IgA1-containing immune complexes. IgA1 hinge region (HR) has up to six clustered ...O-glycans consisting of Ser/Thr-linked N-acetylgalactosamine with β1,3-linked galactose and variable sialylation. IgA1 glycoforms with some galactose-deficient (Gd) HR O-glycans play a key role in IgAN pathogenesis. The clustered and variable O-glycans make the IgA1 glycomic analysis challenging and better approaches are needed. Here, we report a comprehensive analytical workflow for IgA1 HR O-glycoform analysis. We combined an automated quantitative analysis of the HR O-glycopeptide profiles with sequential deglycosylation to remove all but Gd O-glycans from the HR. The workflow was tested using serum IgA1 from healthy subjects. Twelve variants of glycopeptides corresponding to the HR with three to six O-glycans were detected; nine glycopeptides carried up to three Gd O-glycans. Sites with Gd O-glycans were unambiguously identified by electron-transfer/higher-energy collision dissociation tandem mass spectrometry. Extracted ion chromatograms of isomeric glycoforms enabled quantitative assignment of Gd sites. The most frequent Gd site was T
, followed by S
, T
, T
, and S
. The new workflow for quantitative profiling of IgA1 HR O-glycoforms with site-specific resolution will enable identification of pathogenic IgA1 HR O-glycoforms in IgAN.
Abstract
Background
Although the 2018 revised International Society of Nephrology/Renal Pathology Society (ISN/RPS) classification was proposed recently, until now, no reports have been made ...comparing the association of renal prognosis between the 2018 revised ISN/RPS classification and the 2003 ISN/RPS classification. The present study aimed to assess the usefulness, especially of activity and chronicity assessment, of the 2018 revised ISN/RPS classification for lupus nephritis (LN) in terms of renal prognosis compared to the classification in 2003.
Methods
We retrospectively collected medical records of 170 LN patients from the database of renal biopsy at Fujita Health University from January 2003 to April 2019. Each renal biopsy specimen was reevaluated according to both the 2003 ISN/RPS classification and the 2018 revised ISN/RPS classification. Renal endpoint was defined as a 30% decline of estimated glomerular filtration rate (eGFR).
Results
A total of 129 patients were class III/IV±V (class III, 44 patients; class IV, 35 patients; class III/IV+V, 50 patients). The mean age was 42 years, 88% were female, and the median observation period was 50.5 months. Renal prognosis was significantly different among the classes and significantly poor in the patients with higher modified National Institute of Health (mNIH) chronicity index (C index, ≥ 4) by a log-rank test (
p
= 0.05 and
p
= 0.02, respectively). By Cox proportional hazard models, only the C index was significantly associated with renal outcome (hazard ratio 1.32, 95% CI 1.11–1.56,
p
≤ 0.01), while the classes, the 2003 activity and chronicity subdivision, and the mNIH activity index had no significant association with renal outcome. Each component of the C index was significantly associated with renal outcome in different models.
Conclusion
This study demonstrates that the 2018 revised ISN/RPS classification was more useful in terms of association with renal prognosis compared to the 2003 ISN/RPS classification.
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 ( 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.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Capillary electrophoresis coupled with time-of-flight mass spectrometry was used to explore new serum biomarkers with high sensitivity and specificity for diabetic nephropathy (DN) diagnosis, through ...comprehensive analysis of serum metabolites with 78 diabetic patients. Multivariate analyses were used for identification of marker candidates and development of discriminative models. Of the 289 profiled metabolites, orthogonal partial least-squares discriminant analysis identified 19 metabolites that could distinguish between DN with macroalbuminuria and diabetic patients without albuminuria. These identified metabolites included creatinine, aspartic acid, γ-butyrobetaine, citrulline, symmetric dimethylarginine (SDMA), kynurenine, azelaic acid, and galactaric acid. Significant correlations between all these metabolites and urinary albumin-to-creatinine ratios (
p
< 0.009, Spearman’s rank test) were observed. When five metabolites (including γ-butyrobetaine, SDMA, azelaic acid and two unknowns) were selected from 19 metabolites and applied for multiple logistic regression model, AUC value for diagnosing DN was 0.927 using the whole dataset, and 0.880 in a cross-validation test. In addition, when four known metabolites (aspartic acid, SDMA, azelaic acid and galactaric acid) were applied, the resulting AUC was still high at 0.844 with the whole dataset and 0.792 with cross-validation. Combination of serum metabolomics with multivariate analyses enabled accurate discrimination of DN patients. The results suggest that capillary electrophoresis-mass spectrometry based metabolome analysis could be used for DN diagnosis.