Previous scoring models such as the Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) and the Sequential Organ Failure Assessment (SOFA) scoring systems do not adequately ...predict mortality of patients undergoing continuous renal replacement therapy (CRRT) for severe acute kidney injury. Accordingly, the present study applies machine learning algorithms to improve prediction accuracy for this patient subset.
We randomly divided a total of 1571 adult patients who started CRRT for acute kidney injury into training (70%, n = 1094) and test (30%, n = 477) sets. The primary output consisted of the probability of mortality during admission to the intensive care unit (ICU) or hospital. We compared the area under the receiver operating characteristic curves (AUCs) of several machine learning algorithms with that of the APACHE II, SOFA, and the new abbreviated mortality scoring system for acute kidney injury with CRRT (MOSAIC model) results.
For the ICU mortality, the random forest model showed the highest AUC (0.784 0.744-0.825), and the artificial neural network and extreme gradient boost models demonstrated the next best results (0.776 0.735-0.818). The AUC of the random forest model was higher than 0.611 (0.583-0.640), 0.677 (0.651-0.703), and 0.722 (0.677-0.767), as achieved by APACHE II, SOFA, and MOSAIC, respectively. The machine learning models also predicted in-hospital mortality better than APACHE II, SOFA, and MOSAIC.
Machine learning algorithms increase the accuracy of mortality prediction for patients undergoing CRRT for acute kidney injury compared with previous scoring models.
Obesity, Metabolic Abnormality, and Progression of CKD Yun, Hae-Ryong; Kim, Hyoungnae; Park, Jung Tak ...
American journal of kidney diseases,
September 2018, 2018-09-00, 20180901, Letnik:
72, Številka:
3
Journal Article
Recenzirano
Recent studies have yielded conflicting findings on the association between obesity and progression of chronic kidney disease (CKD). Few studies have evaluated whether metabolic abnormalities may ...accelerate the rate of progression of CKD.
Prospective observational cohort study.
1,940 participants from the Korean Cohort Study for Outcome in Patients With Chronic Kidney Disease (KNOW-CKD)
Obesity and metabolic abnormality. Obesity was defined as body mass index ≥ 25kg/m2. Metabolic abnormality was defined as the presence of 3 or more of the following 5 components: hypertension, fasting glucose level > 125mg/dL or the presence of type 2 diabetes, triglyceride level > 150mg/dL or use of lipid-lowering drugs, high-density lipoprotein cholesterol level ≤ 40mg/dL in men and ≤ 50mg/dL in women, and high-sensitivity C-reactive protein level > 1mg/L.
A composite of a 50% decline in estimated glomerular filtration rate from the baseline value or end-stage kidney disease.
Multivariable cause-specific hazards models implemented to assess the association between obesity, metabolic abnormality, and CKD progression.
During a mean follow-up of 3.1 years, the primary outcome occurred in 395 (20.4%) patients. In multivariable analyses, after adjustment for confounding factors, obesity and metabolic abnormality were significantly associated with 1.41-fold (95% CI, 1.08-1.83; P=0.01) and 1.38-fold (95% CI, 1.03-1.85; P=0.03) increased risk for adverse renal outcomes, respectively. Patients were categorized into 4 groups depending on the presence of obesity and metabolic abnormality. Compared with those with neither obesity nor metabolic abnormality, those with obesity and metabolic abnormality had a greater risk for CKD progression (HR, 1.53; P=0.03). Those with obesity without metabolic abnormality also had a higher rate of CKD progression (HR, 1.97; P=0.01).
Observational study, limited power to detect cardiovascular disease outcomes, unmeasured confounders.
Both metabolic abnormality and obesity are associated with a significantly increased risk for CKD progression. Notably, obese patients without metabolic abnormality also have an elevated risk for CKD progression.
Abstract
Hypotension after starting continuous renal replacement therapy (CRRT) is associated with worse outcomes compared with normotension, but it is difficult to predict because several factors ...have interactive and complex effects on the risk. The present study applied machine learning algorithms to develop models to predict hypotension after initiating CRRT. Among 2349 adult patients who started CRRT due to acute kidney injury, 70% and 30% were randomly assigned into the training and testing sets, respectively. Hypotension was defined as a reduction in mean arterial pressure (MAP) ≥ 20 mmHg from the initial value within 6 h. The area under the receiver operating characteristic curves (AUROCs) in machine learning models, such as support vector machine (SVM), deep neural network (DNN), light gradient boosting machine (LGBM), and extreme gradient boosting machine (XGB) were compared with those in disease-severity scores such as the Sequential Organ Failure Assessment and Acute Physiology and Chronic Health Evaluation II. The XGB model showed the highest AUROC (0.828 0.796–0.861), and the DNN and LGBM models followed with AUROCs of 0.822 (0.789–0.856) and 0.813 (0.780–0.847), respectively; all machine learning AUROC values were higher than those obtained from disease-severity scores (AUROCs < 0.6). Although other definitions of hypotension were used such as a reduction of MAP ≥ 30 mmHg or a reduction occurring within 1 h, the AUROCs of machine learning models were higher than those of disease-severity scores. Machine learning models successfully predict hypotension after starting CRRT and can serve as the basis of systems to predict hypotension before starting CRRT.
The 2021 Kidney Disease: Improving Global Outcomes (KDIGO) clinical practice guideline for the management of blood pressure (BP) in chronic kidney disease (CKD) recommends a target systolic BP of ...<120 mmHg as this target can provide cardiovascular benefits. However, it remains unclear whether implementing the new BP target could improve kidney outcomes.
The association between the 2021 KDIGO BP target and CKD progression was examined and compared with the 2012 KDIGO BP target among 1724 participants included in the KoreaN Cohort Study for Outcomes in Patients With CKD. The main exposure was the BP status categorized according to the 2012 or 2021 KDIGO guideline: (1) controlled within the 2021 target, (2) controlled within the 2012 target only, and (3) above both targets. The primary outcome was a composite kidney outcome of ≥50% decline in the estimated glomerular filtration rate from baseline or the initiation of kidney replacement therapy during the follow-up period.
Composite kidney outcomes occurred in 650 (37.7%) participants during the 8078 person-years of follow-up (median, 4.9 years). The incidence rates of this outcome were 55, 66.5, and 116.4 per 1000 person-years in BP controlled within the 2021 and 2012 KDIGO targets, and BP above both targets, respectively. In the multivariable cause-specific hazard model, hazard ratios for the composite outcome were 0.76 (95% confidence interval (CI), 0.60-0.95) for BP controlled within the 2021 target and 1.36 (95% CI, 1.13-1.64) for BP above both targets, compared with BP controlled within 2012 target only.
The newly lowered BP target by the 2021 KDIGO guideline was associated with improved kidney outcome compared with BP target by the 2012 KDIGO guideline.
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.
Summary
Despite the lack of safety and efficacy data regarding immune checkpoint inhibitors (ICIs) for renal dysfunction, they have been approved to treat even in the patients with end-stage renal ...disease (ESRD). We report our experience with ICI administration to three ESRD patients undergoing hemodialysis. One of the patients had a partial response for several months; however, the other patients had a stable disease while undergoing dialysis. The toxicity was tolerable; however, one patient developed grade 2 pneumonitis. A literature review of other rarely reported cases of hemodialysis revealed that 10 out of 13 patients had a partial response or complete response; in addition, grade 3 or grade 4 immune-related adverse events occurred in 3 patients. ESRD combined with dialysis may not be a contraindication for the use of ICIs. ICIs can be beneficial to ESRD patients undergoing dialysis. However, caution is needed regarding immune-related adverse events. Further prospective studies involving pharmacokinetic analyses are necessary to obtain reliable safety and efficacy data.
Aim
To investigate the possible effect of haemodialysis (HD) on the pharmacokinetic (PK) and pharmacodynamic (PD) characteristics of evogliptin, a dipeptidyl peptidase‐4 (DPP‐4) inhibitor.
Methods
A ...single‐dose, open‐label, parallel‐group study of eight end‐stage renal disease (ESRD) patients and eight matched healthy subjects was conducted. ESRD patients received a single oral dose of evogliptin 5 mg after and before HD with a 2‐week washout between each dose, and healthy subjects received a single oral dose of evogliptin 5 mg. Serial blood, dialysate, and urine samples were collected to assess the PK and PD profiles of evogliptin. To compare PK parameters before and after HD, geometric mean ratios (GMRs) and 90% confidence intervals (CIs) were calculated.
Results
The GMRs for the maximum concentration and area under the concentration‐time curve from time 0 to the last measurable timepoint (AUClast) of evogliptin when administered before HD compared with after HD were 0.7293 (90% CI 0.6171‐0.8620) and 0.9480 (90% CI 0.8162‐1.1010), respectively. The maximum DPP‐4 inhibitory effect, area under the DPP‐4 inhibitory effect‐time curve, and time duration of more than 80% DPP‐4 inhibition were comparable when evogliptin was administered before and after HD. Compared with healthy subjects, the mean AUClast of evogliptin was approximately 1.4‐fold greater in ESRD patients, but the difference is unlikely to affect the safety and efficacy of evogliptin.
Conclusion
The effect of HD on the PK and PD characteristics of evogliptin was not clinically significant; therefore, dose adjustment according to HD status is not necessary.
Introduction
The unalleviated burden of chronic physical illness (CPI) increases the risk of suicidal behaviors (SB) in affected individuals. This study tested the interpersonal theory of suicide ...(ITS) in patients with CPI.
Methods
Patients diagnosed with cardiovascular, cerebrovascular, and renal diseases were recruited from two hospitals in South Korea. Data from 257 participants who completed Time (T) 1 and T2 surveys were analyzed. Hierarchical regression analyses for passive and active suicide ideation (PSI and ASI), and suicide plans and attempts (SP and SA) at both time points were conducted.
Results
Interpersonal theory of suicide hypotheses were partially supported. Even accounting for factors such as depression, anxiety, and lifetime SA, some main and interaction effects of the ITS constructs explained SB in a cross‐sectional examination, but to a lesser degree in a longitudinal examination that controlled for T1 SB. PB was a consistent correlate of SB. TB was also relevant, as PB–SA association was significant among participants with high TB both times. ASI was associated with SP and SA at T1, and the ASI‐SP association at T1 was stronger at a high CS level.
Conclusions
Overall, the results suggest the relevance of ITS constructs that warrant attention to prevent SB in patients with CPI.
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.
We obtained 261,647 hemodialysis sessions with 1,600,531 independent timestamps (
., 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.
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 (
<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 (
≤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.
Our deep learning model can be used to predict the real-time risk of intradialytic hypotension.
Cisplatin causes acute kidney injury (AKI) through proximal tubular injury. We investigated the protective effect of the adenosine monophosphate protein kinase (AMPK) activator ...5-aminoimidazole-4-carboxamide ribonucleotide (AICAR) against cisplatin-induced AKI. We investigated whether the AMP-kinase activator AICAR ameliorates cisplatin-induced AKI through the JAK/STAT/SOCS pathway. Male Sprague-Dawley (SD) rats were randomly divided into four groups: control, AICAR, cisplatin, and cisplatin + AICAR. As appropriate to their treatment group, the rats were injected with a single dose of cisplatin (7 mg/kg, i.p.). AICAR was administered to the rats at 100 mg/kg i.p. daily. Blood urea nitrogen (BUN) and serum creatinine were measured. Renal damage was analyzed in sections stained with hematoxylin and eosin (H&E). Renal tissues were also examined by immunohistochemistry and western blot for p-AMPK, Kim-1, cleaved caspase 3, and JAK/STAT/SOCS. For in vitro studies, NRK-52E normal rat kidney cells were treated with cisplatin and/or AICAR. By western blot, we confirmed the expression of p-AMPK and the JAK/STAT/SOCS pathway in NRK-52E cells. AICAR was protective against cisplatin-induced acute tubular injury by up-regulating p-AMPK expression in NRK-52E cells. Protein expression levels of JAK2/STAT1 were markedly ameliorated in NRK-52E cells by AICAR. The protective mechanism of AICAR may be associated with suppression of the JAK2/STAT1 pathway and up-regulation of SOCS1, an inhibitor of the JAK2/STAT1 pathway. The present study demonstrates the protective effects of AICAR against cisplatin-induced AKI and shows a new renoprotective mechanism through the JAK2/STAT1/SOCS1 pathway and apoptosis inhibition. This study suggests that activation of the AMPK activator AICAR might ameliorate cisplatin-induced AKI.
•AICAR, AMPK activator ameliorated cisplatin induced acute kidney injury.•Serum creatinine and BUN levels decreased in cisplatin-treated rats after treatment with AICAR.•AICAR with cisplatin treatment decreased p-STAT1 and p-JAK2, inhibitor of SOCS1 expression was decreased after cisplatin treatment group.•AICAR treatment improved AKI index, down-regulated KIM-1 expression in association with p-AMPK up-regulation.•AICAR ameliorated cisplatin-induced AKI, which may be associated with suppression of the JAK2/STAT1 pathway.