Risk prediction models for contrast induced nephropathy: systematic review

Applicable Machine Learning Model for Predicting Contrast-induced Nephropathy Based on Pre-catheterization Variables

Objective Contrast agents used for radiological examinations are an important cause of acute kidney injury (AKI). We developed and validated a machine learning and clinical scoring prediction model to stratify the risk of contrast-induced nephropathy, considering the limitations of current classical and machine learning models. Methods This retrospective study included 38,481 percutaneous coronary intervention cases from 23,703 patients in a tertiary hospital. We divided the cases into development and internal test sets (8:2). Using the development set, we trained a gradient boosting machine prediction model (complex model). We then developed a simple model using seven variables based on variable importance. We validated the performance of the models using an internal test set and tested them externally in two other hospitals. Results The complex model had the best area under the receiver operating characteristic (AUROC) curve at 0.885 [95% confidence interval (CI) 0.876-0.894] in the internal test set and 0.837 (95% CI 0.819-0.854) and 0.850 (95% CI 0.781-0.918) in two different external validation sets. The simple model showed an AUROC of 0.795 (95% CI 0.781-0.808) in the internal test set and 0.766 (95% CI 0.744-0.789) and 0.782 (95% CI 0.687-0.877) in the two different external validation sets. This was higher than the value in the well-known scoring system (Mehran criteria, AUROC=0.67). The seven precatheterization variables selected for the simple model were age, known chronic kidney disease, hematocrit, troponin I, blood urea nitrogen, base excess, and N-terminal pro-brain natriuretic peptide. The simple model is available at http://52.78.230.235:8081/Conclusions We developed an AKI prediction machine learning model with reliable performance. This can aid in bedside clinical decision making.

Impact of Hyperglycemia on Complication and Mortality after Transarterial Chemoembolization for Hepatocellular Carcinoma

BACKGRUOUND

Current guidelines regarding periprocedural glycemic control to prevent complications after nonsurgical invasive procedures are insufficient. Transarterial chemoembolization (TACE) is a widely used treatment for unresectable hepatocellular carcinoma. We aimed to investigate the association between diabetes mellitus (DM) per se and the degree of hyperglycemia with postprocedural complications after TACE.

METHODS

A total of 22,159 TACE procedures performed at Seoul National University Hospital from 2005 to 2018 were retrospectively analyzed. The associations between DM, preprocedural glycosylated hemoglobin (HbA1c), and periprocedural average glucose with postprocedural adverse outcomes were evaluated. The primary outcome was occurrence of postprocedural bacteremia. Secondary outcomes were acute kidney injury (AKI), delayed discharge and death within 14 days. Periprocedural glucose was averaged over 3 days: the day of, before, and after the TACE procedures. Propensity score matching was applied for procedures between patients with or without DM.

RESULTS

Periprocedural average glucose was significantly associated with bacteremia (adjusted odds ratio per 50 mg/dL of glucose, 1.233; 95% confidence interval, 1.071 to 1.420; P=0.004), AKI, delayed discharge, and death within 14 days. DM per se was only associated with bacteremia and AKI. Preprocedural HbA1c was associated with delayed discharge. Average glucose levels above 202 and 181 mg/dL were associated with a significantly higher risk of bacteremia and AKI, respectively, than glucose levels of 126 mg/dL or lower.

CONCLUSION

Periprocedural average glucose, but not HbA1c, was associated with adverse outcomes after TACE, which is a nonsurgical invasive procedure. This suggests the importance of periprocedural glycemic control to reduce postprocedural complications.

Clinical and economic outcomes of assigning percutaneous coronary intervention patients to contrast-sparing strategies based on the predicted risk of contrast-induced acute kidney injury

OBJECTIVE

Contrast-sparing strategies have been developed for percutaneous coronary intervention (PCI) patients at increased risk of contrast-induced acute kidney injury (CI-AKI), and numerous CI-AKI risk prediction models have been created. However, the potential clinical and economic consequences of using predicted CI-AKI risk thresholds for assigning patients to contrast-sparing regimens have not been evaluated. We estimated the clinical and economic consequences of alternative CI-AKI risk thresholds for assigning Medicare PCI patients to contrast-sparing strategies.

METHODS

Medicare data were used to identify inpatient PCI from January 2017 to June 2021. A prediction model was developed to assign each patient a predicted probability of CI-AKI. Multivariable modeling was used to assign each patient two marginal predicted values for each of several clinical and economic outcomes based on (1) their underlying clinical and procedural characteristics plus their true CI-AKI status in the data and (2) their characteristics plus their counterfactual CI-AKI status. Specifically, CI-AKI patients above the predicted risk threshold for contrast-sparing were reassigned their no CI-AKI (counterfactual) outcomes. Expected event rates, resource use, and costs were estimated before and after those CI-AKI patients were reassigned their counterfactual outcomes. This entailed bootstrapped sampling of the full cohort.

RESULTS

Of the 542,813 patients in the study cohort, 5,802 (1.1%) had CI-AKI. The area under the receiver operating characteristic curve for the prediction model was 0.81. At a predicted risk threshold for CI-AKI of >2%, approximately 18.0% of PCI patients were assigned to contrast-sparing strategies, resulting in (/100,000 PCI patients) 121 fewer deaths, 58 fewer myocardial infarction readmissions, 4,303 fewer PCI hospital days, $11.3 million PCI cost savings, and $25.8 million total one-year cost savings, versus no contrast-sparing strategies.

LIMITATIONS

Claims data may not fully capture disease burden and are subject to inherent limitations such as coding inaccuracies. Further, the dataset used reflects only individuals with fee-for-service Medicare, and the results may not be generalizable to Medicare Advantage or other patient populations.

CONCLUSIONS

Assignment to contrast-sparing regimens at a predicted risk threshold close to the underlying incidence of CI-AKI is projected to result in significant clinical and economic benefits.

Association between fasting stress hyperglycemia ratio and contrast-induced acute kidney injury in coronary angiography patients: a cross-sectional study

Aims

Stress hyperglycemia ratio (SHR), an emerging indicator of critical illness, exhibits a significant association with adverse cardiovascular outcomes. The primary aim of this research endeavor is to evaluate the association between fasting SHR and contrast-induced acute kidney injury (CI-AKI).

Methods

This cross-sectional study comprised 3,137 patients who underwent coronary angiography (CAG) or percutaneous coronary intervention (PCI). The calculation of fasting SHR involved dividing the admission fasting blood glucose by the estimated mean glucose obtained from glycosylated hemoglobin. CI-AKI was assessed based on elevated serum creatinine (Scr) levels. To investigate the relationship between fasting SHR and the proportion of SCr elevation, piecewise linear regression analysis was conducted. Modified Poisson's regression analysis was implemented to evaluate the correlation between fasting SHR and CI-AKI. Subgroup analysis and sensitivity analysis were conducted to explore result stability.

Results

Among the total population, 482 (15.4%) patients experienced CI-AKI. Piecewise linear regression analysis revealed significant associations between the proportion of SCr elevation and fasting SHR on both sides (≤ 0.8 and > 0.8) [β = -12.651, 95% CI (-23.281 to -2.022), P = 0.020; β = 8.274, 95% CI (4.176 to 12.372), P < 0.001]. The Modified Poisson's regression analysis demonstrated a statistically significant correlation between both the lowest and highest levels of fasting SHR and an increased incidence of CI-AKI [(SHR < 0.7 vs. 0.7 ≤ SHR < 0.9) β = 1.828, 95% CI (1.345 to 2.486), P < 0.001; (SHR ≥ 1.3 vs. 0.7 ≤ SHR < 0.9) β = 2.896, 95% CI (2.087 to 4.019), P < 0.001], which was further validated through subgroup and sensitivity analyses.

Conclusion

In populations undergoing CAG or PCI, both lowest and highest levels of fasting SHR were significantly associated with an increased occurrence of CI-AKI.

Meta-analysis of clinical adverse events after CABG vs. PCI in patients with chronic kidney disease and coronary artery disease

AIM

To investigate the efficacy and postoperative clinical adverse events of coronary artery bypass grafting (CABG) or percutaneous coronary intervention (PCI) for chronic kidney disease (CKD) study participants combined with coronary artery disease (CAD).

METHODS

All randomized controlled trials (RCTs) that focus on the therapeutic effect evaluation of CABG and PCI and their effect on postoperative clinical adverse events as well as main adverse cardiovascular and cerebrovascular events (MACCEs) in CKD study participants with CAD were screened from the following databases, including CNKI, CBM, Wan Fang, VIP, Embase, PubMed, as well as Cochrane library clinical controlled trials. The study was conducted under the PRISMA 2020 criteria. Data were extracted, and quality control was evaluated from the modified Jadad rating scale. Meta-analysis was then undertaken through STATA 16.0 software.

RESULTS

A total of 5 RCTs were obtained, including 1198 patients. Study participants were subdivided into two groups, including the PCI group (n = 604) and the CABG group (n = 594). Meta-analysis of clinical adverse events results showed that the long-term survival results of CAD patients with CKD who underwent PCI were worsened compared to CABG, such as long-term MACCEs (RR = 1.59, 95%CI: 1.04-2.43) and the long-term repeated revascularization (RR = 2.48, 95%CI: 1.76-3.49). Also, cardiac death (RR = 1.68, 95%CI:1.04-2.71), as well as cerebrovascular accident (RR = 1.74, 95%CI:1.04-2.90) in CABG group was significantly lower than that in PCI group.

CONCLUSION

This meta-analysis showed that CABG provided a better therapeutic effect than PCI in CKD patients with CAD when considering long-term prognosis. However, more prospective RCTs are needed to define the proper revascularization strategy for CAD patients with CKD.

Diagnostic efficacy of the triglyceride-glucose index in the prediction of contrast-induced nephropathy following percutaneous coronary intervention

Introduction

Contrast-induced nephropathy (CIN) is a common complication of percutaneous coronary intervention (PCI). Identifying patients at high CIN risk remains challenging. The triglyceride-glucose (TyG) index may help predict CIN but evidence is limited. We conducted a meta-analysis to evaluate the diagnostic value of TyG index for CIN after PCI.

Methods

A systematic literature search was performed in MEDLINE, Cochrane, and EMBASE until August 2023 (PROSPERO registration: CRD42023452257). Observational studies examining TyG index for predicting CIN risk in PCI patients were included. This diagnostic meta-analysis aimed to evaluate the accuracy of the TyG index in predicting the likelihood of CIN. Secondary outcomes aimed to assess the pooled incidence of CIN and the association between an elevated TyG index and the risk of CIN.

Results

Five studies (Turkey, n=2; China, n=3) with 3518 patients (age range: 57.6 to 68.22 years) were included. The pooled incidence of CIN was 15.3% [95% confidence interval (CI) 11-20.8%]. A high TyG index associated with increased CIN risk (odds ratio: 2.25, 95% CI 1.82-2.77). Pooled sensitivity and specificity were 0.77 (95% CI 0.59-0.88) and 0.55 (95% CI 0.43-0.68) respectively. Analysis of the summary receiver operating characteristic (sROC) curve revealed an area under the curve of 0.69 (95% CI 0.65-0.73). There was a low risk of publication bias (p = 0.81).

Conclusion

The TyG index displayed a noteworthy correlation with the risk of CIN subsequent to PCI. However, its overall diagnostic accuracy was found to be moderate in nature. While promising, the TyG index should not be used in isolation for CIN screening given the heterogeneity between studies. In addition, the findings cannot be considered conclusive given the scarcity of data. Further large-scale studies are warranted to validate TyG cutoffs and determine how to optimally incorporate it into current risk prediction models.

Systematic Review Registration

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023452257, identifier CRD42023452257.

Change Management Accompanying Implementation of Decision Support for Prevention of Acute Kidney Injury in Cardiac Catheterization Units: Program Report

Purpose of program

Different models exist to guide successful implementation of electronic health tools into clinical practice. The Contrast Reducing Injury Sustained by Kidneys (Contrast RISK) initiative introduced an electronic decision support tool with physician audit and feedback into all of the cardiac catheterization facilities in Alberta, Canada, with the goal of preventing contrast-associated acute kidney injury (CA-AKI) following coronary angiography and intervention. This report describes the change management approaches used by the initiative and end-user's feedback on these processes.

Sources of information and methods

The Canada Health Infoway Change Management model was used to address 6 activities relevant to project implementation: governance and leadership, stakeholder engagement, communications, workflow analysis and integration, training and education, and monitoring and evaluation. Health care providers and invasive cardiologists from all sites completed preimplementation, usability, and postimplementation surveys to assess integration and change success.

Key findings

Prior to implementation, 67% of health providers were less than satisfied with processes to determine appropriate contrast dye volumes, 47% were less than satisfied with processes for administering adequate intravenous fluids, and 68% were less than satisfied with processes to ensure follow-up of high-risk patients. 48% of invasive cardiologists were less than satisfied with preprocedural identification of patients at risk of acute kidney injury (AKI). Following implementation, there were significant increases among health providers in the odds of satisfaction with processes for identifying those at high risk of AKI (odds ratio [OR] 3.01, 95% confidence interval [CI] 1.36-6.66, P = .007), quantifying the appropriate level of contrast dye for each patient (OR 6.98, 95% CI 3.06-15.91, P < .001), determining the optimal amount of IV fluid for each patient (OR 1.86, 95% CI 0.88-3.91, P = .102), and following up of kidney function of high risk patients (OR 5.49, 95%CI 2.45-12.30, P < .001). There were also significant increases among physicians in the odds of satisfaction with processes for identifying those at high risk of AKI (OR 19.53, 95% CI 3.21-118.76, P = .001), quantifying the appropriate level of contrast dye for each patient (OR 26.35, 95% CI 4.28-162.27, P < .001), and for following-up kidney function of high-risk patients (OR 7.72, 95% CI 1.62-36.84.30, P = .010). Eighty-nine percent of staff perceived the initiative as being successful in changing clinical practices to reduce the risk of CA-AKI. Physicians uniformly agreed that the system was well-integrated into existing workflows, while 42% of health providers also agreed.

Implications

The Canada Health Infoway Change Management model was an effective framework for guiding implementation of an electronic decision support tool and audit and feedback intervention to improve processes for AKI prevention within cardiac catheterization units.

Expression of GRP78 and its copartners in HEK293 and pancreatic cancer cell lines (BxPC-3/PANC-1) exposed to MRI and CT contrast agents

Endoplasmic reticulum (ER) stress-associated chaperones trigger a defense mechanism called as unfolded protein response (UPR) which can manage apoptosis and be determinative in cell fate. Both anticancer drug effects and potential toxicity effects of magnetic resonance imaging (MRI) and computed tomography (CT) contrast agents were aimed to be evaluated. For this purpose, we investigated expression profiles of endoplasmic reticulum stress-associated chaperone molecules in human pancreatic tumor lines BxPC-3 and PANC-1 and control human embryonic kidney cells 293 (HEK293) induced with a variety of gadolinium and iohexol contrast agents. Protein expression levels of ER stress-associated chaperones (master regulator: GRP78/Bip and its copartners: Calnexin, Ero1, PDI, CHOP, IRE1α and PERK) were evaluated with Western blotting. Expression levels at mRNA level were also assessed for GRP78/Bip and CHOP with real-time PCR. Induction of cells was carried out with four different Gd-based contrast agents (GBCAs): (Dotarem, Optimark, Primovist and Gadovist) and two different iohexol agents (Omnipol, Omnipaque). CT contrast agents tested in the study did not result in significant ER stress in HEK293 cells. However, they do not seem to have theranostic potential in pancreas cancer through ER pathway. The potential efficiency of macrocyclic MRI contrast agents to provoke apoptosis via ER stress-associated chaperones in BxPC-3 cells lends credibility for their future theranostic use in pancreas cancer as long as undesired toxicity effects were carefully considered. ER stress markers and/or contrast agents seem to have promising potential to be translated into the clinical practice to manage pancreas cancer progression.

Different hydration methods for the prevention of contrast-induced nephropathy in patients with elective percutaneous coronary intervention: a retrospective study

BACKGROUND

Hydration is currently the main measure to prevent contrast-induced nephropathy (CIN). We aimed to compare the preventive effect of preprocedure and postprocedure hydration on CIN in patients with coronary heart disease undergoing elective percutaneous coronary intervention (PCI).

METHODS

A retrospective study included 198 cases of postprocedure hydration and 396 cases of preprocedure hydration using propensity score matching. The incidence of CIN 48 h after PCI and adverse events within 30 days after contrast media exposure were compared between the two groups. Logistic regression analysis was used to analyse the risk factors for CIN.

RESULTS

The incidence of CIN in the postprocedure hydration group was 3.54%, while that in the preprocedure hydration group was 4.8%. There was no significant difference between the two groups (p = 0.478). Multivariate logistic regression analysis showed that diabetes mellitus, baseline BNP and cystatin C levels, and contrast agent dosage were independent risk factors for CIN. There was no significant difference in the incidence of major adverse events between the two groups (3.03% vs. 2.02%, p = 0.830).

CONCLUSIONS

Postprocedure hydration is equally effective compared to preoperative hydration in the prevention of CIN in patients with coronary heart disease undergoing elective PCI.

Pharmacist-led iodinated contrast media infusion risk assessment service

Background: With the increasing development of medical imaging, the use of iodinated contrast media has become more widespread. Adverse reactions caused by iodinated contrast media have drawn much attention. Despite this, there is still a lack of unified standards for the safe infusion process of iodinated contrast media in clinical practice both domestically and internationally. Objectives: Establishing a risk management service system to better predict the risks associated with iodinated contrast media infusion, reduce the incidence of adverse reactions and minimize patient harm. Method: A prospective interventional study was carried out from April 2021 to December 2021 at Nanjing Drum Tower Hospital in China. During this study, a service system was established to manage the risks associated with the infusion of iodinated contrast media. Personalized risk identification and assessment were performed by a pharmacist-led multidisciplinary team before iodinated contrast media infusion. Early warning, prevention, and adverse reaction management were performed according to different risk levels during and after infusion. Results: A multidisciplinary team led by pharmacists was established to evaluate the risks associated with infusion of iodinated contrast media. A total of 157 patients with risk factors related to the iodinated contrast media were screened out, which prevented 22 serious adverse events and enhanced the quality of medical care. All participants expressed high satisfaction with the service. Conclusion: Through practical exploration, the pharmacist-led multidisciplinary team can provide advance warning and effectively limit the risks of adverse reactions caused by iodinated contrast media to a preventable and controllable level. This approach serves as a valuable reference for developing strategies and schemes to reduce the incidence of such reactions. Therefore, we encourage the implementation of this intervention in other areas of China.

Characterization of Risk Prediction Models for Acute Kidney Injury: A Systematic Review and Meta-analysis

Importance

Despite the expansion of published prediction models for acute kidney injury (AKI), there is little evidence of uptake of these models beyond their local derivation nor data on their association with patient outcomes.

Objective

To systematically review published AKI prediction models across all clinical subsettings.

Data Sources

MEDLINE via PubMed (January 1946 to April 2021) and Embase (January 1947 to April 2021) were searched using medical subject headings and text words related to AKI and prediction models.

Study Selection

All studies that developed a prediction model for AKI, defined as a statistical model with at least 2 predictive variables to estimate future occurrence of AKI, were eligible for inclusion. There was no limitation on study populations or methodological designs.

Data Extraction and Synthesis

Two authors independently searched the literature, screened the studies, and extracted and analyzed the data following the Preferred Reporting Items for Systematic Review and Meta-analyses guideline. The data were pooled using a random-effects model, with subgroups defined by 4 clinical settings. Between-study heterogeneity was explored using multiple methods, and funnel plot analysis was used to identify publication bias.

Main Outcomes and Measures

C statistic was used to measure the discrimination of prediction models.

Results

Of the 6955 studies initially identified through literature searching, 150 studies, with 14.4 million participants, met the inclusion criteria. The study characteristics differed widely in design, population, AKI definition, and model performance assessments. The overall pooled C statistic was 0.80 (95% CI, 0.79-0.81), with pooled C statistics in different clinical subsettings ranging from 0.78 (95% CI, 0.75-0.80) to 0.82 (95% CI, 0.78-0.86). Between-study heterogeneity was high overall and in the different clinical settings (eg, contrast medium-associated AKI: I2 = 99.9%; P < .001), and multiple methods did not identify any clear sources. A high proportion of models had a high risk of bias (126 [84.4%]) according to the Prediction Model Risk Of Bias Assessment Tool.

Conclusions and Relevance

In this study, the discrimination of the published AKI prediction models was good, reflected by high C statistics; however, the wide variation in the clinical settings, populations, and predictive variables likely drives the highly heterogenous findings that limit clinical utility. Standardized procedures for development and validation of prediction models are urgently needed.

A Predictive Model for Contrast-Induced Acute Kidney Injury After Percutaneous Coronary Intervention in Elderly Patients with ST-Segment Elevation Myocardial Infarction

Purpose

Development and validation of a nomogram model to predict the risk of Contrast-Induced Acute Kidney Injury (CI-AKI) after emergency percutaneous coronary intervention (PCI) in elderly patients with acute ST-segment elevation myocardial infarction (STEMI).

Patients and Methods

Retrospective analysis of 542 elderly (≥65 years) STEMI patients undergoing emergency PCI in our hospital from January 2019 to June 2022, with all patients randomized to the training cohort (70%; n=380) and the validation cohort (30%; n=162). Univariate analysis, LASSO regression, and multivariate logistic regression analysis were used to determine independent risk factors for developing CI-AKI in elderly STEMI patients. R software is used to generate a nomogram model. The predictive power of the nomogram model was compared with the Mehran score 2. The area under the ROC curve (AUC), calibration curves, and decision curve analysis (DCA) was used to evaluate the prediction model's discrimination, calibration, and clinical validity, respectively.

Results

The nomogram model consisted of five variables: diabetes mellitus (DM), left ventricular ejection fraction (LVEF), Systemic immune-inflammatory index (SII), N-terminal pro-brain natriuretic peptide (NT-proBNP), and highly sensitive C-reactive protein(hsCRP). In the training cohort, the AUC is 0.84 (95% CI: 0.790-0.890), and in the validation cohort, it is 0.844 (95% CI: 0.762-0.926). The nomogram model has better predictive ability than Mehran score 2. Based on the calibration curves, the predicted and observed values of the nomogram model were in good agreement between the training and validation cohort. Decision curve analysis (DCA) and clinical impact curve showed that the nomogram prediction model has good clinical utility.

Conclusion

The established nomogram model can intuitively and specifically screen high-risk groups with a high degree of discrimination and accuracy and has a specific predictive value for CI-AKI occurrence in elderly STEMI patients after PCI.

Association between uric acid level and contrast-induced acute kidney injury in patients with type 2 diabetes mellitus after coronary angiography: a retrospective cohort study

BACKGROUND

This study assessed the predictive value of uric acid (UA) for contrast-induced acute kidney injury (CI-AKI) in patients with type 2 diabetes mellitus (T2DM) who underwent coronary angiography (CAG). A nomogram to aid in the prediction of CI-AKI was also developed and validated, and the construction of a prognostic nomogram combined with clinical features was attempted.

METHODS

This study retrospectively enrolled T2DM patients who underwent CAG between December 2019 and December 2020 at the Affiliated Zhongda Hospital of Southeast University. Multivariable logistic regression analysis was used for the analysis of clinical outcomes. Receiver operating characteristic (ROC) analyses were performed to determine the area under the ROC curve (AUC) and the cut-off points for continuous clinical data. The prediction accuracies of models for CI-AKI were estimated through Harrell's concordance indices (C-index). Nomograms of the prognostic models were plotted for individualized evaluations of CI-AKI in T2DM patients after CAG.

RESULTS

A total of 542 patients with T2DM who underwent CAG were included in this study. We found that a high UA level (≥ 425.5 µmol/L; OR = 6.303), BUN level (≥ 5.98 mmol/L; OR = 3.633), Scr level (≥ 88.5 µmol/L; OR = 2.926) and HbA1C level (≥ 7.05%; OR = 5.509) were independent factors for CI-AKI in T2DM patients after CAG. The nomogram model based on UA, BUN, Scr and HbA1C levels presented outstanding performance for CI-AKI prediction (C-index: 0.878). Decision curve analysis (DCA) showed good clinical applicability in predicting the incidence of CI-AKI in T2DM patients who underwent CAG.

CONCLUSION

High UA levels are associated with an increased incidence of CI-AKI in T2DM patients after CAG. The developed nomogram model has potential predictive value for CI-AKI and might serve as an economic and efficient prognostic tool in clinical practice.

Internal and external validation of machine learning-assisted prediction models for mechanical ventilation-associated severe acute kidney injury

BACKGROUND

Currently, very few preventive or therapeutic strategies are used for mechanical ventilation (MV)-associated severe acute kidney injury (AKI).

OBJECTIVES

We developed clinical prediction models to detect the onset of severe AKI in the first week of intensive care unit (ICU) stay during the initiation of MV.

METHODS

A large ICU database Medical Information Mart for Intensive Care IV (MIMIC-IV) was analysed retrospectively. Data were collected from the clinical information recorded at the time of ICU admission and during the initial 12 h of MV. Using univariate and multivariate analyses, the predictors were selected successively. For model development, two machine learning algorithms were compared. The primary goal was to predict the development of AKI stage 2 or 3 (AKI-23) and AKI stage 3 (AKI-3) in the first week of patients' ICU stay after initial 12 h of MV. The developed models were externally validated using another multicentre ICU database (eICU Collaborative Research Database, eICU) and evaluated in various patient subpopulations.

RESULTS

Models were developed using data from the development cohort (MIMIC-IV: 2008-2016; n = 3986); the random forest algorithm outperformed the logistic regression algorithm. In the internal (MIMIC-IV: 2017-2019; n = 1210) and external (eICU; n = 1494) validation cohorts, the incidences of AKI-23 were 154 (12.7%) and 119 (8.0%), respectively, with areas under the receiver operator characteristic curve of 0.78 (95% confidence interval [CI]: 0.74-0.82) and 0.80 (95% CI: 0.76-0.84); the incidences of AKI-3 were 81 (6.7%) and 67 (4.5%), with areas under the receiver operator characteristic curve of 0.81 (95% CI: 0.76-0.87) and 0.80 (95% CI: 0.73-0.86), respectively.

CONCLUSIONS

Models driven by machine learning and based on routine clinical data may facilitate the early prediction of MV-associated severe AKI. The validated models can be found at: https://apoet.shinyapps.io/mv_aki_2021_v2/.

Predictive value of two different definitions of contrast-associated acute kidney injury for long-term major adverse kidney events in patients with ST-segment elevation myocardial infarction undergoing primary percutaneous coronary intervention

BACKGROUND

It remains controversial whether contrast-associated acute kidney injury (CA-AKI) is associated with long-term major adverse kidney events (MAKE) in patients with ST-segment elevation myocardial infarction (STEMI) undergoing primary percutaneous coronary intervention (PCI).

METHODS

By the Acute Kidney Injury Network (AKIN) criteria, CA-AKI was defined as an increase in serum creatinine ≥ 0.3 mg/dL or 50% from baseline within 48 h after PCI; or an increase in serum creatinine ≥ 0.5 mg/dL or 25% within 72 h by the contrast-induced nephropathy (CIN) criteria. The primary endpoint was 1-year MAKE, defined as a composite of all-cause mortality and persistent renal dysfunction.

RESULTS

A total of 402 patients were finally included in this study. The primary endpoint occurred in 29 (7.2%) patients. There was a significant association between CA-AKI and 1-year MAKE assessed by both the AKIN (hazard ratios [HR]: 11.58, 95% confidence interval [CI]: 4.29-31.24, p = 0.000) and CIN (HR: 6.45, 95% CI: 2.56-16.25, p = 0.000) definitions. However, the AKIN definition (HR: 4.95, 95% CI: 1.17-21.02, p = 0.030) was more reliable in the prediction of persistent renal dysfunction than CIN definition (HR: 4.08, 95% CI: 0.99-16.87, p = 0.052). Additionally, the area under receiver operating characteristic curve was larger for predicting 1-year MAKE with the AKIN definition than CIN definition (0.742 vs. 0.727).

CONCLUSIONS

In patients with STEMI undergoing primary PCI, CA-AKI was significantly associated with 1-year MAKE. Moreover, the AKIN definition might be more reliable in the prediction of long-term prognosis.

Development and validation of an interpretable clinical score for early identification of acute kidney injury at the emergency department

Acute kidney injury (AKI) in hospitalised patients is a common syndrome associated with poorer patient outcomes. Clinical risk scores can be used for the early identification of patients at risk of AKI. We conducted a retrospective study using electronic health records of Singapore General Hospital emergency department patients who were admitted from 2008 to 2016. The primary outcome was inpatient AKI of any stage within 7 days of admission based on the Kidney Disease Improving Global Outcome (KDIGO) 2012 guidelines. A machine learning-based framework AutoScore was used to generate clinical scores from the study sample which was randomly divided into training, validation and testing cohorts. Model performance was evaluated using area under the curve (AUC). Among the 119,468 admissions, 10,693 (9.0%) developed AKI. 8491 were stage 1 (79.4%), 906 stage 2 (8.5%) and 1296 stage 3 (12.1%). The AKI Risk Score (AKI-RiSc) was a summation of the integer scores of 6 variables: serum creatinine, serum bicarbonate, pulse, systolic blood pressure, diastolic blood pressure, and age. AUC of AKI-RiSc was 0.730 (95% CI 0.714–0.747), outperforming an existing AKI Prediction Score model which achieved AUC of 0.665 (95% CI 0.646–0.679) on the testing cohort. At a cut-off of 4 points, AKI-RiSc had a sensitivity of 82.6% and specificity of 46.7%. AKI-RiSc is a simple clinical score that can be easily implemented on the ground for early identification of AKI and potentially be applied in international settings.

Contrast-Associated Acute Kidney Injury

Contrast-associated acute kidney injury (CA-AKI) is an impairment of renal function, which occurs within days of intravascular administration of iodinated contrast media. Taking into account that minimally invasive cardiac interventions are becoming increasingly popular, compared to traditional surgery, given their impact on prognosis and costs, CA-AKI remains a subject of increasing interest for patients and physicians. This review summarizes the epidemiology and risk stratification, diagnostic criteria, pathophysiology and clinical implications of CA-AKI, providing evidence for the most studied preventive strategies.

Systemic Immune-Inflammation Index Predicts Contrast-Induced Acute Kidney Injury in Patients Undergoing Coronary Angiography: A Cross-Sectional Study

Background and Aims

Systemic immune-inflammation index (SII) is an emerging indicator and correlated to the incidence of cardiovascular diseases. This study aimed to explore the association between SII and contrast-induced acute kidney injury (CI-AKI).

Methods

In this retrospective cross-sectional study, 4,381 subjects undergoing coronary angiography (CAG) were included. SII is defined as neutrophil count × platelet count/lymphocyte count. CI-AKI was determined by the elevation of serum creatinine (Scr). Multivariable linear and logistic regression analysis were used to determine the relationship of SII with Scr and CI-AKI, respectively. Receiver operator characteristic (ROC) analysis, structural equation model analysis, and subgroup analysis were also performed.

Results

Overall, 786 (17.9%) patients suffered CI-AKI after the intravascular contrast administration. The subjects were 67.1 ± 10.8 years wold, with a mean SII of 5.72 × 10¹¹/L. Multivariable linear regression analysis showed that SII linearly increased with the proportion of Scr elevation (β [95% confidence interval, CI] = 0.315 [0.206 to 0.424], P < 0.001). Multivariable logistic regression analysis demonstrated that higher SII was associated with an increased incidence of CI-AKI ([≥12 vs. <3 × 10¹¹/L]: odds ratio, OR [95% CI] = 2.914 [2.121 to 4.003], P < 0.001). Subgroup analysis showed consistent results. ROC analysis identified a good predictive value of SII on CI-AKI (area under the ROC curve [95% CI]: 0.625 [0.602 to 0.647]). The structural equation model verified a more remarkable direct effect of SII (β = 0.102, P < 0.001) on CI-AKI compared to C-reactive protein (β = 0.070, P < 0.001).

Conclusions

SII is an independent predictor for CI-AKI in patients undergoing CAG procedures.

Risk factors for acute renal injury caused by contrast media after percutaneous coronary intervention and coronary angiography: A protocol for systematic review and meta-analysis

BACKGROUND

Contrast-induced acute kidney injury (CI-AKI) caused by contrast medium is one of the common complications of percutaneous coronary intervention (PCI)/coronary angiography (CAG). Early identification of the risk factors of CI-AKI in patients with PCI/CAG and help clinical staff to prevent and intervene as soon as possible is very important to improve the clinical outcome of patients. Although domestic and foreign scholars have studied and summarized the risk factors of CI-AKI in PCI/CAG, the conclusions are not the same. Therefore, in this study, meta-analysis was used to summarize the risk factors of CI-AKI in patients with PCI/CAG, and to explore the characteristics of high-risk groups of CI-AKI, to provide reference for early identification and prevention of clinical doctors and nurses.

METHODS

We will search related literature of PubMed, Embase, Cochrane Library, Web of Science, China Biology Medicine Database, China National Knowledge Infrastructure, China Science and Technology Journal Database, and Wanfang Database. Eligible studies will be screened based on inclusion criteria, and data extraction, risk of bias assessment, publication bias assessment, subgroup analysis, and quality assessment will be performed. Review Manager version 5.3 software will be used for data analysis. Each process is independently conducted by 2 researchers, and if there is any objection, it will be submitted to the third researcher for resolution.

RESULTS

We will disseminate the findings of this systematic review and meta-analysis via publications in peer-reviewed journals.

CONCLUSIONS

The results of this analysis can be used to generate a risk prediction model and provide an intervention strategy for the occurrence of CI-AKI in PCI/CAG.

Clinical Utility of a Biomarker to Detect Contrast-Induced Acute Kidney Injury during Percutaneous Cardiovascular Procedures

INTRODUCTION

Contrast-induced acute kidney injury (CI-AKI) is a major clinical complication of percutaneous cardiovascular procedures requiring iodinated contrast. Despite its relative frequency, practicing physicians are unlikely to identify or treat this condition.

METHODS

In a 2-round clinical trial of simulated patients, we examined the clinical utility of a urine-based assay that measures liver-type fatty acid-binding protein (L-FABP), a novel marker of CI-AKI. We sought to determine if interventional cardiologists' ability to diagnose and treat potential CI-AKI improved using the biomarker assay for 3 different patient types: pre-procedure, peri-procedure, and post-procedure patients.

RESULTS

154 participating cardiologists were randomly divided into either control or intervention. At baseline, we found no difference in the demographics or how they identified and treated potential complications of AKI, with both groups providing less than half the necessary care to their patients (46.4% for control vs. 47.6% for intervention, p = 0.250). The introduction of L-FABP into patient care resulted in a statistically significant improvement of 4.6% (p = 0.001). Compared to controls, physicians receiving L-FABP results were 2.9 times more likely to correctly identify their patients' risk for AKI (95% CI 2.1-4.0) and were more than twice as likely to treat for AKI by providing volume expansion and withholding nephrotoxic medications. We found the greatest clinical utility in the pre-procedure and peri-procedure settings but limited value in the post-procedure setting.

CONCLUSION

This study suggests L-FABP as a clinical marker for assessing the risk of potential CI-AKI, has clinical utility, and can lead to more accurate diagnosis and treatment.

Mehran 2 Contrast-Associated Acute Kidney Injury Risk Score: Is it Applicable to the Asian Percutaneous Coronary Intervention Population?

Contrast-associated acute kidney injury (CA-AKI) can occur after percutaneous coronary intervention (PCI). The Mehran score is the gold standard for predicting CA-AKI risk, and it has recently been updated. The Mehran 2 CA-AKI risk score, based on existing variables in patients undergoing PCI, can accurately differentiate the risk of CA-AKI. This study aimed to verify whether the new Mehran score is applicable to the Asian PCI population. The study included the clinical data of 2487 patients undergoing PCI from August 2020 to February 2022. The goodness-of-fit test (Hosmer-Lemeshow) was used to evaluate the correction ability of the Mehran 2 score, and the area under the receiver operating characteristic curve (ROC) was used to evaluate the accuracy of the Mehran 2 score in predicting CA-AKI. CA-AKI occurred in 28 of 2487 patients, with an incidence rate of 1.12%. The proportion of high risk factors for AKI in the cohort was lower than that in the Mehran 2 cohort (a large contemporary PCI cohort to develop the Mehran 2 score). The Mehran 2 risk score had excellent goodness-of-fit (χ2 = 5.320, df = 6, P = 0.503) and high predictive accuracy (area under the ROC curve 0.836, P < 0.0001). The Mehran 2 score shows good predictive and correction performance in the Asian population and has good clinical application value. The inclusion of the Mehran 2 risk score in patients hospitalised for coronary angiography appears to be good practice.

Development and Validation of a Risk Nomogram Model for Predicting Contrast-Induced Acute Kidney Injury in Patients with Non-ST-Elevation Acute Coronary Syndrome Undergoing Primary Percutaneous Coronary Intervention

Objective

To establish a nomogram model to predict the risk of contrast-induced acute kidney injury (CI-AKI) by analyzing the risk factors of CI-AKI and to evaluate its effectiveness.

Methods

Retrospectively analyze the clinical data of non-ST-elevation acute coronary syndrome (NSTE-ACS) patients who underwent percutaneous coronary intervention (PCI) in our cardiology department from September 2018 to June 2021. Of these, patients who underwent PCI in an earlier period formed the training cohort (70%; n = 809) for nomogram development, and those who underwent PCI thereafter formed the validation cohort (30%; n = 347) to confirm the model’s performance. The independent risk factors of CI-AKI were determined by LASSO regression and multivariable logistic regression analysis. By using R software from which nomogram models were subsequently generated. The nomogram was developed and evaluated based on discrimination, calibration, and clinical efficacy using the concordance statistic (C-statistic), calibration plot, and decision curve analysis (DCA), respectively.

Results

The nomogram consisted of six variables: age >75, left ventricular ejection fraction, diabetes mellitus, fibrinogen-to-albumin ratio, high-sensitive C-reactive protein, and lymphocyte count. The C-index of the nomogram is 0.835 (95% CI: 0.800–0.871) in the training cohort and 0.767 (95% CI: 0.711–0.824) in the validation cohort, respectively. The calibration plots exhibited that the nomogram was in good agreement between prediction and observation in the training and validation cohorts. Decision curve analysis and clinical impact curve suggested that the predictive nomogram had clinical utility.

Conclusion

The nomogram model established has a good degree of differentiation and accuracy, which is intuitively and individually to screen high-risk groups and has a certain predictive value for the occurrence of CI-AKI in NSTE-ACS patients after PCI.

Predictive value of plasma volume status for contrast-induced nephropathy in patients with heart failure undergoing PCI

Aims

Contrast‐induced nephropathy remains a common complication of coronary procedure and increases poor outcomes, especially in patients with heart failure. Plasma volume expansion relates to worsening prognosis of heart failure. We hypothesized that calculated plasma volume status (PVS) might provide predictive utility for contrast‐induced nephropathy in patients with heart failure undergoing elective percutaneous coronary intervention (PCI).

Methods and results

We enrolled 441 patients with heart failure undergoing elective PCI from 2012 to 2018. Pre‐procedural estimated PVS by the Duarte's formula (Duarte‐ePVS) and Kaplan–Hakim formula (KH‐ePVS) were calculated for all patients. CIN was defined as an absolute serum creatinine (SCr) increase ≥0.5 mg/dL or a relative increase ≥25% compared with the baseline value within 48 h of contrast medium exposure. We assessed the association between PVS and CIN in patients with heart failure undergoing elective PCI. In 441 patients, 28 (6.3%) patients developed CIN. The median Duarte‐ePVS was 4.44 (3.87, 5.13) and the median KH‐ePVS was −0.03 (−0.09, 0.05). The best cutoff values for Duarte‐ePVS and KH‐ePVS to predict CIN were 4.64 (with 78.6% sensitivity and 61.7% specificity) and 0.04 (with 64.5% sensitivity and 75.5% specificity), respectively. After adjusting for potential confounding variables, KH‐ePVS > 0.04 [odds ratio (OR) 2.685, 95% confidence interval (CI) 1.012–7.123, P = 0.047] remained significantly associated with CIN whereas Duarte‐ePVS was not.

Conclusions

Pre‐procedural KH‐ePVS is an independent risk factor for CIN in patients with heart failure undergoing elective PCI. The best cutoff point of KH‐ePVS for predicting CIN was 0.04.

Albuminuria Pre-Emptively Identifies Cardiac Patients at Risk of Contrast-Induced Nephropathy

Contrast-induced nephropathy (CIN) is a complication associated with the administration of contrast media (CM). The CIN diagnosis is based on creatinine, a biomarker late and insensitive. The objective proposed was to evaluate the ability of novel biomarkers to detect patients susceptible to suffering CIN before CM administration. The study was carried out with patients undergoing cardiac catheterization involving CM. Patients were divided into two groups: (1) CIN, patients who developed this pathology; (2) control, patients who did not suffer CIN. Prior to the administration of CM, urine samples were collected to measure proteinuria, N-acetyl-β-d-glucosaminidase, neutrophil gelatinase-associated lipocalin and kidney injury molecule-1, albumin, transferrin, t-gelsolin and GM2 ganglioside activator protein (GM2AP). The risk factors advanced age, low body mass index and low estimated glomerular filtration rate; and the urinary biomarkers albumin, transferrin and GM2AP showed significant predictive capacity. Of all of them, albuminuria demonstrated the highest diagnostic power. When a cutoff point was established for albuminuria at values still considered subclinical (10–30 µg/mg Cr_u), it was found that there was a high incidence of CIN (40–75%). Therefore, albuminuria could be applied as a new diagnostic tool to prevent and predict CIN with P4 medicine criteria, independently of risk factors and comorbidities.

The relationship between pre-procedural elevated arterial lactate and contrast-induced nephropathy following primary percutaneous coronary intervention

Background

Risk stratification has been one of the main steps in preventing contrast-induced nephropathy (CIN), which is a common complication after percutaneous coronary intervention (PCI). Elevated arterial lactate is a biomarker indicating severe disease condition and post-intervention complications. The relationship between lactate and CIN has not been established. This study is performed to investigate the relationship between elevated arterial lactate level and contrast-induced nephropathy (CIN).

Methods

Patients diagnosed with ST-segment elevated myocardial infarction (STEMI) were prospectively enrolled, with lactate measured within 0.5–1 hours before primary percutaneous coronary intervention (PCI). Patients with cardiopulmonary resuscitation, any forms of severe anaerobic condition, or end-stage renal disease undergoing dialysis were excluded. CIN was defined as an increase in serum creatinine ≥0.5 mg/dL or 25% within 72 hours after PCI. The Mehran Risk Score (MRS) is widely regarded as a classic risk model for CIN and the risk factors of MRS were applied in our multivariate regression analysis.

Results

Of the 227 enrolled patients, 47 (20.7%) developed CIN according to the definition. The mean lactate level was higher in the CIN group than in the non-CIN group (2.68±2.27 vs. 1.74±1.94, P<0.001). The arterial lactate level ≥2.0 mmol/L had 57.5% sensitivity and 75.6% specificity in predicting CIN. The performance of the lactate level in discriminating CIN was similar to that of the MRS (AUC_lac =0.707 vs. AUC_MRS =0.697, P=0.86). After adjusting for other risk factors, lactate ≥2.0 mmol/L still significantly predicted CIN (odds ratio =3.77, 95% CI, 1.77–7.99, P=0.001).

Conclusions

An arterial lactate level of ≥2.0 mmol/L is associated with CIN in STEMI patients after primary PCI.

Clinical usefulness of prediction tools to identify adult hospitalized patients at risk of drug-related problems: A systematic review of clinical prediction models and risk assessment tools

AIMS

This study aimed to review systematically all available prediction tools identifying adult hospitalized patients at risk of drug-related problems, and to synthesize the evidence on performance and clinical usefulness.

METHODS

PubMed, Scopus, Web of Science, Embase, and CINAHL databases were searched for relevant studies. Titles, abstracts and full-text studies were sequentially screened for inclusion by two independent reviewers. The Prediction Model Risk of Bias Assessment Tool (PROBAST) and the Revised Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) checklists were used to assess risk of bias and applicability of prediction tools. A narrative synthesis was performed.

RESULTS

A total of 21 studies were included, 14 of which described the development of new prediction tools (four risk assessment tools and ten clinical prediction models) and six studies were validation based and one an impact study. There were variations in tool development processes, outcome measures and included predictors. Overall, tool performance had limitations in reporting and consistency, with the discriminatory ability based on area under the curve receiver operating characteristics (AUROC) ranging from poor to good (0.62-0.81), sensitivity and specificity ranging from 57.0% to 89.9% and 30.2% to 88.0%, respectively. The Medicines Optimisation Assessment tool and Assessment of Risk tool were prediction tools with the lowest risk of bias and low concern for applicability. Studies reporting external validation and impact on patient outcomes were scarce.

CONCLUSION

Most prediction tools have limitations in development and validation processes, as well as scarce evidence of clinical usefulness. Future studies should attempt to either refine currently available tools or apply a rigorous process capturing evidence of acceptance, usefulness, performance and outcomes.

Use of Deep Learning to Predict Acute Kidney Injury After Intravenous Contrast Media Administration: Prediction Model Development Study

Background

Precise prediction of contrast media–induced acute kidney injury (CIAKI) is an important issue because of its relationship with poor outcomes.

Objective

Herein, we examined whether a deep learning algorithm could predict the risk of intravenous CIAKI better than other machine learning and logistic regression models in patients undergoing computed tomography (CT).

Methods

A total of 14,185 patients who were administered intravenous contrast media for CT at the preventive and monitoring facility in Seoul National University Hospital were reviewed. CIAKI was defined as an increase in serum creatinine of ≥0.3 mg/dL within 2 days or ≥50% within 7 days. Using both time-varying and time-invariant features, machine learning models, such as the recurrent neural network (RNN), light gradient boosting machine (LGM), extreme gradient boosting machine (XGB), random forest (RF), decision tree (DT), support vector machine (SVM), κ-nearest neighbors, and logistic regression, were developed using a training set, and their performance was compared using the area under the receiver operating characteristic curve (AUROC) in a test set.

Results

CIAKI developed in 261 cases (1.8%). The RNN model had the highest AUROC of 0.755 (0.708-0.802) for predicting CIAKI, which was superior to that obtained from other machine learning models. Although CIAKI was defined as an increase in serum creatinine of ≥0.5 mg/dL or ≥25% within 3 days, the highest performance was achieved in the RNN model with an AUROC of 0.716 (95% confidence interval [CI] 0.664-0.768). In feature ranking analysis, the albumin level was the most highly contributing factor to RNN performance, followed by time-varying kidney function.

Conclusions

Application of a deep learning algorithm improves the predictability of intravenous CIAKI after CT, representing a basis for future clinical alarming and preventive systems.

Development and Evaluation of an Audit and Feedback Process for Prevention of Acute Kidney Injury During Coronary Angiography and Intervention

Background

Contrast-associated acute kidney injury (CA-AKI) is a potentially preventable complication of coronary angiography and intervention. Relatively little research has been done to determine how knowledge on CA-AKI prevention can be translated into clinical practice.

Methods

We developed, implemented, and surveyed end-users about the usability, acceptability, and utility of an audit and feedback process for CA-AKI prevention in Alberta, Canada. The audit and feedback reported on amount of radiocontrast dye used, hemodynamic optimization of intravenous fluids, and CA-AKI incidence for each cardiologist practicing coronary angiography or percutaneous coronary intervention, compared with peers at their site and across the province. Reports were developed through an iterative process involving interventional cardiologists throughout the design process and usability testing.

Results

Cardiologists participating in usability testing indicated a preference for the visual displays of data and summarizing indicators on the front page, and endorsed the value of peer-to-peer comparisons of performance measures. Of 31 eligible cardiologists from across Alberta, 17 responded to a survey evaluating the audit and feedback process. Fifteen respondents (88.2%) agreed that the data presented in the audit and feedback report were understandable; 17 respondents (100%) agreed or strongly agreed that the presentation of the report helped them better understand their performance compared with that of their peers; and 14 (82.4%) agreed that the audit and feedback process helped them identify ways to reduce the risk of AKI for their patients.

Conclusions

Conducting an audit and providing feedback was an understandable and acceptable intervention to help cardiologists identify ways to improve prevention of CA-AKI during coronary angiography or intervention.

Safe Limits of Contrast Media for Contrast-Induced Nephropathy: A Multicenter Prospective Cohort Study

Background: The safe level of contrast media volume (CV) is an important modifiable risk factor for contrast-induced nephropathy (CIN). The safe limit of CV remains unclear and is limited to single-center studies. Our objective was to determine the association between the ratio of contrast volume-to-glomerular filtration (CV/GFR) and CIN in patients undergoing coronary angiography (CAG) or percutaneous coronary intervention (PCI). Methods: We assessed the association between CV/GFR and the risk of CIN in 4,254 patients undergoing CAG or PCI from the year 2013 to 2016 and enrolled in the REICIN (REduction of rIsk for Contrast-Induced Nephropathy), a prospective, multicenter, observational cohort study. CV/GFR was calculated at the five primary GFR equation. Results: Sixty-nine (1.7%) patients with a median contrast volume-to-chronic kidney disease epidemiology collaboration (CV/CKD-EPI) ratio of 2.16 (1.30-3.93) have suffered from CIN. The CV/CKD-EPI demonstrated the best performance of model fit, discrimination (area under curve = 0.736), calibration, reclassification, and equation conciseness (1 variable). The CV/CKD-EPI ≥1.78 was the statistical significance associated with CIN [adjusted odds ratio, 4.64 (2.84-7.56); p < 0.001]. Furthermore, similar results were found in the subgroup analyses. Conclusions: The CV/CKD-EPI showed the best performance in patients undergoing CAG or PCI. CV/CKD-EPI ≥1.78 could be a more reliable and convenient predictor of CIN. Intraprocedural preventive measures should include a priori calculation of CV/GFR to limit contrast volume.

Acute Kidney Injury Following Percutaneous Coronary Intervention for Acute Coronary Syndrome: Incidence, Aetiology, Risk Factors and Outcomes

We investigated the predictors, aetiology and long-term outcomes of acute kidney injury (AKI) following urgent percutaneous coronary intervention (PCI) for acute coronary syndrome (ACS). Acute kidney injury occurred in 198 (7.2%) of 2917 patients: 14.1% of AKI cases were attributed to cardiogenic shock and 5.1% were classified as atheroembolic renal disease (AERD). Significant risk factors for AKI included age (odds ratio [OR] 1.05, 95% confidence limits [CI] 1.03-1.06), diabetes (OR 1.73, 95% CI 1.20-2.47), hypertension (OR 1.43, 95% CI 1.03-2.00), heart failure (OR 3.01, 95% CI 1.58-5.57), femoral access (OR 1.50, 95% CI 1.03-2.15), cardiogenic shock (OR 2.03, 95% CI 1.19-3.37) and ST-elevation myocardial infarction (STEMI) (OR 3.89, 95% CI 2.80-5.47). One-year mortality after AERD was 44.4% and renal replacement therapy (RRT) requirement 22.2% (compared with mortality 33.3% and RRT requirement 7.4%, respectively, in all other AKI patients). Mortality at 1 year was associated with AKI (OR 4.33, 95% CI 2.89-6.43), age (OR 1.08, 95% CI 1.06-1.09), heart failure (OR 1.92, 95% CI 1.05-3.44), femoral access (OR 2.05, 95% CI 1.41-2.95) and cardiogenic shock (OR 3.63, 95% CI 2.26-5.77). Acute kidney injury after urgent PCI is strongly associated with worse outcomes. Atheroembolic renal disease has a poor outcome and a high likelihood of long-term RRT requirement.

A preprocedural risk score predicts acute kidney injury following primary percutaneous coronary intervention

BACKGROUND

Reliable preprocedural risk scores for the prediction of Contrast-Induced Acute Kidney Injury (CI-AKI) following Percutaneous Coronary Intervention (pPCI) in patients with ST-elevation myocardial infarction (STEMI) are lacking. Aim of this study was to derive and validate a preprocedural Risk Score in this setting.

METHODS

Two prospectively enrolled patient cohorts were used for derivation and validation (n = 3,736). CI-AKI was defined as creatinine increase ≥0.5 mg/dl <72 h postpPCI. Odds ratios from multivariable logistic regression model were converted to an integer, whose sum represented the Risk Score.

RESULTS

Independent CI-AKI predictors were: diabetes, Killip class II-III (2 points each), age > 75 years, anterior MI (3 points), Killip class IV (4 points), estimated GFR < 60 ml/min/1.73m² (5 points). The Risk Score c-statistic was 0.84 in both cohorts. Compared with patients with Risk Score ≤ 4, the relative risks of CI-AKI among patients scoring 5-9 were 6.2 (derivation cohort) and 7.1 (validation cohort); among patients scoring ≥10, 19.8, and 21.4, respectively.

CONCLUSIONS

Among STEMI patients, a simple preprocedural Risk Score accurately and reproducibly predicted the risk of CI-AKI, identifying ¼ of patients with a seven-fold risk and 1/10 of patients with a 20-fold risk. This knowledge may help tailored strategies, including delaying revascularization of nonculprit vessels in patients at high risk of CI-AKI.

Creatinine level variation in patients subjected to contrast-enhanced tomography: a meta-analysis

Variation in the creatinine levels of patients who have undergone contrast-enhanced computed tomography (CT) has been adopted as a practical method for assessment of possible kidney damage caused by the contrast. Criteria employed include an absolute increase in serum creatinine ≥ 0.5 mg/dL or a relative increase ≥ 25% as indicative of possible renal disorders, such as contrast-induced nephropathy (CIN). Our objective was to analyze the incidence of CIN by means of a meta-analysis of nine articles related to incidence of kidney damage caused by contrast, calculating odds ratios (OR) and confidence intervals (95%CI) using RStudio. The overall incidence of CIN in patients who had CT scans was 11.29%, with an OR of 1.38 (95%CI 0.88–2.16). Non-ionic contrasts are safer than other types of contrast, and volumes exceeding 115 mL may be associated with CIN. Preexisting kidney disease had a statistically significant relationship with worse CIN rates.

The importance of the urinary output criterion for the detection and prognostic meaning of AKI

Most reports on AKI claim to use KDIGO guidelines but fail to include the urinary output (UO) criterion in their definition of AKI. We postulated that ignoring UO alters the incidence of AKI, may delay diagnosis of AKI, and leads to underestimation of the association between AKI and ICU mortality. Using routinely collected data of adult patients admitted to an intensive care unit (ICU), we retrospectively classified patients according to whether and when they would be diagnosed with KDIGO AKI stage ≥ 2 based on baseline serum creatinine (Screa) and/or urinary output (UO) criterion. As outcomes, we assessed incidence of AKI and association with ICU mortality. In 13,403 ICU admissions (62.2% male, 60.8 ± 16.8 years, SOFA 7.0 ± 4.1), incidence of KDIGO AKI stage ≥ 2 was 13.2% when based only the SCrea criterion, 34.3% when based only the UO criterion, and 38.7% when based on both criteria. By ignoring the UO criterion, 66% of AKI cases were missed and 13% had a delayed diagnosis. The cause-specific hazard ratios of ICU mortality associated with KDIGO AKI stage ≥ 2 diagnosis based on only the SCrea criterion, only the UO criterion and based on both criteria were 2.11 (95% CI 1.85–2.42), 3.21 (2.79–3.69) and 2.85 (95% CI 2.43–3.34), respectively. Ignoring UO in the diagnosis of KDIGO AKI stage ≥ 2 decreases sensitivity, may lead to delayed diagnosis and results in underestimation of KDIGO AKI stage ≥ 2 associated mortality.

Risk factors of contrast-induced nephropathy after percutaneous coronary intervention: a retrospective analysis

Objective

Contrast-induced nephropathy (CIN) is a serious complication in patients with acute coronary syndrome (ACS) and percutaneous coronary intervention (PCI). This study aimed to analyze the potential risk factors for CIN in patients undergoing PCI.

Methods

Patients with ACS who underwent PCI treatment from January 2017 to January 2020 were selected. The patients’ characteristics and medical information were collected and compared.

Results

A total of 1331 patients undergoing PCI were included. The incidence of CIN was 15.33%. Logistic regression analyses showed that a left ventricular ejection fraction ≤45% (odds ratio [OR] 4.18, 95% confidence interval [CI] 1.10–7.36), serum creatinine levels ≤60 μmol/L (OR 3.03, 95% CI 1.21–5.57), age ≥65 years (OR 2.75, 95% CI 1.32–4.60), log N-terminal pro-B-type natriuretic peptide levels ≥2.5 pg/mL (OR 2.31, 95% CI 1.18–5.13), uric acid levels ≥350 μmol/L (OR 2.29, 95% CI 1.04–5.30), emergency percutaneous intervention (OR 1.35, 95% CI 0.34–3.12), and triglyceride levels ≤1.30 mmol/L (OR 1.10, 95% CI 0.01–2.27) were independent risk factors for CIN in patients who underwent PCI.

Conclusions

Early prevention is required to reduce the occurrence of CIN in patients who undergo PCI and have risk factors for CIN.

Risk prediction models for acute kidney injury in adults: An overview of systematic reviews

Background

The incidence of Acute Kidney Injury (AKI) and its human and economic cost is increasing steadily. One way to reduce the burden associated with AKI is to prevent the event altogether. An important step in prevention lies in AKI risk prediction. Due to the increasing number of available risk prediction models (RPMs) clinicians need to be able to rely on systematic reviews (SRs) to provide an objective assessment on which RPM can be used in a specific setting. Our aim was to assess the quality of SRs of RPMs in AKI.

Methods

The protocol for this overview was registered in PROSPERO. MEDLINE and Embase were searched for SRs of RPMs of AKI in any setting from 2003 till August 2020. We used the ROBIS tool to assess the methodological quality of the retrieved SRs.

Results

Eight SRs were retrieved. All studies were assessed as being at high risk for bias using the ROBIS tool. Eight reviews had a high risk of bias in study eligibility criteria (domain 1), five for study identification and selection (domain 2), seven for data collection and appraisal (domain 3) and seven for synthesis and findings (domain 4). Five reviews were scored at high risk of bias across all four domains. Risk of bias assessment with a formal risk of bias tool was only performed in five reviews. Primary studies were heterogeneous and used a wide range of AKI definitions. Only 19 unique RPM were externally validated, of which 11 had only 1 external validation report.

Conclusion

The methodological quality of SRs of RPMs of AKI is inconsistent. Most SRs lack a formal risk of bias assessment. SRs ought to adhere to certain standard quality criteria so that clinicians can rely on them to select a RPM for use in an individual patient.

Trial registration

PROSPERO registration number is CRD 42020204236, available at https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=204236.

A Simple Nomogram to Predict Contrast-Induced Acute Kidney Injury in Patients with Congestive Heart Failure Undergoing Coronary Angiography

Background

Patients with congestive heart failure (CHF) are vulnerable to contrast-induced kidney injury (CI-AKI), but few prediction models are currently available. Therefore, we aimed to establish a simple nomogram for CI-AKI risk assessment for patients with CHF undergoing coronary angiography.

Methods

A total of 1876 consecutive patients with CHF (defined as New York Heart Association functional class II-IV or Killip class II-IV) were enrolled and randomly (2:1) assigned to a development cohort and a validation cohort. The endpoint was CI-AKI defined as serum creatinine elevation of ≥0.3 mg/dL or 50% from baseline within the first 48–72 hours following the procedure. Predictors for the simple nomogram were selected by multivariable logistic regression with a stepwise approach. The discriminative power was assessed using the area under the receiver operating characteristic (ROC) curve and was compared with the classic Mehran score in the validation cohort. Calibration was assessed using the Hosmer–Lemeshow test and 1000 bootstrap samples.

Results

The incidence of CI-AKI was 9.06% (170) in the total sample, 8.64% (n = 109) in the development cohort, and 9.92% (n = 61) in the validation cohort (P=0.367). The simple nomogram including four predictors (age, intra-aortic balloon pump, acute myocardial infarction, and chronic kidney disease) demonstrated a similar predictive power as the Mehran score (area under the curve: 0.80 vs. 0.75, P=0.061), as well as a well-fitted calibration curve.

Conclusions

The present simple nomogram including four predictors is a simple and reliable tool to identify CHF patients at risk of CI-AKI, whereas further external validations are needed.

Prediction Models for AKI in ICU: A Comparative Study

PURPOSE

To assess the performance of models for early prediction of acute kidney injury (AKI) in the Intensive Care Unit (ICU) setting.

PATIENTS AND METHODS

Data were collected from the Medical Information Mart for Intensive Care (MIMIC)-III database for all patients aged ≥18 years who had their serum creatinine (SCr) level measured for 72 h following ICU admission. Those with existing conditions of kidney disease upon ICU admission were excluded from our analyses. Seventeen predictor variables comprising patient demographics and physiological indicators were selected on the basis of the Kidney Disease Improving Global Outcomes (KDIGO) and medical literature. Six models from three types of methods were tested: Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Decision Machine (LightGBM), and Convolutional Neural Network (CNN). The area under receiver operating characteristic curve (AUC), accuracy, precision, recall and F-measure (F1) were calculated for each model to evaluate performance.

RESULTS

We extracted the ICU records of 17,205 patients from MIMIC-III dataset. LightGBM had the best performance, with all evaluation indicators achieving the highest value (average AUC = 0.905, F1 = 0.897, recall = 0.836). XGBoost had the second best performance and LR, RF, SVM performed similarly (P = 0.082, 0.158 and 0.710, respectively) on AUC. The CNN model achieved the lowest score for accuracy, precision, F1 and AUC. SVM and LR had relatively low recall compared with that of the other models. The SCr level had the most significant effect on the early prediction of AKI onset in LR, RF, SVM and LightGBM.

CONCLUSION

LightGBM demonstrated the best capability for predicting AKI in the first 72 h of ICU admission. LightGBM and XGBoost showed great potential for clinical application owing to their high recall value. This study can provide references for artificial intelligence-powered clinical decision support systems for AKI early prediction in the ICU setting.

Predictive Value of Hypoalbuminemia for Contrast-Associated Acute Kidney Injury: A Systematic Review and Meta-Analysis

Contrast-associated acute kidney injury (CA-AKI) is a major adverse complication of intravascular administration of contrast medium. Current studies have shown that hypoalbuminemia might be a novel risk factor of CA-AKI. This systematic review and meta-analysis was performed to evaluate the predictive value of hypoalbuminemia for CA-AKI. Relevant studies were identified in Ovid-Medline, PubMed, Embase, and Cochrane Library up to December 31, 2019. Two authors independently screened studies, consulting with a third author when necessary to resolve discrepancies. The pooled odds ratio (OR) was calculated to assess the association between hypoalbuminemia and CA-AKI using a random-effects model or fixed-effects model. Eight relevant studies involving a total of 18 687 patients met our inclusion criteria. The presence of hypoalbuminemia was associated with an increased risk of CA-AKI development (pooled OR: 2.59, 95% CI: 1.80-3.73). Hypoalbuminemia is independently associated with the occurrence of CA-AKI and may be a potentially modifiable factor for clinical intervention. This systematic review and meta-analysis was registered in PROSPERO (CRD42020168104).

Contrast-associated acute kidney injury: An update of risk factors, risk factor scores, and preventive measures

As lifespans lengthen, age-related diseases such as cardiovascular disease and diabetes are becoming more prevalent. Correspondingly, the use of contrast agents for medical imaging is also becoming more common, and there is increasing awareness of contrast-associated acute kidney injury (CA-AKI). There is no specific treatment for CA-AKI, and clinicians currently focus on prevention, interventions that alter its pathogenesis, and identification of risk factors. Although the incidence of CA-AKI is low in the general population, the risk of CA-AKI can reach 20% to 30% in patients with multiple risk factors. Many models have been applied in the clinic to assess the risk factors for CA-AKI, enable identification of high-risk groups, and improve clinical management. Hypotonic or isotonic contrast media are recommended to prevent CA-AKI in high-risk patients. Patients with risk factors should avoid using contrast media multiple times within a short period of time. All nephrotoxic drugs should be stopped at least 24 h before the administration of contrast media in high-risk populations, and adequate hydration is recommended for all patients. This review summarizes the pathophysiology of CA-AKI and the progress in diagnosis and differential diagnosis; updates the risk factors and risk factor scoring systems; reviews the latest advances related to prevention and treatment; discusses current problems in epidemiological studies; and highlights the importance of identifying high-risk subjects to control modifiable risk factors and use of a rating scale to estimate the risk and implement appropriate prevention strategies.

Artificial Intelligence in Acute Kidney Injury: From Static to Dynamic Models

Artificial intelligence (AI) is the development of computer systems that normally require human intelligence. In the field of acute kidney injury (AKI) AI has led to an evolution of risk prediction models. In the past, static prediction models were developed using baseline (eg, preoperative) data to evaluate AKI risk. Newer models which incorporated baseline as well as evolving data collected during a hospital admission have shown improved predicative abilities. In this review, we will summarize the advances made in AKI risk prediction over the last several years, including a shift toward more dynamic, real-time, electronic medical record-based models. In addition, we will be discussing the role of electronic AKI alerts and decision support tools. Recent studies have demonstrated improved patient outcomes through the use of these tools which monitor for nephrotoxin medication exposures as well as provide kidney focused care bundles for patients at high risk for severe AKI. Finally, we will briefly discuss the pitfalls and implications of implementing these scores, alerts, and support tools.

Refining Safe Contrast Limits for Preventing Acute Kidney Injury After Percutaneous Coronary Intervention

Background

Contrast‐associated acute kidney injury (CA‐AKI) is associated with substantial morbidity and may be prevented by using less contrast during percutaneous coronary intervention (PCI). However, tools for determining safe contrast volumes are limited. We developed risk models to tailor safe contrast volume limits during PCI.

Methods and Results

Using data from all PCIs performed at 18 hospitals from January 2015 to March 2018, we developed logistic regression models for predicting CA‐AKI, including simpler models (“pragmatic full,” “pragmatic minimum”) using only predictors easily derivable from electronic health records. We prospectively validated these models using PCI data from April 2018 to December 2018 and compared them to preexisting safe contrast models using the area under the receiver operating characteristic curve (AUC). The model derivation data set included 20 579 PCIs with 2102 CA‐AKI cases. When applying models to the separate validation data set (5423 PCIs, 488 CA‐AKI cases), prior safe contrast limits (5*Weight/Creatinine, 2*CreatinineClearance) were poor measures of safety with accuracies of 53.7% and 56.6% in predicting CA‐AKI, respectively. The full, pragmatic full, and pragmatic minimum models performed significantly better (accuracy, 73.1%, 69.3%, 66.6%; AUC, 0.80, 0.76, 0.72 versus 0.59 for 5 * Weight/Creatinine, 0.61 for 2*CreatinineClearance). We found that applying safe contrast limits could meaningfully reduce CA‐AKI risk in one‐quarter of patients.

Conclusions

Compared with preexisting equations, new multivariate models for safe contrast limits were substantially more accurate in predicting CA‐AKI and could help determine which patients benefit most from limiting contrast during PCI. Using readily available electronic health record data, these models could be implemented into electronic health records to provide actionable information for improving PCI safety.

Acute Kidney Injury: A Bona Fide Complication of Diabetes

The landscape of kidney disease in diabetes has shifted. The classical dogma of "diabetic nephropathy" progressing through stages of albuminuria, leading to decline in glomerular filtration rate and end-stage kidney disease (ESKD), has been replaced by a more nuanced understanding of the complex and heterogeneous nature of kidney disease in diabetes. Paralleling this evolution, standardized definitions have resulted in a growing appreciation that acute kidney injury (AKI) is increasing in its incidence rapidly and that people with diabetes are much more likely to develop AKI than people without diabetes. Here, I propose that AKI should be considered a complication of diabetes alongside other complications that similarly do not fit neatly into the historical microvascular/macrovascular paradigm. In this article, we take a look at the evidence indicating that diabetes is a major risk factor for AKI and we review the causes of this increased risk. We consider the long-term implications of AKI in diabetes and its potential contribution to the future development of chronic kidney disease, ESKD, and mortality. Finally, we look toward the future at strategies to better identify people at risk for AKI and to develop new approaches to improve AKI outcomes. Recognizing AKI as a bona fide complication of diabetes should open up new avenues for investigation that may ultimately improve the outlook for people living with diabetes and at risk for kidney disease.

Advances in the pathogenesis and prevention of contrast-induced nephropathy

With the increasing application of medical imaging contrast materials, contrast-induced nephropathy has become one of the leading causes of iatrogenic renal insufficiency. The underlying mechanism is associated with renal medullary hypoxia, direct toxicity of contrast agents, oxidative stress, apoptosis, immune/inflammation and epigenetic regulation in contrast-induced nephropathy. Up to date, there is no effective therapy for contrast-induced nephropathy, and thus risk predication and effective preventive strategies are keys to reduce the occurrence of contrast-induced nephropathy. It was found that the proper use of contrast medium, personalized hydration, and high-dose statins may reduce the occurrence of contrast-induced nephropathy, while antioxidants have not shown significant therapeutic benefits. Additionally, the role of remote ischemia preconditioning and vasodilators in the prevention of contrast-induced nephropathy needs further study. This review aims to discuss the incidence, pathogenesis, risk prediction, and preventive strategies for contrast-induced nephropathy.

A prediction model of contrast-associated acute kidney injury in patients with hypoalbuminemia undergoing coronary angiography

BACKGROUND

Risk stratification is recommended as the key step to prevent contrast-associated acute kidney injury (CA-AKI) among at-risk patients following coronary angiography (CAG) and/or percutaneous coronary intervention (PCI). Patients with hypoalbuminemia are prone to CA-AKI and do not have their own risk stratification tool. Therefore, this study developed and validated a new model for predicting CA-AKI among hypoalbuminemia patients CAG/PCI.

METHODS

1272 patients with hypoalbuminemia receiving CAG/PCI were enrolled and randomly allocated (2:1 ratio) into the development cohort (n = 848) and the validation cohort (n = 424). CA-AKI was defined as an increase of ≥0.3 mg/dL or 50% in serum creatinine (SCr) compared to baseline in the 48 to 72 h after CAG/PCI. A prediction model was established with independent predictors according to stepwise logistic regression, showing as a nomogram. The discrimination of the new model was evaluated by the area under the curve (AUC) and was compared to the classic Mehran CA-AKI model. The Hosmer-Lemeshow test was conducted to assess the calibration of our model.

RESULTS

Overall, 8.4% (71/848) patients of the development group and 11.2% (48/424) patients of the validation group experienced CA-AKI. A new nomogram included estimated glomerular filtration rate (eGFR), serum albumin (ALB), age and the use of intra-aortic balloon pump (IABP); showed better predictive ability than the Mehran score (C-index 0.756 vs. 0.693, p = 0.02); and had good calibration (Hosmer-Lemeshow test p = 0.187).

CONCLUSIONS

We developed a simple model for predicting CA-AKI among patients with hypoalbuminemia undergoing CAG/PCI, but our findings need validating externally.

TRIAL REGISTRATION

http://www.ClinicalTrials.gov NCT01400295 , retrospectively registered 21 July 2011.