The role of biomarkers in early identification of acute kidney injury among non-critically ill patients

BACKGROUND

Prediction and/or early identification of acute kidney injury (AKI) and individuals at greater risk remains of great interest in clinical medicine. Acute kidney injury continues to be a common complication among hospitalized patients, with an incidence ranging from 6 to 58%, depending on the setting. Aim of this study was to determine the performance of Insulin-like growth factor binding protein-7 (IGFBP7), tissue metallopeptidase inhibitor 2 (TIMP2), and urinary neutrophil gelatinase-associated lipocalin (uNGAL) in early detection of AKI among non-critically ill patients.

METHODS

In this prospective observational study at Mayo Clinic Hospitals in Rochester, Minnesota, USA, non-critically ill patients admitted from the emergency department between October 31st, 2016 and May 1st, 2018, who had an acute kidney injury (AKI) probability of 5% or higher were included. Biomarkers were measured in residual urine samples collected in the emergency department. The primary outcome was biomarker performance in predicting AKI development within the first 72 h.

RESULTS

Among 368 included patients, the mean age was 79 ± 12 years, and 160 (43%) were male. Acute kidney injury occurred in 62 (17%) patients; 11.5% stage 1, 2.5% stage 2, and 3% stage 3. Twelve patients (3%) died during hospitalization and 102 (28%) within nine months after admission. The median uNGAL and IGFBP7-TIMP2 were 57 [20-236 ng/ml], and 0.3 [0.1-0.8], respectively. The C-statistic of uNGAL and IGFBP7-TIMP2 of > 0.3 and > 2.0 for AKI prediction were 0.56, 0.54, and 0.53, respectively. In a model where one point is assigned to each marker of AKI (elevated serum creatinine, IGFBP7-TIMP2 > 0.3, and uNGAL), a higher score correlated with higher nine-month mortality [OR of 1.32 per point (95% CI 1.02-1.71)].

CONCLUSION

Among non-critically ill hospitalized patients, the performance of uNGAL and IGFBP7-TIMP2 for AKI prediction within 72 h of admission was modest. This suggests a limited role for these biomarkers in AKI risk stratification among non-critically ill patients. Key learning points What was known Acute kidney injury (AKI) is a common complication among hospitalized patients. It is associated with increased morbidity and mortality. Various clinical prediction models and biomarkers have been developed to identify patients in special populations (such as ICU and cardiac surgery) who are at risk of AKI and diagnose AKI early. This study adds The performance of the biomarkers uNGAL, TIMP-2, and IGFBP-7 in predicting AKI within 72 h of admission in non-critically ill patients was modest. However, these biomarkers were found to have a prognostic value for predicting 9-month mortality. One potential application of these biomarkers is identifying patients at higher AKI risk before exposing them to nephrotoxic agents. Potential impact This study provides evidence regarding the real-world performance of current FDA-approved biomarkers (uNGAL, TIMP-2, and IGFBP-7) for predicting acute kidney injury (AKI) within 72 h of hospital admission among noncritically ill patients. While the performance of these biomarkers for predicting short-term AKI was modest, they may have a prognostic value for predicting 9-month mortality.

Development and Validation of a Predictive Model for Acute Kidney Injury in Sepsis Patients Based on Recursive Partition Analysis

BACKGROUND

Sepsis-associated acute kidney injury (SA-AKI) is a critical condition with significant clinical implications, yet there is a need for a predictive model that can reliably assess the risk of its development. This study is undertaken to bridge a gap in healthcare by creating a predictive model for SA-AKI with the goal of empowering healthcare providers with a tool that can revolutionize patient care and ultimately lead to improved outcomes.

METHODS

A cohort of 615 patients afflicted with sepsis, who were admitted to the intensive care unit, underwent random stratification into 2 groups: a training set (n = 435) and a validation set (n = 180). Subsequently, a multivariate logistic regression model, imbued with nonzero coefficients via LASSO regression, was meticulously devised for the prognostication of SA-AKI. This model was thoughtfully rendered in the form of a nomogram. The salience of individual risk factors was assessed and ranked employing Shapley Additive Interpretation (SHAP). Recursive partition analysis was performed to stratify the risk of patients with sepsis.

RESULTS

Among the panoply of clinical variables examined, hypertension, diabetes mellitus, C-reactive protein, procalcitonin (PCT), activated partial thromboplastin time, and platelet count emerged as robust and independent determinants of SA-AKI. The receiver operating characteristic curve analysis for SA-AKI risk discrimination in both the training set and validation set yielded an area under the curve estimates of 0.843 (95% CI: 0.805 to 0.882) and 0.834 (95% CI: 0.775 to 0.893), respectively. Notably, PCT exhibited the most conspicuous influence on the model's predictive capacity. Furthermore, statistically significant disparities were observed in the incidence of SA-AKI and the 28-day survival rate across high-risk, medium-risk, and low-risk cohorts (P < .05).

CONCLUSION

The composite predictive model, amalgamating the quintet of SA-AKI predictors, holds significant promise in facilitating the identification of high-risk patient subsets.

Development and validation of a medication-based risk prediction model for acute kidney injury in older outpatients

BACKGROUND

Older adults are at an increased risk of acute kidney injury (AKI), particularly in community settings, often due to medications. Effective prevention hinges on identifying high-risk patients, yet existing models for predicting AKI risk in older outpatients are scarce, particularly those incorporating medication variables. We aimed to develop an AKI risk prediction model that included medication-related variables for older outpatients.

METHODS

We constructed a cohort of 2,272,257 outpatients aged ≥65 years using a national claims database. This cohort was split into a development (70%) and validation (30%) groups. Our primary goal was to identify newly diagnosed AKI within one month of cohort entry in an outpatient context. We screened 170 variables and developed a risk prediction model using logistic regression.

RESULTS

The final model integrated 12 variables: 2 demographic, 4 comorbid, and 6 medication-related. It showed good performance with acceptable calibration. In the validation cohort, the area under the receiver operating characteristic curve value was 0.720 (95% confidence interval, 0.692-0.748). Sensitivity and specificity were 69.9% and 61.9%, respectively. Notably, the model identified high-risk patients as having a 27-fold increased AKI risk compared with low-risk individuals.

CONCLUSION

We have developed a new AKI risk prediction model for older outpatients, incorporating critical medication-related variables with good discrimination. This tool may be useful in identifying and targeting patients who may require interventions to prevent AKI in an outpatient setting.

Development and validation of a deep interpretable network for continuous acute kidney injury prediction in critically ill patients

Early detection of acute kidney injury (AKI) may provide a crucial window of opportunity to prevent further injury, which helps improve clinical outcomes. This study aimed to develop a deep interpretable network for continuously predicting the 24-hour AKI risk in real-time and evaluate its performance internally and externally in critically ill patients. A total of 21,163 patients' electronic health records sourced from Beth Israel Deaconess Medical Center (BIDMC) were first included in building the model. Two external validation populations included 3025 patients from the Philips eICU Research Institute and 2625 patients from Zhongda Hospital Southeast University. A total of 152 intelligently engineered predictors were extracted on an hourly basis. The prediction model referred to as DeepAKI was designed with the basic framework of squeeze-and-excitation networks with dilated causal convolution embedded. The integrated gradients method was utilized to explain the prediction model. When performed on the internal validation set (3175 [15 %] patients from BIDMC) and the two external validation sets, DeepAKI obtained the area under the curve of 0.799 (95 % CI 0.791-0.806), 0.763 (95 % CI 0.755-0.771) and 0.676 (95 % CI 0.668-0.684) for continuousAKI prediction, respectively. For model interpretability, clinically relevant important variables contributing to the model prediction were informed, and individual explanations along the timeline were explored to show how AKI risk arose. The potential threats to generalisability in deep learning-based models when deployed across health systems in real-world settings were analyzed.

Nephrotoxic Risk Associated With Combination Therapy of Vancomycin and Piperacillin-Tazobactam in Critically Ill Patients With Chronic Kidney Disease

Background: The combination of vancomycin and piperacillin-tazobactam (VPT) has been associated with acute kidney injury (AKI) in hospitalized patients when compared to similar combinations. Additional studies examining this nephrotoxic risk in critically ill patients have not consistently demonstrated the aforementioned association. Furthermore, patients with baseline renal dysfunction have been excluded from almost all of these studies, creating a need to examine the risk in this patient population. Methods: This was a retrospective cohort analysis of critically ill adults with baseline chronic kidney disease (CKD) who received vancomycin plus an anti-pseudomonal beta-lactam at Emory University Hospital. The primary outcome was incidence of AKI. Secondary outcomes included stage of AKI, time to development of AKI, time to return to baseline renal function, new requirement for renal replacement therapy, intensive care unit and hospital length of stay, and in-hospital mortality. Results: A total of 109 patients were included. There was no difference observed in the primary outcome between the VPT (50%) and comparator (58%) group (P = .4), stage 2 or 3 AKI (15.9% vs 6%; P = .98), time to AKI development (1.7 vs 2 days; P = .5), time to return to baseline renal function (4 vs 3 days; P = .2), new requirement for RRT (4.5% vs 1.5%; P = .3), ICU length of stay (7.3 vs 7.4 days; P = .9), hospital length of stay (19.3 vs 20.1 days; P = .87), or in-hospital mortality (15.9% vs 10.8%; P = .4). A significant difference was observed in the duration of antibiotic exposure (3.32 vs 2.62 days; P = .045 days). Conclusion: VPT was not associated with an increased risk of AKI or adverse renal outcomes. Our findings suggest that the use of this antibiotic combination should not be avoided in this patient population. More robust prospective studies are warranted to confirm these findings.

Development and external validation of multimodal postoperative acute kidney injury risk machine learning models

Objectives

To develop and externally validate machine learning models using structured and unstructured electronic health record data to predict postoperative acute kidney injury (AKI) across inpatient settings.

Materials and Methods

Data for adult postoperative admissions to the Loyola University Medical Center (2009-2017) were used for model development and admissions to the University of Wisconsin-Madison (2009-2020) were used for validation. Structured features included demographics, vital signs, laboratory results, and nurse-documented scores. Unstructured text from clinical notes were converted into concept unique identifiers (CUIs) using the clinical Text Analysis and Knowledge Extraction System. The primary outcome was the development of Kidney Disease Improvement Global Outcomes stage 2 AKI within 7 days after leaving the operating room. We derived unimodal extreme gradient boosting machines (XGBoost) and elastic net logistic regression (GLMNET) models using structured-only data and multimodal models combining structured data with CUI features. Model comparison was performed using the receiver operating characteristic curve (AUROC), with Delong's test for statistical differences.

Results

The study cohort included 138 389 adult patient admissions (mean [SD] age 58 [16] years; 11 506 [8%] African-American; and 70 826 [51%] female) across the 2 sites. Of those, 2959 (2.1%) developed stage 2 AKI or higher. Across all data types, XGBoost outperformed GLMNET (mean AUROC 0.81 [95% confidence interval (CI), 0.80-0.82] vs 0.78 [95% CI, 0.77-0.79]). The multimodal XGBoost model incorporating CUIs parameterized as term frequency-inverse document frequency (TF-IDF) showed the highest discrimination performance (AUROC 0.82 [95% CI, 0.81-0.83]) over unimodal models (AUROC 0.79 [95% CI, 0.78-0.80]).

Discussion

A multimodality approach with structured data and TF-IDF weighting of CUIs increased model performance over structured data-only models.

Conclusion

These findings highlight the predictive power of CUIs when merged with structured data for clinical prediction models, which may improve the detection of postoperative AKI.

Construction and validation of a risk prediction model for acute kidney injury in patients after cardiac arrest

OBJECTIVE

Identifying patients at high risk for cardiac arrest-associated acute kidney injury (CA-AKI) helps in early preventive interventions. This study aimed to establish and validate a high-risk nomogram for CA-AKI.

METHODS

In this retrospective dataset, 339 patients after cardiac arrest (CA) were enrolled and randomized into a training or testing dataset. The Student's t-test, non-parametric Mann-Whitney U test, or χ2 test was used to compare differences between the two groups. Optimal predictors of CA-AKI were determined using the Least Absolute Shrinkage and Selection Operator (LASSO). A nomogram was developed to predict the early onset of CA-AKI. The performance of the nomogram was assessed using metrics such as area under the curve (AUC), calibration curves, decision curve analysis (DCA), and clinical impact curve (CIC).

RESULTS

In total, 150 patients (44.2%) were diagnosed with CA-AKI. Four independent risk predictors were identified and integrated into the nomogram: chronic kidney disease, albumin level, shock, and heart rate. Receiver operating characteristic (ROC) analyses showed that the nomogram had a good discrimination performance for CA-AKI in the training dataset 0.774 (95%CI, 0.715-0.833) and testing dataset 0.763 (95%CI, 0.670-0.856). The AUC values for the two groups were calculated and compared using the Hanley-McNeil test. No statistically significant differences were observed between the groups. The calibration curve demonstrated good agreement between the predicted outcome and actual observations. Good clinical usefulness was identified using DCA and CIC.

CONCLUSION

An easy-to-use nomogram for predicting CA-AKI was established and validated, and the prediction efficiency of the clinical model has reasonable clinical practicability.

Prediction differences and implications of acute kidney injury with and without urine output criteria in adult critically ill patients

BACKGROUND

Due to the convenience of serum creatinine (SCr) monitoring and the relative complexity of urine output (UO) monitoring, most studies have predicted acute kidney injury (AKI) only based on SCr criteria. This study aimed to compare the differences between SCr alone and combined UO criteria in predicting AKI.

METHODS

We applied machine learning methods to evaluate the performance of 13 prediction models composed of different feature categories on 16 risk assessment tasks (half used only SCr criteria, half used both SCr and UO criteria). The area under receiver operator characteristic curve (AUROC), the area under precision recall curve (AUPRC) and calibration were used to assess the prediction performance.

RESULTS

In the first week after ICU admission, the prevalence of any AKI was 29% under SCr criteria alone and increased to 60% when the UO criteria was combined. Adding UO to SCr criteria can significantly identify more AKI patients. The predictive importance of feature types with and without UO was different. Using only laboratory data maintained similar predictive performance to the full feature model under only SCr criteria [e.g. for AKI within the 48-h time window after 1 day of ICU admission, AUROC (95% confidence interval) 0.83 (0.82, 0.84) vs 0.84 (0.83, 0.85)], but it was not sufficient when the UO was added [corresponding AUROC (95% confidence interval) 0.75 (0.74, 0.76) vs 0.84 (0.83, 0.85)].

CONCLUSIONS

This study found that SCr and UO measures should not be regarded as equivalent criteria for AKI staging, and emphasizes the importance and necessity of UO criteria in AKI risk assessment.

The predictive value of hematological inflammatory markers for acute kidney injury and mortality in adults with hemophagocytic Lymphohistiocytosis: A retrospective analysis of 585 patients

BACKGROUND

Hemophagocytic lymphohistiocytosis (HLH) is a rare immunological hyperactivation-related disease with a high mortality rate. The purpose of this study was to examine the relationship between complete blood count parameters and the occurrence of acute kidney injury (AKI) and mortality in patients with HLH.

METHODS

We included 585 adult patients with HLH. Logistic regression models for AKI and 28-day mortality were developed.

RESULTS

Multivariate logistic regression models revealed that hemoglobin (HB) ≤ 7.3 g/dl (adjusted OR, 1.651; 95% CI, 1.044-2.612), hemoglobin-to-red blood cell distribution width ratio (HRR) < 0.49 (adjusted OR, 1.692), neutrophil-to-lymphocyte ratio (NLR) ≥ 3.15 (adjusted OR, 1.697), and neutrophil-to-lymphocyte-platelet ratio (NLPR) ≥ 11.0 (adjusted OR, 1.608) were independent risk factors for the development of AKI. Moreover, lower platelet levels (31 × 109/L < platelets < 84 × 109/L, adjusted OR, 2.133; platelets ≤ 31 × 109/L, adjusted OR, 3.545) and higher red blood cell distribution width-to-platelet ratio (RPR) levels (0.20 < RPR < 0.54, adjusted OR, 2.595; RPR ≥ 0.54, adjusted OR, 4.307), lymphocytes ≤ 0.34 × 109/L (adjusted OR, 1.793), NLPR ≥ 11.0 (adjusted OR, 2.898), and the aggregate index of systemic inflammation (AISI) ≤ 7 (adjusted OR,1.778) were also independent risk factors for 28-day mortality. Furthermore, patients with AKI had a worse prognosis than those without AKI (P < 0.05).

CONCLUSION

In patients with HLH, hematological parameters are of great value for the early identification of patients at high risk of AKI and 28-day mortality.

Closed-Loop Medication Management with an Electronic Health Record System in U.S. and Finnish Hospitals

Many medication errors in the hospital setting are due to manual, error-prone processes in the medication management system. Closed-loop Electronic Medication Management Systems (EMMSs) use technology to prevent medication errors by replacing manual steps with automated, electronic ones. As Finnish Helsinki University Hospital (HUS) establishes its first closed-loop EMMS with the new Epic-based Electronic Health Record system (APOTTI), it is helpful to consider the history of a more mature system: that of the United States. The U.S. approach evolved over time under unique policy, economic, and legal circumstances. Closed-loop EMMSs have arrived in many U.S. hospital locations, with myriad market-by-market manifestations typical of the U.S. healthcare system. This review describes and compares U.S. and Finnish hospitals' EMMS approaches and their impact on medication workflows and safety. Specifically, commonalities and nuanced differences in closed-loop EMMSs are explored from the perspectives of the care/nursing unit and hospital pharmacy operations perspectives. As the technologies are now fully implemented and destined for evolution in both countries, perhaps closed-loop EMMSs can be a topic of continued collaboration between the two countries. This review can also be used for benchmarking in other countries developing closed-loop EMMSs.

Development and validation of the creatinine clearance predictor machine learning models in critically ill adults

BACKGROUND

In critically ill patients, measured creatinine clearance (CrCl) is the most reliable method to evaluate glomerular filtration rate in routine clinical practice and may vary subsequently on a day-to-day basis. We developed and externally validated models to predict CrCl one day ahead and compared them with a reference reflecting current clinical practice.

METHODS

A gradient boosting method (GBM) machine-learning algorithm was used to develop the models on data from 2825 patients from the EPaNIC multicenter randomized controlled trial database. We externally validated the models on 9576 patients from the University Hospitals Leuven, included in the M@tric database. Three models were developed: a "Core" model based on demographic, admission diagnosis, and daily laboratory results; a "Core + BGA" model adding blood gas analysis results; and a "Core + BGA + Monitoring" model also including high-resolution monitoring data. Model performance was evaluated against the actual CrCl by mean absolute error (MAE) and root-mean-square error (RMSE).

RESULTS

All three developed models showed smaller prediction errors than the reference. Assuming the same CrCl of the day of prediction showed 20.6 (95% CI 20.3-20.9) ml/min MAE and 40.1 (95% CI 37.9-42.3) ml/min RMSE in the external validation cohort, while the developed model having the smallest RMSE (the Core + BGA + Monitoring model) had 18.1 (95% CI 17.9-18.3) ml/min MAE and 28.9 (95% CI 28-29.7) ml/min RMSE.

CONCLUSIONS

Prediction models based on routinely collected clinical data in the ICU were able to accurately predict next-day CrCl. These models could be useful for hydrophilic drug dosage adjustment or stratification of patients at risk.

TRIAL REGISTRATION

Not applicable.

Accurate and interpretable prediction of ICU-acquired AKI

PURPOSE

We developed and validated two parsimonious algorithms to predict the time of diagnosis of any stage of acute kidney injury (any-AKI) or moderate-to-severe AKI in clinically actionable prediction windows.

MATERIALS AND METHODS

In this retrospective single-center cohort of adult ICU admissions, we trained two gradient-boosting models: 1) any-AKI model, predicting the risk of any-AKI at least 6 h before diagnosis (50,342 admissions), and 2) moderate-to-severe AKI model, predicting the risk of moderate-to-severe AKI at least 12 h before diagnosis (39,087 admissions). Performance was assessed before disease diagnosis and validated prospectively.

RESULTS

The models achieved an area under the receiver operating characteristic curve (AUROC) of 0.756 at six hours (any-AKI) and 0.721 at 12 h (moderate-to-severe AKI) prior. Prospectively, both models had high positive predictive values (0.796 and 0.546 for any-AKI and moderate-to-severe AKI models, respectively) and triggered more in patients who developed AKI vs. those who did not (median of 1.82 [IQR 0-4.71] vs. 0 [IQR 0-0.73] and 2.35 [IQR 0.14-4.96] vs. 0 [IQR 0-0.8] triggers per 8 h for any-AKI and moderate-to-severe AKI models, respectively).

CONCLUSIONS

The two AKI prediction models have good discriminative performance using common features, which can aid in accurately and informatively monitoring AKI risk in ICU patients.

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.

Predictors and Adverse Outcomes of Acute Kidney Injury in Hospitalized Renal Transplant Recipients

Data about in-hospital AKI in RTRs is lacking. We conducted a retrospective study of 292 RTRs, with 807 hospital admissions, to reveal predictors and outcomes of AKI during admission. In-hospital AKI developed in 149 patients (51%). AKI in a previous admission was associated with a more than twofold increased risk of AKI in subsequent admissions (OR 2.13, p &lt; 0.001). Other major significant predictors for in-hospital AKI included an infection as the major admission diagnosis (OR 2.93, p = 0.015), a medical history of hypertension (OR 1.91, p = 0.027), minimum systolic blood pressure (OR 0.98, p = 0.002), maximum tacrolimus trough level (OR 1.08, p = 0.005), hemoglobin level (OR 0.9, p = 0.016) and albumin level (OR 0.51, p = 0.025) during admission. Compared to admissions with no AKI, admissions with AKI were associated with longer length of stay (median time of 3.83 vs. 7.01 days, p &lt; 0.001). In-hospital AKI was associated with higher rates of mortality during admission, almost doubled odds for rehospitalization within 90 days from discharge and increased the risk of overall mortality in multivariable mixed effect models. In-hospital AKI is common and is associated with poor short- and long-term outcomes. Strategies to prevent AKI during admission in RTRs should be implemented to reduce re-admission rates and improve patient survival.

Development and validation of clinical prediction models for acute kidney injury recovery at hospital discharge in critically ill adults

PURPOSE

Acute kidney injury (AKI) recovery prediction remains challenging. The purpose of the present study is to develop and validate prediction models for AKI recovery at hospital discharge in critically ill patients with ICU-acquired AKI stage 3 (AKI-3).

METHODS

Models were developed and validated in a development cohort (n = 229) and a matched validation cohort (n = 244) from the multicenter EPaNIC database to create prediction models with the least absolute shrinkage and selection operator (Lasso) machine-learning algorithm. We evaluated the discrimination and calibration of the models and compared their performance with plasma neutrophil gelatinase-associated lipocalin (NGAL) measured on first AKI-3 day (NGAL_AKI3) and reference model that only based on age.

RESULTS

Complete recovery and complete or partial recovery occurred in 33.20% and 51.23% of the validation cohort patients respectively. The prediction model for complete recovery based on age, need for renal replacement therapy (RRT), diagnostic group (cardiac/surgical/trauma/others), and sepsis on admission had an area under the receiver operating characteristics curve (AUROC) of 0.53. The prediction model for complete or partial recovery based on age, need for RRT, platelet count, urea, and white blood cell count had an AUROC of 0.61. NGAL_AKI3 showed AUROCs of 0.55 and 0.53 respectively. In cardiac patients, the models had higher AUROCs of 0.60 and 0.71 than NGAL_AKI3's AUROCs of 0.52 and 0.54. The developed models demonstrated a better performance over the reference models (only based on age) for cardiac surgery patients, but not for patients with sepsis and for a general ICU population.

CONCLUSION

Models to predict AKI recovery upon hospital discharge in critically ill patients with AKI-3 showed poor performance in the general ICU population, similar to the biomarker NGAL. In cardiac surgery patients, discrimination was acceptable, and better than NGAL. These findings demonstrate the difficulty of predicting non-reversible AKI early.

Prediction of Mortality and Major Adverse Kidney Events in Critically Ill Patients With Acute Kidney Injury

RATIONALE & OBJECTIVE

Risk prediction tools for assisting acute kidney injury (AKI) management have focused on AKI onset but have infrequently addressed kidney recovery. We developed clinical models for risk stratification of mortality and major adverse kidney events (MAKE) in critically ill patients with incident AKI.

STUDY DESIGN

Multicenter cohort study.

SETTING & PARTICIPANTS

9,587 adult patients admitted to heterogeneous intensive care units (ICUs; March 2009 to February 2017) who experienced AKI within the first 3 days of their ICU stays.

PREDICTORS

Multimodal clinical data consisting of 71 features collected in the first 3 days of ICU stay.

OUTCOMES

(1) Hospital mortality and (2) MAKE, defined as the composite of death during hospitalization or within 120 days of discharge, receipt of kidney replacement therapy in the last 48 hours of hospital stay, initiation of maintenance kidney replacement therapy within 120 days, or a ≥50% decrease in estimated glomerular filtration rate from baseline to 120 days from hospital discharge.

ANALYTICAL APPROACH

Four machine-learning algorithms (logistic regression, random forest, support vector machine, and extreme gradient boosting) and the SHAP (Shapley Additive Explanations) framework were used for feature selection and interpretation. Model performance was evaluated by 10-fold cross-validation and external validation.

RESULTS

One developed model including 15 features outperformed the SOFA (Sequential Organ Failure Assessment) score for the prediction of hospital mortality, with areas under the curve of 0.79 (95% CI, 0.79-0.80) and 0.71 (95% CI, 0.71-0.71) in the development cohort and 0.74 (95% CI, 0.73-0.74) and 0.71 (95% CI, 0.71-0.71) in the validation cohort (P < 0.001 for both). A second developed model including 14 features outperformed KDIGO (Kidney Disease: Improving Global Outcomes) AKI severity staging for the prediction of MAKE: 0.78 (95% CI, 0.78-0.78) versus 0.66 (95% CI, 0.66-0.66) in the development cohort and 0.73 (95% CI, 0.72-0.74) versus 0.67 (95% CI, 0.67-0.67) in the validation cohort (P < 0.001 for both).

LIMITATIONS

The models are applicable only to critically ill adult patients with incident AKI within the first 3 days of an ICU stay.

CONCLUSIONS

The reported clinical models exhibited better performance for mortality and kidney recovery prediction than standard scoring tools commonly used in critically ill patients with AKI in the ICU. Additional validation is needed to support the utility and implementation of these models.

PLAIN-LANGUAGE SUMMARY

Acute kidney injury (AKI) occurs commonly in critically ill patients admitted to the intensive care unit (ICU) and is associated with high morbidity and mortality rates. Prediction of mortality and recovery after an episode of AKI may assist bedside decision making. In this report, we describe the development and validation of a clinical model using data from the first 3 days of an ICU stay to predict hospital mortality and major adverse kidney events occurring as long as 120 days after hospital discharge among critically ill adult patients who experienced AKI within the first 3 days of an ICU stay. The proposed clinical models exhibited good performance for outcome prediction and, if further validated, could enable risk stratification for timely interventions that promote kidney recovery.

Development and validation of short-term renal prognosis prediction model in diabetic patients with acute kidney injury

OBJECTIVE

Diabetes is a major cause of the progression of acute kidney injury (AKI). Few prediction models have been developed to predict the renal prognosis in diabetic patients with AKI so far. The aim of this study was to develop and validate a predictive model to identify high-risk individuals with non-recovery of renal function at 90 days in diabetic patients with AKI.

METHODS

Demographic data and related laboratory indicators of diabetic patients with AKI in the First Affiliated Hospital of Guangxi Medical University from January 31, 2012 to January 31, 2022 were retrospectively analysed, and patients were followed up to 90 days after AKI diagnosis. Based on the results of Logistic regression, a model predicting the risk of non-recovery of renal function at 90 days in diabetic patients with AKI was developed and internal validated. Consistency index (C-index), calibration curve, and decision curve analysis were used to evaluate the differentiation, accuracy, and clinical utility of the prediction model, respectively.

RESULTS

A total of 916 diabetic patients with AKI were enrolled, with a male to female ratio of 2.14:1. The rate of non-recovery of renal function at 90 days was 66.8% (612/916). There were 641 in development cohort and 275 in validation cohort (ration of 7:3). In the development cohort, a prediction model was developed based on the results of Logistic regression analysis. The variables included in the model were: diabetes duration (OR = 1.022, 95% CI  1.012-1.032), hypertension (OR = 1.574, 95% CI 1.043-2.377), chronic kidney disease (OR = 2.241, 95% CI 1.399-3.591), platelet (OR = 0.997, 95% CI 0.995-1.000), 25-hydroxyvitamin D3 (OR = 0.966, 95% CI  0.956-0.976), postprandial blood glucose (OR = 1.104, 95% CI 1.032-1.181), discharged serum creatinine (OR = 1.003, 95% CI 1.001-1.005). The C-indices of the prediction model were 0.807 (95% CI 0.738-0.875) and 0.803 (95% CI 0.713-0.893) in the development and validation cohorts, respectively. The calibration curves were all close to the straight line with slope 1. The decision curve analysis showed that in a wide range of threshold probabilities.

CONCLUSION

A prediction model was developed to help predict short-term renal prognosis of diabetic patients with AKI, which has been verified to have good differentiation, calibration degree and clinical practicability.

KIT-LSTM: Knowledge-guided Time-aware LSTM for Continuous Clinical Risk Prediction

Rapid accumulation of temporal Electronic Health Record (EHR) data and recent advances in deep learning have shown high potential in precisely and timely predicting patients' risks using AI. However, most existing risk prediction approaches ignore the complex asynchronous and irregular problems in real-world EHR data. This paper proposes a novel approach called Knowledge-guIded Time-aware LSTM (KIT-LSTM) for continuous mortality predictions using EHR. KIT-LSTM extends LSTM with two time-aware gates and a knowledge-aware gate to better model EHR and interprets results. Experiments on real-world data for patients with acute kidney injury with dialysis (AKI-D) demonstrate that KIT-LSTM performs better than the state-of-the-art methods for predicting patients' risk trajectories and model interpretation. KIT-LSTM can better support timely decision-making for clinicians.

Impact of Diabetes on the Recurrence and Prognosis of Acute Kidney Injury in Older Male Patients: A 10-Year Retrospective Cohort Study

INTRODUCTION

While patients with diabetes are at higher risk of developing acute kidney injury (AKI), there are few studies on the recurrence of AKI in older adult patients. This study therefore aimed to examine the impact of diabetes on AKI recurrence and long-term outcomes in older male patients.

METHODS

This retrospective cohort study included older male patients who experienced AKI during hospitalization from July 2007 to August 2011. Medical records of all patients were followed up for 10 years. Patients with AKI were classified into groups with and without diabetes. We analyzed differences in common geriatric comorbidities, AKI recurrence frequency, and severity between the two groups, identified risk factors affecting recurrence frequency, and assessed outcomes.

RESULTS

Of all 266 patients, 128 had diabetes and 138 did not. The AKI recurrence rate was significantly higher in the group with diabetes (80.5 vs. 66.7%; P = 0.011). There was a significantly higher proportion of AKI caused by infections in patients with diabetes (43.3 vs. 33.2%, P = 0.006). The proportion of patients with an AKI recurrence frequency ≥ 3 was significantly higher in the group with diabetes (44.7 vs. 29.4%, P = 0.027). Diabetes and coronary heart disease were independent risk factors for AKI recurrence (P < 0.05), diabetes control was associated with multiple AKI recurrences (P = 0.016), and no significant difference was found between the groups regarding the 10-year prognosis (P = 0.522). However, a subgroup analysis showed that patients with multiple AKI recurrences within 2 years had the worst survival outcome (P = 0.004).

CONCLUSIONS

Older male patients with diabetes are prone to AKI recurrence after initial onset of AKI. Diabetes is an independent risk factor for AKI recurrence, and active diabetes control (HbA1c < 7%) may thus reduce the recurrence of AKI and improve the very poor outcomes of patients with multiple recurrences of AKI within 2 years.

Predicting mortality in acute kidney injury patients undergoing continuous renal replacement therapy using a visualization model: A retrospective study

Background: Patients with severe acute kidney injury (AKI) require continuous renal replacement therapy (CRRT) when hemodynamically unstable. We aimed to identify prognostic factors and develop a nomogram that could predict mortality in patients with AKI undergoing CRRT. Methods: Data were extracted from the Dryad Digital Repository. We enrolled 1,002 participants and grouped them randomly into training (n = 670) and verification (n = 332) datasets based on a 2:1 proportion. Based on Cox proportional modeling of the training set, we created a web-based dynamic nomogram to estimate all-cause mortality. Results: The model incorporated phosphate, Charlson comorbidity index, body mass index, mean arterial pressure, levels of creatinine and albumin, and sequential organ failure assessment scores as independent predictive indicators. Model calibration and discrimination were satisfactory. In the training dataset, the area under the curves (AUCs) for estimating the 28-, 56-, and 84-day all-cause mortality were 0.779, 0.780, and 0.787, respectively. The model exhibited excellent calibration and discrimination in the validation dataset, with AUC values of 0.791, 0.778, and 0.806 for estimating 28-, 56-, and 84-day all-cause mortality, respectively. The calibration curves exhibited the consistency of the model between the two cohorts. To visualize the results, we created a web-based calculator. Conclusion: We created a web-based calculator for assessing fatality risk in patients with AKI receiving CRRT, which may help rationalize clinical decision-making and personalized therapy.

How to Determine Fluid Management Goals during Continuous Kidney Replacement Therapy in Patients with AKI: Focus on POCUS

The utilization of kidney replacement therapies (KRT) for fluid management of patients who are critically ill has significantly increased over the last years. Clinical studies have suggested that both fluid accumulation and high fluid removal rates are associated with adverse outcomes in the critically ill population receiving KRT. Importantly, the ideal indications and/or fluid management strategies that could favorably affect these patients are unknown; however, differentiating clinical scenarios in which effective fluid removal may provide benefit to the patient by avoiding congestive organ injury, compared with other settings in which this intervention may result in harm, is direly needed in the critical care nephrology field. In this review, we describe observational data related to fluid management with KRT, and examine the role of point-of-care ultrasonography as a potential tool that could provide physiologic insights to better individualize decisions related to fluid management through KRT.

P(v-a)CO2/C(a-v)O2 as a red blood cell transfusion trigger and prognostic indicator for sepsis-related anaemia: protocol for a prospective cohort study

INTRODUCTION

Red blood cell (RBC) transfusion primarily aims to improve oxygen transport and tissue oxygenation. The transfusion strategy based on haemoglobin concentration could not accurately reflect cellular metabolism. The ratio of venous-arterial carbon dioxide tension difference to arterial-venous oxygen content difference (P(v-a)CO₂/C(a-v)O₂) is a good indicator of cellular hypoxia. We aim to explore the influence of P(v-a)CO₂/C(a-v)O₂ as an RBC transfusion trigger on outcomes in septic shock patients.

METHODS AND ANALYSIS

The study is a single-centre prospective cohort study. We consecutively enrol adult septic shock patients requiring RBC transfusion at intensive care unit (ICU) admission or during ICU stay. P(v-a)CO₂/C(a-v)O₂ will be recorded before and 1 hour after each transfusion. The primary outcome is ICU mortality. Binary logistic regression analyses will be performed to detect the independent association between P(v-a)CO₂/C(a-v)O₂ and ICU mortality. A cut-off value for P(v-a)CO₂/C(a-v)O₂ will be obtained by maximising the Youden index with the receiver operator characteristic curve. According to this cut-off value, patients included will be divided into two groups: one with the P(v-a)CO₂/C(a-v)O₂ >cut-off and the other with the P(v-a)CO₂/C(a-v)O₂ ≤cut off. Differences in clinical outcomes between the two groups will be assessed after propensity matching.

ETHICS AND DISSEMINATION

The study has been approved by the Institutional Review Board of Affiliated Hospital of Weifang Medical University (wyfy-2021-ky-059). Findings will be disseminated through conference presentations and peer-reviewed journals.

TRIAL REGISTRATION NUMBER

ChiCTR2100051748.

Prognosis of patients with heart disease with acute kidney injury undergoing dialysis treatment

OBJECTIVES

to verify the relationship of cardiovascular diseases with acute kidney injury and assess the prognosis of patients in renal replacement therapy.

METHODS

a cohort study, carried out in a public hospital specialized in cardiology. Treatment, comorbidities, duration of treatment, laboratory tests, discharge and deaths were analyzed.

RESULTS

of the 101 patients, 75 (74.3%) received non-dialysis treatment. The most frequent cardiological diagnoses were hypertension, cardiomyopathies and coronary syndrome. Hospitalization in patients undergoing dialysis was 18 days, hemoglobin <10.5g/dl and anuria in the first days of hospitalization contributed to the type of treatment. Each increase in hemoglobin units from the first day of hospitalization decreases the chance of dialysis by 19.2%. There was no difference in mortality.

CONCLUSIONS

the main cardiological diseases were not predictive of dialysis indication, and clinical treatment was the most frequent. Anuria and anemia were predictors for dialysis treatment.

Urinary sodium excretion is low prior to acute kidney injury in patients in the intensive care unit

Background

The incidence of acute kidney injury (AKI) is high in intensive care units (ICUs), and a better understanding of AKI is needed. Early chronic kidney disease is associated with urinary concentration inability and AKI recovery with increased urinary solutes in humans. Whether the inability of the kidneys to concentrate urine and excrete solutes at appropriate levels could occur prior to the diagnosis of AKI is still uncertain, and the associated mechanisms have not been studied.

Methods

In this single-center prospective observational study, high AKI risk in ICU patients was followed up for 7 days or until ICU discharge. They were grouped as "AKI" or "No AKI" according to their AKI status throughout admission. We collected daily urine samples to measure solute concentrations and osmolality. Data were analyzed 1 day before AKI, or from the first to the fifth day of admission in the "No AKI" group. We used logistic regression models to evaluate the influence of the variables on future AKI diagnosis. The expression of kidney transporters in urine was evaluated by Western blotting.

Results

We identified 29 patients as "No AKI" and 23 patients as "AKI," the latter being mostly low severity AKI. Urinary sodium excretion was lower in "AKI" patients prior to AKI diagnosis, particularly in septic patients. The expression of Na+/H+ exchanger (NHE3), a urinary sodium transporter, was higher in "AKI" patients.

Conclusions

Urinary sodium excretion is low before an AKI episode in ICU patients, and high expressions of proximal tubule sodium transporters might contribute to this.

Clinical characteristics of new-onset acute kidney injury in patients with established acute respiratory distress syndrome: A prospective single-center post hoc observational study

Background

We assessed the incidence and clinical characteristics of acute kidney injury (AKI) in acute respiratory distress syndrome (ARDS) patients and its effect on clinical outcomes.

Methods

We conducted a single-center prospective longitudinal study. Patients who met the Berlin definition of ARDS in the medical ICU in China-Japan Friendship Hospital from March 1, 2016, to September 30, 2020, were included. AKI was defined according to the KDIGO clinical practice guidelines. Early and late AKI were defined as AKI occurring within 48 h after ARDS was diagnosed or after 48 h, respectively.

Results

Of the 311 ARDS patients, 161 (51.8%) developed AKI after ICU admission. Independent risk factors for AKI in ARDS patients were age (OR 1.027, 95% CI 1.009–1.045), a history of diabetes mellitus (OR 2.110, 95%CI 1.100–4.046) and chronic kidney disease (CKD) (OR 9.328, 95%CI 2.393–36.363), APACHE II score (OR 1.049, 95%CI 1.008–1.092), average lactate level in the first 3 days (OR 1.965, 95%CI 1.287–3.020) and using ECMO support (OR 2.359, 95%CI 1.154–4.824). Early AKI was found in 91 (56.5%) patients and late AKI was found in 70 (43.5%). Early AKI was related to the patient’s underlying disease and the severity of hospital admission, while late AKI was related to the application of nephrotoxic drugs. The mortality rate of ARDS combined with AKI was 57.1%, which was independently associated with shock (OR 54.943, 95%CI 9.751–309.573).

Conclusion

A significant number of patients with ARDS developed AKI, and the mortality rate for ARDS patients was significantly higher when combined with AKI. Therapeutic drug monitoring should be routinely used to avoid drug toxicity during treatment.

Nomogram Prediction Model of Serum Chloride and Sodium Ions on the Risk of Acute Kidney Injury in Critically Ill Patients

Purpose

This study aims to investigate the effect of serum chloride and sodium ions on AKI occurrence in ICU patients, and further constructs a prediction model containing these factors to explore the predictive value of these ions in AKI.

Methods

The clinical information of patients admitted to ICU of Beijing Friendship Hospital Affiliated to Capital Medical University was collected for retrospective analysis. Logistic regression analysis was used to analyzing the influencing factors. A nomogram for predicting AKI risk was constructed with R software and validated by repeated sampling. Afterwards, the effectiveness and accuracy of the model were tested and evaluated.

Results

A total of 446 cases met the requirements of this study, of which 178 developed AKI during their stay in ICU, with an incidence rate of 39.9%. Hypernatremia, heart failure, sepsis, APACHE II score, and initial creatinine value and BE value at ICU admission before the diagnosis of AKI were identified as independent risk factors for developing AKI during ICU stay. These predictors were incorporated into the nomogram of AKI risk in critically ill patients, which was constructed by using R software. Receiver operating characteristic curve analysis was further used and showed that the area under the curve of the model was 0.7934 (95% CI 0.742–0.8447), indicating that the model had an ideal value. Finally, further evaluated its clinical effectiveness. The clinical effect curve and decision curve showed that most areas of the decision curve of this model were greater than 0, indicating that this model owned a certain clinical effectiveness.

Conclusion

The nomogram based on hypernatremia, heart failure, sepsis, APACHE II score, and initial creatinine and BE value in ICU can predict the individualized risk of AKI with satisfactory distinguishability and accuracy.

Assessment of prescribed vs. achieved fluid balance during continuous renal replacement therapy and mortality outcome

Background

Fluid management during continuous renal replacement therapy (CRRT) requires accuracy in the prescription of desired patient fluid balance (FBGoal) and precision in the attainable patient fluid balance (FBAchieved). Herein, we examined the association of the gap between prescribed vs. achieved patient fluid balance during CRRT (%FBGap) with hospital mortality in critically ill patients.

Methods

Cohort study of critically ill adults with acute kidney injury (AKI) requiring CRRT and a prescription of negative fluid balance (mean patient fluid balance goal of negative ≥0.5 liters per day). Fluid management parameters included: 1) NUF (net ultrafiltration rate); 2) FBGoal; 3) FBAchieved; and 4) FBGap (% gap of fluid balance achieved vs. goal), all adjusted by patient’s weight (kg) and duration of CRRT (hours).

Results

Data from 653 patients (median of 102.2 patient-hours of CRRT) were analyzed. Mean (SD) age was 56.7 (14.6) years and 61.9% were male. Hospital mortality rate was 64%. Despite FBGoal was similar in patients who died vs. survived, survivors achieved greater negative fluid balance during CRRT than non-survivors: median FBAchieved -0.25 [-0.52 to -0.05] vs. 0.06 [-0.26 to 0.62] ml/kg/h, p<0.001. Median NUF was lower in patients who died vs. survived: 1.06 [0.63–1.47] vs. 1.22 [0.82–1.69] ml/kg/h, p<0.001, and median %FBGap was higher in patients who died (112.8%, 61.5 to 165.7) vs. survived (64.2%, 30.5 to 91.8), p<0.001. In multivariable models, higher %FBGap was independently associated with increased risk of hospital mortality: aOR (95% CI) 1.01 (1.01–1.02), p<0.001. NUF was not associated with hospital mortality when adjusted by %FBGap and other clinical parameters: aOR 0.96 (0.72–1.28), p = 0.771.

Conclusions

Higher %FBGap was independently associated with an increased risk of hospital mortality in critically ill adults with AKI on CRRT in whom clinicians prescribed negative fluid balance via CRRT. %FBGap represents a novel quality indicator of CRRT delivery that could assist with operationalizing fluid management interventions during CRRT.

Development and validation of outcome prediction models for acute kidney injury patients undergoing continuous renal replacement therapy

Object

This study aimed to develop and validate a set of practical predictive tools that reliably estimate the 28-day prognosis of acute kidney injury patients undergoing continuous renal replacement therapy.

Methods

The clinical data of acute kidney injury patients undergoing continuous renal replacement therapy were extracted from the Medical Information Mart for Intensive Care IV database with structured query language and used as the development cohort. An all-subset regression was used for the model screening. Predictive models were constructed via a logistic regression, and external validation of the models was performed using independent external data.

Results

Clinical prediction models were developed with clinical data from 1,148 patients and validated with data from 121 patients. The predictive model based on seven predictors (age, vasopressor use, red cell volume distribution width, lactate, white blood cell count, platelet count, and phosphate) exhibited good predictive performance, as indicated by a C-index of 0.812 in the development cohort, 0.811 in the internal validation cohort and 0.768 in the external validation cohort.

Conclusions

The model reliably predicted the 28-day prognosis of acute kidney injury patients undergoing continuous renal replacement therapy. The predictive items are readily available, and the web-based prognostic calculator (https://libo220284.shinyapps.io/DynNomapp/) can be used as an adjunctive tool to support the management of patients.

Small, short-term, point-of-care creatinine changes as predictors of acute kidney injury in critically ill patients

PURPOSE

To assess short-term creatinine changes as predictors of acute kidney injury (AKI) when used alone and in combination with AKI risk factors.

METHODS

In this prospective cohort study, we identified all creatinine measurements from frequent point-of-care arterial blood gas measurements from ICU admission until AKI. We evaluated the predictive value of small changes between these creatinine measurements for AKI development, alone and with AKI risk factors.

RESULTS

Of 377 patients with 3235 creatinine measurements, generating 15,075 creatinine change episodes, 215 (57%) patients developed AKI, and 68 (18%) developed stage 2 or 3 AKI. In isolation, a creatinine increase over 4.1-7.3 h had a 0.65 area under the curve for predicting stage 2 or 3 AKI within 3-37.7 h. Combining creatinine increases of ≥1 μmol/L/h (≥0.0113 mg/dL/h) over 4-5.8 h with three AKI risk factors (cardiac surgery, use of vasopressors, chronic liver disease) had 83% sensitivity, 79% specificity and 0.87 area under the curve for stage 2 or 3 AKI occurring 8.7-25.6 h later.

CONCLUSION

In combination with key risk factors, frequent point-of-care creatinine assessment on arterial blood gases to detect small, short-term creatinine changes provides a robust, novel, low-cost, and rapid method for predicting AKI in critically ill patients.

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.

A Novel Risk Prediction Model for Severe Acute Kidney Injury in Intensive Care Unit Patients Receiving Fluid Resuscitation

Background

To develop a risk prediction model for the occurrence of severe acute kidney injury (AKI) in intensive care unit (ICU) patients receiving fluid resuscitation.

Methods

We conducted a secondary analysis of the Crystalloid vs. Hydroxyethyl Starch Trial (CHEST) trial, a blinded randomized controlled trial that enrolled ICU patients who received intravenous fluid resuscitation. The primary outcome was the first event in a composite outcome of doubling of serum creatinine and/or treatment with renal replacement treatment (RRT) within 28 days of randomization. The final model developed using multivariable logistic regression with backwards elimination was validated internally and then translated into a predictive equation.

Results

Six thousand seven hundred twenty-seven ICU participants were studied, among whom 745 developed the study outcome. The final model having six variables, including admission diagnosis of sepsis, illness severity score, mechanical ventilation, tachycardia, baseline estimated glomerular filtration rate and emergency admission. The model had good discrimination (c-statistic = 0.72, 95% confidence interval 0.697–0.736) and calibration (Hosmer-Lemeshow test, χ² = 14.4, p = 0.07) for the composite outcome, with a c-statistic after internal bootstrapping validation of 0.72, which revealed a low degree of over-fitting. The positive predictive value and negative predictive value were 58.8 and 89.1%, respectively. The decision curve analysis indicates a net benefit in prediction of severe AKI using the model across a range of threshold probabilities between 5 and 35%.

Conclusions

Our model, using readily available clinical variables to identify ICU patients at high risk of severe AKI achieved good predictive performance in a clinically relevant population.

Serum IL-17 levels are higher in critically ill patients with AKI and associated with worse outcomes

Background

Interleukin-17 (IL-17) antagonism in rats reduces the severity and progression of AKI. IL-17-producing circulating T helper-17 (TH17) cells is increased in critically ill patients with AKI indicating that this pathway is also activated in humans. We aim to compare serum IL-17A levels in critically ill patients with versus without AKI and to examine their relationship with mortality and major adverse kidney events (MAKE).

Methods

Multicenter, prospective study of ICU patients with AKI stage 2 or 3 and without AKI. Samples were collected at 24–48 h after AKI diagnosis or ICU admission (in those without AKI) [timepoint 1, T1] and 5–7 days later [timepoint 2, T2]. MAKE was defined as the composite of death, dependence on kidney replacement therapy or a reduction in eGFR of ≥ 30% from baseline up to 90 days following hospital discharge.

Results

A total of 299 patients were evaluated. Patients in the highest IL-17A tertile (versus lower tertiles) at T1 had higher acuity of illness and comorbidity scores. Patients with AKI had higher levels of IL-17A than those without AKI: T1 1918.6 fg/ml (692.0–5860.9) versus 623.1 fg/ml (331.7–1503.4), p < 0.001; T2 2167.7 fg/ml (839.9–4618.9) versus 1193.5 fg/ml (523.8–2198.7), p = 0.006. Every onefold higher serum IL-17A at T1 was independently associated with increased risk of hospital mortality (aOR 1.35, 95% CI: 1.06–1.73) and MAKE (aOR 1.26, 95% CI: 1.02–1.55). The highest tertile of IL-17A (vs. the lowest tertile) was also independently associated with higher risk of MAKE (aOR 3.03, 95% CI: 1.34–6.87). There was no effect modification of these associations by AKI status. IL-17A levels remained significantly elevated at T2 in patients that died or developed MAKE.

Conclusions

Serum IL-17A levels measured by the time of AKI diagnosis or ICU admission were differentially elevated in critically ill patients with AKI when compared to those without AKI and were independently associated with hospital mortality and MAKE.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13054-022-03976-4.

[Prevention of acute kidney injury]

Acute kidney injury contributes significantly to morbidity and mortality in hospitalized patients and is a common complication in the intensive care unit. Identification of patients at risk, elimination of modifiable risk factors and initiation of recommended preventive measures are the main cornerstones to prevent the onset and progression of acute kidney injury. Clinical and biomarker-based risk scores can help assess AKI-risk in specific patient populations. To date, there is no approved clinically effective drug to prevent AKI. Current guidelines suggest preventive care bundles that include optimizing volume status and renal perfusion by improving mean arterial pressure and using vasopressors, mainly norepinephrine. In addition, avoidance of volume overload and the targeted use of diuretics to achieve euvolemia are recommended. Nephrotoxic drugs require a critical risk-benefit assessment and therapeutic drug monitoring when appropriate. Contrast imaging should not be withheld from patients at risk of AKI when indicated but contrast medium should be limited to the smallest possible volume. Finally, recommendations include maintenance of normoglycemia and other measures to optimize organ function in specific patient populations.

Application of Machine Learning Algorithms to Predict Acute Kidney Injury in Elderly Orthopedic Postoperative Patients

Objective

There has been a worldwide increment in acute kidney injury (AKI) incidence among elderly orthopedic operative patients. The AKI prediction model provides patients’ early detection a possibility at risk of AKI; most of the AKI prediction models derive, however, from the cardiothoracic operation. The purpose of this study is to predict the risk of AKI in elderly patients after orthopedic surgery based on machine learning algorithm models.

Methods

We organized a retrospective study being comprised of 1000 patients with postoperative AKI undergoing orthopedic surgery from September 2016, to June, 2021. They were divided into training (80%;n=799) and test (20%;n=201) sets.We utilized nine machine learning (ML) algorithms and used intraoperative information and preoperative clinical features to acquire models to predict AKI. The performance of the model was evaluated according to the area under the receiver operating characteristic (AUC), sensitivity, specificity and accuracy. Select the optimal model and establish the nomogram to make the prediction model visualization. The concordance statistic (C-statistic) and calibration curve were used to discriminate and calibrate the nomogram respectively.

Results

In predicting AKI, nine ML algorithms posted AUC of 0.656–1.000 in the training cohort, with the randomforest standing out and AUC of 0.674–0.821 in the test cohort, with the logistic regression model standing out. Thus, we applied the logistic regression model to establish nomogram. The nomogram was comprised of ten variables: age, body mass index, American Society of Anesthesiologists, hypoproteinemia, hypertension, diabetes, anemia, duration of low mean arterial pressure, mean arterial pressure, transfusion.The calibration curves showed good agreement between prediction and observation in both the training and test sets.

Conclusion

By including intraoperative and preoperative risk factors, ML algorithm can predict AKI and logistic regression model performing the best. Our prediction model and nomogram that are based on this ML algorithm can help lead decision-making for strategies to inhibit AKI over the perioperative duration.

Machine learning for the prediction of acute kidney injury in critical care patients with acute cerebrovascular disease

Purpose

Acute kidney injury (AKI) is a common complication and associated with a poor clinical outcome. In this study, we developed and validated a model for predicting the risk of AKI through machine learning methods in critical care patients with acute cerebrovascular disease.

Methods

This study was a retrospective study based on two different cohorts. Five machine learning methods were used to develop AKI risk prediction models. We used six popular metrics (AUROC, F2-Score, accuracy, sensitivity, specificity and precision) to evaluate the performance of these models.

Results

We identified 2935 patients in the MIMIC-III database and 499 patients in our local database to develop and validate the AKI risk prediction model. The incidence of AKI in these two different cohorts was 18.3% and 61.7%, respectively. Analysis showed that several laboratory parameters (serum creatinine, hemoglobin, white blood cell count, bicarbonate, blood urea nitrogen, sodium, albumin, and platelet count), age, and length of hospital stay, were the top ten important factors associated with AKI. The analysis demonstrated that the XGBoost had higher AUROC (0.880, 95%CI: 0.831–0.929), indicating that the XGBoost model was better at predicting AKI risk in patients with acute cerebrovascular disease than other models.

Conclusions

This study developed machine learning methods to identify critically ill patients with acute cerebrovascular disease who are at a high risk of developing AKI. This result suggested that machine learning techniques had the potential to improve the prediction of AKI risk models in critical care.

Early and late acute kidney injury: temporal profile in the critically ill pediatric patient

Background

Increasing AKI diagnosis precision to refine the understanding of associated epidemiology and outcomes is a focus of recent critical care nephrology research. Timing of onset of acute kidney injury (AKI) during pediatric critical illness and impact on outcomes has not been fully explored.

Methods

This was a secondary analysis of the Assessment of Worldwide Acute Kidney Injury, Renal Angina and Epidemiology (AWARE) database. AKI was defined as per Kidney Disease: Improving Global Outcomes criteria. Early AKI was defined as diagnosed at ≤48 h after intensive care unit (ICU) admission, with any diagnosis >48 h denoted as late AKI. Transient AKI was defined as return to baseline serum creatinine ≤48 h of onset, and those without recovery fell into the persistent category. A second incidence of AKI ≥48 h after recovery was denoted as recurrent. Patients were subsequently sorted into distinct phenotypes as early-transient, late-transient, early-persistent, late-persistent and recurrent. Primary outcome was major adverse kidney events (MAKE) at 28 days (MAKE28) or at study exit, with secondary outcomes including AKI-free days, ICU length of stay and inpatient renal replacement therapy.

Results

A total of 1262 patients had AKI and were included. Overall mortality rate was 6.4% (n = 81), with 34.2% (n = 432) fulfilling at least one MAKE28 criteria. The majority of patients fell in the early-transient cohort (n = 704, 55.8%). The early-persistent phenotype had the highest odds of MAKE28 (odds ratio 7.84, 95% confidence interval 5.45–11.3), and the highest mortality rate (18.8%). Oncologic and nephrologic/urologic comorbidities at AKI diagnosis were associated with MAKE28.

Conclusion

Temporal nature and trajectory of AKI during a critical care course are significantly associated with patient outcomes, with several subtypes at higher risk for poorer outcomes. Stratification of pediatric critical care-associated AKI into distinct phenotypes is possible and may become an important prognostic tool.

Prediction of acute kidney injury in ICU with gradient boosting decision tree algorithms

PURPOSE

To predict acute kidney injury (AKI) in a large intensive care unit (ICU) database.

MATERIALS AND METHODS

A total of 30,020 ICU admissions with 17,222 AKI episodes were extracted from the Medical Information Mart from Intensive Care (MIMIC)-III database. These were randomly divided into a training set and an independent testing set in a ratio of 4:1. Data pertaining to demographics, admission information, vital signs, laboratory tests, critical illness scores, medications, comorbidities, and intervention measures were collected. Logistic regression, random forest, LightGBM, XGBoost, and an ensemble model was used for early prediction of AKI occurrence and important feature extraction. The SHAP analysis was adopted to reveal the impact of prediction for each feature.

RESULTS

The ensemble model had the best overall performance for predicting AKI before 24 h, 48 h and 72 h. The F1 values were 0.915, 0.893, and 0.878, respectively. AUCs were 0.923, 0.903, and 0.895, respectively.

CONCLUSIONS

Based on readily available electronic medical record (EMR) data, gradient boosting decision tree models are highly accurate at early AKI prediction in critically ill patients.

Acute Kidney Injury in the Outpatient Setting: Developing and Validating a Risk Prediction Model

Rationale & Objective

Risk factors for acute kidney injury (AKI) in the hospital have been well studied. Yet, risk factors for identifying high-risk patients for AKI occurring and managed in the outpatient setting are unknown and may differ.

Study Design

Predictive model development and external validation using observational electronic health record data.

Setting & Participants

Patients aged 18-90 years with recurrent primary care encounters, known baseline serum creatinine, and creatinine measured during an 18-month outcome period without established advanced kidney disease.

New Predictors & Established Predictors

Established predictors for inpatient AKI were considered. Potential new predictors were hospitalization history, smoking, serum potassium levels, and prior outpatient AKI.

Outcomes

A ≥50% increase in the creatinine level above a moving baseline of the recent measurement(s) without a hospital admission within 7 days defined outpatient AKI.

Analytical Approach

Logistic regression with bootstrap sampling for backward stepwise covariate elimination was used. The model was then transformed into 2 binary tests: one identifying high-risk patients for research and another identifying patients for additional clinical monitoring or intervention.

Results

Outpatient AKI was observed in 4,611 (3.0%) and 115,744 (2.4%) patients in the development and validation cohorts, respectively. The model, with 18 variables and 3 interaction terms, produced C statistics of 0.717 (95% CI, 0.710-0.725) and 0.722 (95% CI, 0.720-0.723) in the development and validation cohorts, respectively. The research test, identifying the 5.2% most at-risk patients in the validation cohort, had a sensitivity of 0.210 (95% CI, 0.208-0.213) and specificity of 0.952 (95% CI, 0.951-0.952). The clinical test, identifying the 20% most at-risk patients, had a sensitivity of 0.494 (95% CI, 0.491-0.497) and specificity of 0.806 (95% CI, 0.806-0.807).

Limitations

Only surviving patients with measured creatinine levels during a baseline period and outcome period were included.

Conclusions

The outpatient AKI risk prediction model performed well in both the development and validation cohorts in both continuous and binary forms.

Association between Latent Trajectories of Fluid Balance and Clinical Outcomes in Critically Ill Patients with Acute Kidney Injury: A Prospective Multicenter Observational Study

INTRODUCTION

We aimed to identify different trajectories of fluid balance (FB) and investigate the effect of FB trajectories on clinical outcomes in intensive care unit (ICU) patients with acute kidney injury (AKI) and the dose-response association between fluid overload (FO) and mortality.

METHODS

We derived data from the Beijing Acute Kidney Injury Trial (BAKIT). A total of 1,529 critically ill patients with AKI were included. The primary outcome was 28-day mortality, and hospital mortality, ICU mortality and AKI stage were the secondary outcomes. A group-based trajectory model was used to identify the trajectory of FB during the first 7 days. Multivariable logistic regression was performed to examine the relationship between FB trajectories and clinical outcomes. A logistic regression model with restricted cubic splines was used to examine the dose relationship between FO and 28-day mortality.

RESULTS

Three distinct trajectories of FB were identified: low FB (1,316, 86.1%), decreasing FB (120, 7.8%), and high FB (93, 6.1%). Compared with low FB, high FB was associated with increased 28-day mortality (odds ratio [OR] 1.94, 95% confidence interval [CI] 1.17-3.19) and AKI stage (OR 2.04, 95% CI 1.23-3.37), whereas decreasing FB was associated with a reduction in 28-day mortality by approximately half (OR 0.53, 95% CI 0.32-0.87). Similar results were found for the outcomes of ICU mortality and hospital mortality. We observed a J-shaped relationship between maximum FO and 28-day mortality, with the lowest risk at a maximum FO of 2.8% L/kg.

CONCLUSION

Different trajectories of FB in critically ill patients with AKI were associated with clinical outcomes. An FB above or below a certain range was associated with an increased risk of mortality. Further studies should explore this relationship and search for the optimal fluid management strategies for critically ill patients with AKI.

Prognóstico de pacientes cardiopatas com injuria renal aguda submetidos a tratamento dialítico

RESUMO Objetivos: verificar a relação de patologias cardíacas com injuria renal aguda e avaliar o prognóstico do paciente em terapia de substituição renal. Métodos: estudo de coorte, realizado em hospital público especializado em cardiologia. O tratamento, comorbidades, tempo de tratamento, exames laboratoriais, alta e óbitos foram analisados. Resultados: dos 101 pacientes, 75 (74,3%) receberam tratamento não dialítico. Os diagnósticos cardiológicos mais frequentes foram hipertensão arterial, miocardiopatias e síndrome coronariana. A internação nos pacientes dialíticos foi de 18 dias, a hemoglobina <10,5g/dl e a anuria nos primeiros dias de internação contribuíram para o tipo de tratamento. Cada aumento de unidade de hemoglobina a partir do primeiro dia de internação diminui em 19,2% a chance de diálise. Não houve diferença na mortalidade. Conclusões: as principais doenças cardiológicas não foram preditivas de indicação de diálise, e o tratamento clínico foi o mais frequente. Anuria e anemia foram preditores para o tratamento dialítico.

Dimethyl fumarate attenuates LPS induced septic acute kidney injury by suppression of NFκB p65 phosphorylation and macrophage activation

Septic acute kidney injury (AKI) always accounts for high mortality of septic patients in ICU. Due to its not well understood mechanism for infection and immune-regulation in kidney dysfunction, there is a lack of effective therapy without side effects. Dimethyl fumarate (DMF) as an immunomodulatory molecule has been approved for treatment to multiple sclerosis. However, the therapeutic effect and immunomodulatory role underlying DMF action in septic AKI is unclear. This study aimed to elucidate the role of DMF in lipopolysaccharide (LPS)-induced septic AKI involving macrophage regulation. In current study, we administered DMF by oral gavage to mice with LPS-induced AKI, then harvested serum and kidney at three different time points. We further isolated Bone marrow-derived macrophages (BMDMs) from mice and stimulated them with LPS followed by DMF treatment. To explore immunomodulatory role of DMF in macrophages, we depleted macrophages in mice using liposomal clodronate after DMF treatment upon LPS-induced septic AKI. Then we observed that DMF attenuated renal dysfunction and murine pathological kidney injury after LPS injection. DMF could inhibit translocation of phosphorylated NF-κB p65 and suppress macrophage activation in LPS-induced AKI. DMF reduced the secretion of TNF-α and IL-6 whereas increased the secretion of IL-10 and Arg-1 in BMDMs after LPS stimulation. DMF also inhibited NF-κB p65 phosphorylation in BMDMs after LPS stimulation. Importantly, the effect of DMF against LPS-induced AKI, macrophage activation, and translocation of phosphorylated NF-κB p65 was impaired upon macrophage depletion. Thus, DMF could attenuate LPS-induced septic AKI by suppression of NF-κB p65 phosphorylation and macrophage activation. This work suggested the potential therapeutic role of DMF for patients in ICU threatened by septic AKI.

Development and Validation of a Prediction Model for Acute Kidney Injury Among Patients With Acute Decompensated Heart Failure

Background: Acute kidney injury is an adverse event that carries significant morbidity among patients with acute decompensated heart failure (ADHF). We planned to develop a parsimonious model that is simple enough to use in clinical practice to predict the risk of acute kidney injury (AKI) occurrence. Methods: Six hundred and fifty patients with ADHF were enrolled in this study. Data for each patient were collected from medical records. We took three different approaches of variable selection to derive four multivariable logistic regression model. We selected six candidate predictors that led to a relatively stable outcome in different models to derive the final prediction model. The prediction model was verified through the use of the C-Statistics and calibration curve. Results: Acute kidney injury occurred in 42.8% of the patients. Advanced age, diabetes, previous renal dysfunction, high baseline creatinine, high B-type natriuretic peptide, and hypoalbuminemia were the strongest predictors for AKI. The prediction model showed moderate discrimination C-Statistics: 0.766 (95% CI, 0.729-0.803) and good identical calibration. Conclusion: In this study, we developed a prediction model and nomogram to estimate the risk of AKI among patients with ADHF. It may help clinical physicians detect AKI and manage it promptly.

External validation of the Madrid Acute Kidney Injury Prediction Score

Background

The Madrid Acute Kidney Injury Prediction Score (MAKIPS) is a recently described tool capable of performing automatic calculations of the risk of hospital-acquired acute kidney injury (HA-AKI) using data from from electronic clinical records that could be easily implemented in clinical practice. However, to date, it has not been externally validated. The aim of our study was to perform an external validation of the MAKIPS in a hospital with different characteristics and variable case mix.

Methods

This external validation cohort study of the MAKIPS was conducted in patients admitted to a single tertiary hospital between April 2018 and September 2019. Performance was assessed by discrimination using the area under the receiver operating characteristics curve and calibration plots.

Results

A total of 5.3% of the external validation cohort had HA-AKI. When compared with the MAKIPS cohort, the validation cohort showed a higher percentage of men as well as a higher prevalence of diabetes, hypertension, cardiovascular disease, cerebrovascular disease, anaemia, congestive heart failure, chronic pulmonary disease, connective tissue diseases and renal disease, whereas the prevalence of peptic ulcer disease, liver disease, malignancy, metastatic solid tumours and acquired immune deficiency syndrome was significantly lower. In the validation cohort, the MAKIPS showed an area under the curve of 0.798 (95% confidence interval 0.788–0.809). Calibration plots showed that there was a tendency for the MAKIPS to overestimate the risk of HA-AKI at probability rates ˂0.19 and to underestimate at probability rates between 0.22 and 0.67.

Conclusions

The MAKIPS can be a useful tool, using data that are easily obtainable from electronic records, to predict the risk of HA-AKI in hospitals with different case mix characteristics.

High risk of acute kidney injury in Malawian trauma patients: a prospective observational cohort study

Background

Trauma is a common cause of acute kidney injury (AKI). Yet little data exist regarding trauma-related-AKI in low-resourced settings, where the majority of deaths from AKI and trauma occur. We prospectively evaluated epidemiology of AKI in hospitalized Malawian trauma patients.

Methods

AKI was defined by creatinine-only Kidney Disease Improving Global Outcomes (KDIGO) criteria. Those with AKI were followed up 3–6 months later to determine persistent kidney abnormalities. We calculated univariate statistics with Wilcoxon rank sum tests, Fisher’s exact, and chi-square tests to compare those with and without AKI. Multivariate log-risk regression modelling was used to determine risk ratios (RR) and 95% confidence intervals (CI) for AKI development.

Results

Of 223 participants, 14.4% (n = 32) developed AKI. Most patients were young (median age 32) males (n = 193, 86.5%) involved in road traffic injuries (n = 120, 53.8%). After adjusting for confounders, those with severe anemia during their admission were 1.4 times (RR 1.4, 95% CI 1.1–1.8) more likely to develop AKI than those without. Overall mortality was 7.6% (n = 17), and those who developed AKI were more likely to die than those who did not (18.8% vs 5.6%, p-value = 0.02). Almost half of those with AKI (n = 32) either died (n = 6) or had persistent kidney dysfunction at follow-up (n = 8).

Conclusion

In one of the few African studies on trauma-related AKI, we found a high incidence of AKI (14.4%) in Malawian trauma patients with associated poor outcomes. Given AKI’s association with increased mortality and potential ramifications on long-term morbidity, urgent attention is needed to improve AKI-related outcomes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12882-021-02564-y.

Comparison of Static and Dynamic Baseline Creatinine Surrogates for Defining Acute Kidney Injury

BACKGROUND

"Dynamic" baseline serum creatinine (sCr), based on a rolling 48-h window, and a static baseline sCr (previous outpatient sCr) were used to define acute kidney injury (AKI).

METHODS

Retrospective cohort study of adult admissions to the University of Alabama (UAB) Health System hospitals for years 2016-2018. Included admissions had >1- and <180-day length of stay, >2 inpatient sCr measurements, and an averaged estimated glomerular filtration rate >15 mL/min/1.73 m2. The final cohort of 62,380 patients included 100,570 admissions, 3,509 inpatient deaths, and 1,916 admissions with inpatient dialysis. AKI was defined by Kidney Disease Improving Global Outcomes (KDIGO) criteria and a static or dynamic baseline sCr. Discrimination was evaluated with area under receiver operator curves (AUC), logistic regression, and net reclassification improvement (NRI).

RESULTS

Preadmission outpatient "static" sCr values were available for 43,433 admissions. The lowest sCr value during a rolling 48-h window before each inpatient sCr defined a "dynamic" baseline sCr. Using point-wise comparisons, the dynamic baseline sCr performed better than static baseline sCr for inpatient mortality (AUC [0.819 vs. 0.741; p < 0.001] and NRI ≥0.306 [p < 0.001]) and inpatient dialysis (AUC [0.903 vs. 0.864; p < 0.001] and NRI ≥0.317 [p < 0.001]).

CONCLUSIONS

The dynamic baseline sCr is available without reference to preadmission sCr values and avoids confounding associated with missing outpatient sCr values. AKI defined with the dynamic baseline sCr significantly improved discrimination of risk for inpatient mortality and dialysis compared to static baseline sCr.

Cul4a attenuates LPS-induced acute kidney injury via blocking NF-κB signaling pathway in sepsis

Background

Acute kidney injury (AKI) is a common disease that can develop into end-stage kidney disease. Sepsis is one of the main causes of AKI. Currently, there is no satisfactory way to treat septic AKI. Therefore, we have shown the protective function of Cul4a in septic AKI and its molecular mechanism.

Methods

The cellular and animal models of septic AKI were established by using lipopolysaccharide (LPS). Western blot (WB) was employed to analyze Cul4a expression. RT-qPCR was employed to test the expression of Cul4a, SOD1, SOD2, GPX1, CAT, IL-6, TNF-a, Bcl-2, IL1b, Bax and KIM-1 mRNA. ELISA was performed to detect the contents of inflammatory factors and LDH. CCK-8 was utilized to detect cell viability. Flow cytometry was utilized to analyze the apoptosis. DHE-ROS kit was used to detect the content of ROS.

Results

Cul4a was down-regulated in cellular and animal models of septic AKI. Oxidative stress is obviously induced by LPS, as well as apoptosis and inflammation. However, these can be significantly inhibited by up-regulating Cul4a. Moreover, LPS induced the activation of the NF-kB pathway, which could also be inhibited by overexpression of Cul4a.

Conclusions

Cul4awas found to be a protective factor in septic AKI, which could inhibit LPS-induced oxidative stress, apoptosis and inflammation of HK-2 cells by inhibiting the NF-kB pathway.

KGDAL: Knowledge Graph Guided Double Attention LSTM for Rolling Mortality Prediction for AKI-D Patients

With the rapid accumulation of electronic health record (EHR) data, deep learning (DL) models have exhibited promising performance on patient risk prediction. Recent advances have also demonstrated the effectiveness of knowledge graphs (KG) in providing valuable prior knowledge for further improving DL model performance. However, it is still unclear how KG can be utilized to encode high-order relations among clinical concepts and how DL models can make full use of the encoded concept relations to solve real-world healthcare problems and to interpret the outcomes. We propose a novel knowledge graph guided double attention LSTM model named KGDAL for rolling mortality prediction for critically ill patients with acute kidney injury requiring dialysis (AKI-D). KGDAL constructs a KG-based two-dimension attention in both time and feature spaces. In the experiment with two large healthcare datasets, we compared KGDAL with a variety of rolling mortality prediction models and conducted an ablation study to test the effectiveness, efficacy, and contribution of different attention mechanisms. The results showed that KGDAL clearly outperformed all the compared models. Also, KGDAL-derived patient risk trajectories may assist healthcare providers to make timely decisions and actions. The source code, sample data, and manual of KGDAL are available at https://github.com/lucasliu0928/KGDAL.

A validation study of UCSD-Mayo risk score in predicting hospital-acquired acute kidney injury in COVID-19 patients

Introduction

Acute kidney injury (AKI) in coronavirus disease 2019 (COVID-19) patients is associated with poor prognosis. Early prediction and intervention of AKI are vital for improving clinical outcome of COVID-19 patients. As lack of tools for early AKI detection in COVID-19 patients, this study aimed to validate the USCD-Mayo risk score in predicting hospital-acquired AKI in an extended multi-center COVID-19 cohort.

Methods

Five hundred seventy-two COVID-19 patients from Wuhan Tongji Hospital Guanggu Branch, Wuhan Leishenshan Hospital, and Wuhan No. Ninth Hospital was enrolled for this study. Patients who developed AKI or reached an outcome of recovery or death during the study period were included. Predictors were evaluated according to data extracted from medical records.

Results

Of all patients, a total of 44 (8%) developed AKI. The UCSD-Mayo risk score achieved excellent discrimination in predicting AKI with the C-statistic of 0.88 (95%CI: 0.84–0.91). Next, we determined the UCSD-Mayo risk score had good overall performance (Nagelkerke R² = 0.32) and calibration in our cohort. Further analysis showed that the UCSD-Mayo risk score performed well in subgroups defined by gender, age, and several chronic comorbidities. However, the discrimination of the UCSD-Mayo risk score in ICU patients and patients with mechanical ventilation was not good which might be resulted from different risk factors of these patients.

Conclusions

We validated the performance of UCSD-Mayo risk score in predicting hospital-acquired AKI in COVID-19 patients was excellent except for patients from ICU or patients with mechanical ventilation.

Risk Scoring Systems Including Electrolyte Disorders for Predicting the Incidence of Acute Kidney Injury in Hospitalized Patients

Introduction

Electrolyte disorders are common among hospitalized patients with acute kidney injury (AKI) and adversely affect the outcome. This study aimed to explore the potential role of abnormal electrolyte levels on predicting AKI and severe AKI.

Methods

In this retrospective, observational study, we included all hospitalized patients in our hospital in China from October 01, 2014, to September 30, 2015. Since only a few patients had arterial blood gas analysis (ABG), all subjects involved were divided into two groups: patients with ABG and patients without ABG. Severe AKI was defined as AKI stage 2 or 3 according to KDIGO guideline.

Results

A total of 80,091 patients were enrolled retrospectively and distributed randomly into the test cohort and the validation cohort (2:1). Logistic regression was performed in the test cohort to analyze risk factors including electrolyte disorders and elucidate the association. The test data (derivation cohort) led to AUC values of 0.758 (95% CI: 0.743–0.773; AKI with ABG), 0.751 (95% CI: 0.740–0.763; AKI without ABG), 0.733 (95% CI: 0.700–0.767; severe AKI with ABG), 0.853 (95% CI: 0.824–0.882; severe AKI without ABG). Application of the scoring system in the validation cohort led to AUC values of 0.724 (95% CI: 0.703–0.744; AKI with ABG), 0.738 (95% CI: 0.721–0.755; AKI without ABG), 0.774 (95% CI: 0.732–0.815; severe AKI with ABG), 0.794 (95% CI: 0.760–0.827; severe AKI without ABG). Hosmer–Lemeshow tests revealed a good calibration.

Conclusion

The risk scoring systems involving electrolyte disorders were established and validated adequately efficient to predict AKI and severe AKI in hospitalized patients. Electrolyte imbalance needs to be carefully monitored and corrections should be made on time to avoid further adverse outcome.