Short- and long-term outcomes of intensive care patients with acute kidney disease

Biomarkers vs Machines: The Race to Predict Acute Kidney Injury

BACKGROUND

Acute kidney injury (AKI) is a serious complication affecting up to 15% of hospitalized patients. Early diagnosis is critical to prevent irreversible kidney damage that could otherwise lead to significant morbidity and mortality. However, AKI is a clinically silent syndrome, and current detection primarily relies on measuring a rise in serum creatinine, an imperfect marker that can be slow to react to developing AKI. Over the past decade, new innovations have emerged in the form of biomarkers and artificial intelligence tools to aid in the early diagnosis and prediction of imminent AKI.

CONTENT

This review summarizes and critically evaluates the latest developments in AKI detection and prediction by emerging biomarkers and artificial intelligence. Main guidelines and studies discussed herein include those evaluating clinical utilitiy of alternate filtration markers such as cystatin C and structural injury markers such as neutrophil gelatinase-associated lipocalin and tissue inhibitor of metalloprotease 2 with insulin-like growth factor binding protein 7 and machine learning algorithms for the detection and prediction of AKI in adult and pediatric populations. Recommendations for clinical practices considering the adoption of these new tools are also provided.

SUMMARY

The race to detect AKI is heating up. Regulatory approval of select biomarkers for clinical use and the emergence of machine learning algorithms that can predict imminent AKI with high accuracy are all promising developments. But the race is far from being won. Future research focusing on clinical outcome studies that demonstrate the utility and validity of implementing these new tools into clinical practice is needed.

Heterogeneity in the definition of major adverse kidney events: a scoping review

Acute kidney injury (AKI) is associated with persistent renal dysfunction, the receipt of dialysis, dialysis dependence, and mortality. Accordingly, the concept of major adverse kidney events (MAKE) has been adopted as an endpoint for assessing the impact of AKI. However, applied criteria or observation periods for operationalizing MAKE appear to vary across studies. To evaluate this heterogeneity for MAKE evaluation, we performed a systematic scoping review of studies that employed MAKE as an AKI endpoint. Four major academic databases were searched, and we identified 122 studies with increasing numbers over time. We found marked heterogeneity in applied criteria and observation periods for MAKE across these studies, with some even lacking a description of criteria. Moreover, 13 different observation periods were employed, with 30 days and 90 days as the most common. Persistent renal dysfunction was evaluated by estimated glomerular filtration rate (34%) or serum creatinine concentration (48%); however, 37 different definitions for this component were employed in terms of parameters, cut-off criteria, and assessment periods. The definition for the dialysis component also showed significant heterogeneity regarding assessment periods and duration of dialysis requirement (chronic vs temporary). Finally, MAKE rates could vary by 7% [interquartile range: 1.7-16.7%] with different observation periods or by 36.4% with different dialysis component definitions. Our findings revealed marked heterogeneity in MAKE definitions, particularly regarding component assessment and observation periods. Dedicated discussion is needed to establish uniform and acceptable standards to operationalize MAKE in terms of selection and applied criteria of components, observation period, and reporting criteria for future trials on AKI and related conditions.

Invasive pulmonary aspergillosis among patients with severe community-acquired pneumonia and influenza in ICUs: a retrospective cohort study

RATIONALE

The prevalence, clinical characteristics, and outcomes of invasive pulmonary aspergillosis in patients with severe community-acquired pneumonia (CAP) in intensive care units remain underestimated because of the lack of a disease-recognition scheme and the inadequacy of diagnostic tests.

OBJECTIVES

To identify the prevalence, risk factors, and outcomes of severe CAP complicated with invasive pulmonary aspergillosis (IPA) in intensive care units (ICUs).

METHODS

We conducted a retrospective cohort study including recruited 311 ICU-hospitalized patients with severe CAP without influenza or with influenza. Bronchoalveolar lavage fluid (BALF) samples were from all patients and subjected to mycological testing. Patients were categorized as having proven or probable Aspergillus infection using a modified form of the AspICU algorithm comprising clinical, radiological, and mycological criteria.

MEASUREMENTS AND MAIN RESULTS

Of the 252 patients with severe CAP and 59 influenza patients evaluated, 24 met the diagnostic criteria for proven or probable Aspergillus infection in the CAP group and 9 patients in the influenza group, giving estimated prevalence values of 9.5% and 15.3%, respectively. COPD and the use of inhaled corticosteroids were independent risk factors for IPA. IPA in patients with severe CAP was significantly associated with the duration of mechanical support, the length of ICU stay, and the 28-day mortality.

CONCLUSIONS

An aggressive diagnostic approach for IPA patients with severe CAP and not only influenza or COVID-19 should be pursued. Further randomized controlled trials need to evaluate the timing, safety, and efficacy of antifungal therapy in reducing IPA incidence and improving clinical outcomes.

Machine Learning for Predicting Risk and Prognosis of Acute Kidney Disease in Critically Ill Elderly Patients During Hospitalization: Internet-Based and Interpretable Model Study

BACKGROUND

Acute kidney disease (AKD) affects more than half of critically ill elderly patients with acute kidney injury (AKI), which leads to worse short-term outcomes.

OBJECTIVE

We aimed to establish 2 machine learning models to predict the risk and prognosis of AKD in the elderly and to deploy the models as online apps.

METHODS

Data on elderly patients with AKI (n=3542) and AKD (n=2661) from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were used to develop 2 models for predicting the AKD risk and in-hospital mortality, respectively. Data collected from Xiangya Hospital of Central South University were for external validation. A bootstrap method was used for internal validation to obtain relatively stable results. We extracted the indicators within 24 hours of the first diagnosis of AKI and the fluctuation range of some indicators, namely delta (day 3 after AKI minus day 1), as features. Six machine learning algorithms were used for modeling; the area under the receiver operating characteristic curve (AUROC), decision curve analysis, and calibration curve for evaluating; Shapley additive explanation (SHAP) analysis for visually interpreting; and the Heroku platform for deploying the best-performing models as web-based apps.

RESULTS

For the model of predicting the risk of AKD in elderly patients with AKI during hospitalization, the Light Gradient Boosting Machine (LightGBM) showed the best overall performance in the training (AUROC=0.844, 95% CI 0.831-0.857), internal validation (AUROC=0.853, 95% CI 0.841-0.865), and external (AUROC=0.755, 95% CI 0.699-0.811) cohorts. In addition, LightGBM performed well for the AKD prognostic prediction in the training (AUROC=0.861, 95% CI 0.843-0.878), internal validation (AUROC=0.868, 95% CI 0.851-0.885), and external (AUROC=0.746, 95% CI 0.673-0.820) cohorts. The models deployed as online prediction apps allowed users to predict and provide feedback to submit new data for model iteration. In the importance ranking and correlation visualization of the model's top 10 influencing factors conducted based on the SHAP value, partial dependence plots revealed the optimal cutoff of some interventionable indicators. The top 5 factors predicting the risk of AKD were creatinine on day 3, sepsis, delta blood urea nitrogen (BUN), diastolic blood pressure (DBP), and heart rate, while the top 5 factors determining in-hospital mortality were age, BUN on day 1, vasopressor use, BUN on day 3, and partial pressure of carbon dioxide (PaCO2).

CONCLUSIONS

We developed and validated 2 online apps for predicting the risk of AKD and its prognostic mortality in elderly patients, respectively. The top 10 factors that influenced the AKD risk and mortality during hospitalization were identified and explained visually, which might provide useful applications for intelligent management and suggestions for future prospective research.

Determinants of acute kidney injury during high-power mechanical ventilation: secondary analysis from experimental data

BACKGROUND

The individual components of mechanical ventilation may have distinct effects on kidney perfusion and on the risk of developing acute kidney injury; we aimed to explore ventilatory predictors of acute kidney failure and the hemodynamic changes consequent to experimental high-power mechanical ventilation.

METHODS

Secondary analysis of two animal studies focused on the outcomes of different mechanical power settings, including 78 pigs mechanically ventilated with high mechanical power for 48 h. The animals were categorized in four groups in accordance with the RIFLE criteria for acute kidney injury (AKI), using the end-experimental creatinine: (1) NO AKI: no increase in creatinine; (2) RIFLE 1-Risk: increase of creatinine of > 50%; (3) RIFLE 2-Injury: two-fold increase of creatinine; (4) RIFLE 3-Failure: three-fold increase of creatinine; RESULTS: The main ventilatory parameter associated with AKI was the positive end-expiratory pressure (PEEP) component of mechanical power. At 30 min from the initiation of high mechanical power ventilation, the heart rate and the pulmonary artery pressure progressively increased from group NO AKI to group RIFLE 3. At 48 h, the hemodynamic variables associated with AKI were the heart rate, cardiac output, mean perfusion pressure (the difference between mean arterial and central venous pressures) and central venous pressure. Linear regression and receiving operator characteristic analyses showed that PEEP-induced changes in mean perfusion pressure (mainly due to an increase in CVP) had the strongest association with AKI.

CONCLUSIONS

In an experimental setting of ventilation with high mechanical power, higher PEEP had the strongest association with AKI. The most likely physiological determinant of AKI was an increase of pleural pressure and CVP with reduced mean perfusion pressure. These changes resulted from PEEP per se and from increase in fluid administration to compensate for hemodynamic impairment consequent to high PEEP.

Ketamine restriction correlates with reduced cholestatic liver injury and improved outcomes in critically ill patients with burn injury

Background & Aims

Ketamine-associated cholestatic liver injury is reported in patients with severe burn injury, but its association with patient outcome is unclear. We investigated the relationship between ketamine exposure, cholestatic liver injury, and outcome of critically ill patients with burn injury.

Methods

In a retrospective study, patients with severe burn injury were analysed across two periods: unrestricted ketamine prescription (ketamine-liberal) and capped ketamine dosage (ketamine-restricted). The primary endpoint was cholestatic liver injury, and the secondary endpoint was 3-month mortality. Binary logistic regression models and the revised electronic causality assessment method were used to measure the strength of associations and causality assessment, respectively.

Results

Of 279 patients (median age 51 [IQR 31-67] years; 63.1% men; burned surface area 28.5%, IQR 20-45%), 155 (56%) were in the ketamine-liberal group, and 124 (44%) were in the ketamine-restricted group, with comparable clinical characteristics, except for ketamine exposure (median doses 265.0 [IQR 0-8,021] mg and 20 [IQR 0-105] mg, respectively; p <0.001). A dose- and time-dependent relationship was observed between ketamine exposure and cholestatic liver injury. Ketamine restriction was associated with a reduced risk of cholestatic liver injury (adjusted odds ratio 0.16, 95% CI 0.04-0.50; p = 0.003) and with a higher probability of 3-month survival (p = 0.035). The revised electronic causality assessment method indicated that ketamine was probably and possibly the cause of cholestatic liver injury for 14 and 10 patients, respectively. Cholangitis was not observed in the ketamine-restricted group. In propensity-matched patients, the risk of 3-month mortality was higher (adjusted odds ratio 9.92, 95% CI 2.76-39.05; p = 0.001) in patients with cholestatic liver injury and ketamine exposure ≥10,000 mg. Other sedative drugs were not associated with liver and patient outcome.

Conclusions

In this cohort, ketamine restriction was associated with less cholestatic liver injury and reduced 3-month mortality.

Impact and implications

In a cohort of 279 critically ill patients with burn injury, ketamine was associated with a risk of liver bile duct toxicity. The risk was found to be dependent on both the dosage and duration of ketamine use. A restriction policy of ketamine prescription was associated with a risk reduction of liver injury and 3-month mortality. These findings have implications for the analgesia and sedation of critically ill patients with ketamine, with higher doses raising safety concerns.

Impact of acute kidney injury on major adverse cardiovascular events in intensive care survivors

Background

Acute kidney injury commonly occurs in patients admitted to ICU. After acute kidney injury, kidney function may not completely recover leading to increased risk of future cardiovascular events. We sought to ascertain the rates of cardiovascular events in ICU survivors and if these rates were affected by the presence of acute kidney injury whilst in ICU.

Methods

This retrospective observational cohort study utilised routinely collected data to identify patients who had survived an admission to one of two ICUs between July 2015 and June 2018. Baseline serum creatinine and subsequent values were used to identify acute kidney injury. Major adverse cardiovascular events described were myocardial injury, coronary artery intervention, or radiological evidence of stroke.

Results

Of the 3994 ICU survivors, major adverse cardiovascular events were identified in 385 patients (9.6%; 95% confidence interval [CI] 8.8-10.6%). Presence of acute kidney injury whilst in ICU was significantly associated with future major adverse cardiovascular events (hazard ratio=1.38; 95% CI 1.12-1.70; P-value=0.003) and future biochemical myocardial injury (hazard ratio=1.48; 95% CI 1.16-1.89; P-value=0.001). Acute kidney injury did not have a statistically significant association with future coronary artery interventions or future cerebrovascular events.

Conclusions

One in 10 ICU survivors experiences a major adverse cardiovascular event after discharge. Acute kidney injury whilst in ICU was associated with an increased risk of major adverse cardiovascular events and specifically myocardial injury. Further research is warranted on whether ICU survivors with acute kidney injury merit enhanced strategies for cardiovascular protection.

The Role of Oxidative Stress in Kidney Injury

Acute kidney injury and chronic kidney disease are among the most common non-communicable diseases in the developed world, with increasing prevalence. Patients with acute kidney injury are at an increased risk of developing chronic kidney disease. One of kidney injury's most common clinical sequelae is increased cardiovascular morbidity and mortality. In recent years, new insights into the pathophysiology of renal damage have been made. Oxidative stress is the imbalance favoring the increased generation of ROS and/or reduced body's innate antioxidant defense mechanisms and is of pivotal importance, not only in the development and progression of kidney disease but also in understanding the enhanced cardiovascular risk in these patients. This article summarizes and emphasizes the role of oxidative stress in acute kidney injury, various forms of chronic kidney disease, and also in patients on renal replacement therapy (hemodialysis, peritoneal dialysis, and after kidney transplant). Additionally, the role of oxidative stress in the development of drug-related nephrotoxicity and also in the development after exposure to various environmental and occupational pollutants is presented.

Peritoneal Dialysis in Critically Ill Patients: Time for a Critical Reevaluation?

Peritoneal dialysis (PD) as an AKI treatment in adults was widely accepted in critical care settings well into the 1980s. The advent of extracorporeal continuous KRT led to widespread decline in the use of PD for AKI across high-income countries. The lack of familiarity and comfort with the use of PD in critical care settings has also led to lack of use even among those receiving maintenance PD. Many critical care units reflexively convert patients receiving maintenance PD to alternative dialysis therapies at admission. Renewed interest in the use of PD for AKI therapy has emerged due to its increasing use in low- and middle-income countries. In high-income countries, the coronavirus disease 2019 (COVID-19) pandemic, saw PD for AKI used early on, where many critical care units were in crisis and relied on PD use when resources for other AKI therapy modalities were limited. In this review, we highlight advantages and disadvantages of PD in critical care settings and indications and contraindications for its use. We provide an overview of literature to support both PD treatment during AKI and its continuation as a maintenance therapy during critical illness. For AKI therapy, we further discuss establishment of PD access, PD prescription management, and complication monitoring and treatment. Finally, we discuss expansion in the use of PD for AKI therapy extending beyond its role during times of resource constraints.

Establishment and external validation of an online dynamic nomogram for predicting in-hospital death risk in sepsis-associated acute kidney disease

OBJECTIVES

Approximately one-third of patients with sepsis-associated acute kidney injury (AKI) progress to acute kidney disease (AKD) with higher short-term mortality. We aimed to identify the clinical characteristics that influence in-hospital death in sepsis-associated AKD and develop a nomogram to facilitate early warning.

METHODS

Logical regression was applied to screen variables based on clinical data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. A nomogram was established to predict in-hospital death risk in patients with sepsis-associated AKD. The eICU Collaborative Research Database (eICU-CRD) was used for external validation. The receiver operating characteristic and calibration curves were used to determine the model's performance.

RESULTS

A total of 1,779 patients with sepsis-associated AKD were included from the MIMIC-IV and 344 from the eICU-CRD. Age, Glasgow coma scale score, systolic blood pressure, peripheral oxygen saturation, platelet count, white blood cell count, and bicarbonate levels were significantly correlated with death. The nomogram demonstrated high discrimination in the training (C-index, 0.829; 95% confidence interval [CI] [0.807-0.852]) and testing sets (C-index: 0.760; 95% CI [0.706-0.814]). At the optimal cut-off value of 0.270, the model's sensitivity in the training and validation datasets was 72.8% (95% CI [68.3-76.9%]) and 64.5% (95% CI [54.9-73.4%]), while the specificity was 79.2% (95% CI [76.9-81.4%]) and 74.8% (95% CI [68.7-80.2%]), respectively.

CONCLUSION

We identified seven predictors of in-hospital death in patients with sepsis-associated AKD. In addition, we developed an online dynamic nomogram to accurately and conveniently predict short-term outcomes, which performed well in the external dataset.

Update on prognosis driven classification of pediatric AKI

Acute kidney injury (AKI) affects a large proportion of hospitalized children and increases morbidity and mortality in this population. Initially thought to be a self-limiting condition with uniformly good prognosis, we now know that AKI can persist and progress to acute kidney disease (AKD) and chronic kidney disease (CKD). AKI is presently categorized by stage of injury defined by increase in creatinine, decrease in eGFR, or decrease in urine output. These commonly used biomarkers of acute kidney injury do not change until the injury is well established and are unable to detect early stage of the disease when intervention is likely to reverse injury. The kidneys have the ability to compensate and return serum creatinine to a normal or baseline level despite nephron loss in the setting of AKI possibly masking persistent dysfunction. Though these definitions are important, classifying children by their propensity for progression to AKD and CKD and defining these risk strata by other factors besides creatinine may allow for better prognosis driven discussion, expectation setting, and care for our patients. In order to develop a classification strategy, we must first be able to recognize children who are at risk for AKD and CKD based on modifiable and non-modifiable factors as well as early biomarkers that identify their risk of persistent injury. Prevention of initial injury, prompt evaluation and treatment if injury occurs, and mitigating further injury during the recovery period may be important factors in decreasing risk of AKD and CKD after AKI. This review will cover presently used definitions of AKI, AKD, and CKD, recent findings in epidemiology and risk factors for AKI to AKD to CKD progression, novel biomarkers for early identification of AKI and AKI that may progress to CKD and future directions for improving outcome in children with AKI.