Development of a risk stratification-based model for prediction of acute kidney injury in critically ill patients

Prevalence and Mortality Rates of Acute Kidney Injury among Critically Ill Patients: A Retrospective Study

Acute kidney injury (AKI) poses a significant challenge in critically ill patients. To determine the prevalence, risk factors, and mortality rate of AKI among nonsurgical critically ill patients in Jordan University Hospital, we conducted a retrospective study using a consecutive sampling method, including 457 nonsurgical critically ill patients admitted to the medical intensive care unit (MICU) from January to June 2021. The mean age was 63.8 ± 18 years, with 196 (42.8%) developing AKI during their stay in the MICU. Among AKI nonsurgical patients, pulmonary diseases (n = 52; 34.5%) emerged as the primary cause for admission, exhibiting the highest prevalence, followed by sepsis (n = 40; 20.4%). Furthermore, we found that older age (adjusted OR (AOR): 1.04; 95% confidence interval (CI): 1.04-1.06; p = 0.003), preadmission use of diuretics (AOR: 2.12; 95% CI: 1.06-4.25; p = 0.03), use of ventilators (2.19; 95% CI: 1.12-2.29; p = 0.02), and vasopressor use during MICU stay (AOR: 4.25; 95% CI: 2.1308.47; p = 0.001) were observed to have higher mortality rates. Prior utilization of statins before admission exhibited a significant association with reduced mortality rate (AOR: 0.42; 95% CI: 0.2-0.85; p = 0.02). Finally, AKI was associated with a higher mortality rate during MICU stay (AOR: 2.44; 95% CI: 1.07-5.56; p = 0.03). The prevalence of AKI among nonsurgical patients during MICU stay is higher than what has been reported previously in the literature, which highlights the nuanced importance of identifying more factors contributing to AKI in developing countries, and hence providing preventive measures and adhering to global strategies are recommended.

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.

The Association between COVID-19 Infection and Kidney Damage in a Regional University Hospital

Background and Objectives: Kidneys are one of the main targets for SARS-CoV-2. Early recognition and precautionary management are essential in COVID-19 patients due to the multiple origins of acute kidney injury and the complexity of chronic kidney disease management. The aims of this research were to investigate the association between COVID-19 infection and renal injury in a regional hospital. Materials and Methods: The data of 601 patients from the Vilnius regional university hospital between 1 January 2020 and 31 March 2021 were collected for this cross-sectional study. Demographic data (gender, age), clinical outcomes (discharge, transfer to another hospital, death), length of stay, diagnoses (chronic kidney disease, acute kidney injury), and laboratory test data (creatinine, urea, C-reactive protein, potassium concentrations) were collected and analyzed statistically. Results: Patients discharged from the hospital were younger (63.18 ± 16.02) than those from the emergency room (75.35 ± 12.41, p < 0.001), transferred to another hospital (72.89 ± 12.06, p = 0.002), or who died (70.87 ± 12.83, p < 0.001). Subsequently, patients who died had lower creatinine levels on the first day than those who survived (185.00 vs. 311.17 µmol/L, p < 0.001), and their hospital stay was longer (Spearman's correlation coefficient = -0.304, p < 0.001). Patients with chronic kidney disease had higher first-day creatinine concentration than patients with acute kidney injury (365.72 ± 311.93 vs. 137.58 ± 93.75, p < 0.001). Patients with acute kidney injury and chronic kidney disease complicated by acute kidney injury died 7.81 and 3.66 times (p < 0.001) more often than patients with chronic kidney disease alone. The mortality rate among patients with acute kidney injury was 7.79 (p < 0.001) times higher than among patients without these diseases. Conclusions: COVID-19 patients who developed acute kidney injury and whose chronic kidney disease was complicated by acute kidney injury had a longer hospital stay and were more likely to die.

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.

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.

Predicting Risk Factors of Acute Kidney Injury in the First 7 Days after Admission: Analysis of a Group of Critically Ill Patients

Background

Acute kidney injury (AKI) is a common complication in critically ill patients. Some predictive models have been reported, but the conclusions are controversial. The aim of this study was the formation of nomograms to predict risk factors for AKI in critically ill patients within the first 7 days after admission to the intensive care unit (ICU).

Methods

Data were extracted from the Medical Information Mart for Intensive Care- (MIMIC-) III database. The random forest method was used to fill in the missing values, and least absolute shrinkage and selection operator (Lasso) regression analysis was performed to screen for possible risk factors.

Results

A total of 561 patients were enrolled. Complication with AKI is significantly associated with a longer length of stay (LOS). For all patients, the predictors contained in the prediction nomogram included hypertension, coronary artery disease (CAD), cardiopulmonary bypass (CPB), coronary artery bypass grafting (CABG), Simplified Acute Physiology Score II (SAPS II), central venous pressure (CVP) measured for the first time after admission, and maximum and minimum mean artery pressure (MAP). The model showed good discrimination (C - index = 0.818, 95% CI: 0.779-0.857). In the subgroup of patients with well-controlled blood glucose levels, the significant predictors included hypertension, CABG, CPB, SAPS II, and maximum and minimum MAP. Good discrimination was also present before (C - index = 0.785, 95% CI: 0.736-0.834) and after adjustment (adjusted C - index = 0.770).

Conclusion

Hypertension, CAD, CPB, CABG, SAPS II, CVP measured for the first time after admission, and maximum and minimum MAP were independent risk factors for AKI in critically ill patients.

Activating Transcription Factor 3 Based Early Alarm Model of Acute Kidney Injury after Cardiopulmonary Bypass in Adults

Acute kidney injury (AKI) is a common complication after cardiopulmonary bypass (CPB) for cardiac surgery, and there is no effective treatment. This study was aimed at constructing an early warning model of AKI after CPB in adults and investigating the performance of this model. Patients who underwent CPB in the Department of Cardiac Surgery, Shanghai Tenth People's Hospital, from January 2018 to December 2019 were recruited into the present study. Blood and urine samples were collected preoperatively (0 h) and 2 h, 6 h, 12 h, 24 h, and 48 h after surgery, and the creatinine and activating transcription factor 3 (ATF3) were detected. According to the diagnostic criteria of AKI, patients were divided into the AKI group and the non-AKI group, and the risk factors for AKI after CPB were screened. The receiver operating characteristic (ROC) curve analysis was used to identify the optimal biomarkers for the establishment of early warning model of AKI after CPB. Finally, the performance of this model was further verified. A total of 83 patients were included in this study, 42 of whom developed AKI after surgery. After CPB, the serum and urine levels of creatinine and ATF3 increased to different degrees, and the increase in urine ATF3 was the most obvious in the AKI group. The area under ROC (AUC) of urine ATF3 at 12 h after surgery was 0.691 (95% CI: 0.576-0.807). When ATF3 was higher than 1216 pg/mL, the sensitivity and specificity of ATF3 in the diagnosis of AKI were 0.43 and 0.85, respectively. The height, conjugated bilirubin on the surgery day, urine ATF3 12 h after surgery, and serum creatinine 24 h after surgery were independent risk factors for postoperative AKI. Urine ATF3 and other factors were used to establish AKI warning model after CPB, which showed good fitting and accuracy. In conclusion, ATF3 is an early biomarker of post-CPB AKI. Addition of urine ATF3 to AKI risk factors can improve the accuracy of early AKI prediction.

Risk factors and prognosis for COVID-19-induced acute kidney injury: a meta-analysis

OBJECTIVE

To analyse the incidence, risk factors and impact of acute kidney injury (AKI) on the prognosis of patients with COVID-19.

DESIGN

Meta-analysis.

DATA SOURCES

PubMed, Embase, CNKI and MedRxiv of Systematic Reviews from 1 January 2020 to 15 May 2020.

STUDY SELECTION

Studies examining the following demographics and outcomes were included: patients' age; sex; incidence of and risk factors for AKI and their impact on prognosis; COVID-19 disease type and incidence of continuous renal replacement therapy (CRRT) administration during COVID-19 infection.

RESULTS

A total of 79 research articles, including 49 692 patients with COVID-19, met the systemic evaluation criteria. The mortality rate and incidence of AKI in patients with COVID-19 in China were significantly lower than those in patients with COVID-19 outside China. A significantly higher proportion of patients with COVID-19 from North America were aged ≥65 years and also developed AKI. European patients with COVID-19 had significantly higher mortality and a higher CRRT rate than patients from other regions. Further analysis of the risk factors for COVID-19 combined with AKI showed that age ≥60 years and severe COVID-19 were independent risk factors for AKI, with an OR of 3.53, 95% CI (2.92-4.25) and an OR of 6.07, 95% CI (2.53-14.58), respectively. The CRRT rate in patients with severe COVID-19 was significantly higher than in patients with non-severe COVID-19, with an OR of 6.60, 95% CI (2.83-15.39). The risk of death in patients with COVID-19 and AKI was significantly increased, with an OR of 11.05, 95% CI (9.13-13.36).

CONCLUSION

AKI was a common and serious complication of COVID-19. Older age and having severe COVID-19 were independent risk factors for AKI. The risk of in-hospital death was significantly increased in patients with COVID-19 complicated by AKI.

Association of gender, age, and race on renal outcomes and mortality in patients with severe sepsis and septic shock

BACKGROUND

The association of age, gender and race with renal outcomes in patients with severe sepsis and septic shock (SEP) is not completely elucidated. We aimed to shed light on these relationships.

METHODS

We performed a retrospective cohort study of hospitalized patients in the USA discharged between January 1st, 2005 and December 31st, 2014 using the National Inpatient Sample. We adjusted analyses using the Charlson comorbidity index.

RESULTS

65,772,607 records were included of which 1,064,790 had SEP. There were 60% female and 12% African American (AA). The incidence of SEP was 1.6% and patients with SEP were older, had more AA and less females. Acute kidney injury (AKI) and mortality among patients with SEP were 62% and 30.7% respectively. AA race was associated with increased risk of SEP, AKI and dialysis, (OR = 1.12, 1.25 and 1.7 respectively, all p < 0.001). Female gender was associated with lower risk of all measured outcomes with odds ratios ranging from 0.65 to 0.78 (p < 0.001). Increasing age was associated with a higher risk of all outcomes except for dialysis.

CONCLUSION

Female gender is associated with a lower risk of poor renal outcomes and death among patients with SEP, while AA race places patients at higher risk of poor outcomes in that setting. Increasing age is generally associated with adverse outcomes.

Effect of renal support therapy on 5-year survival in patients discharged from the intensive care unit

Background

Between 30 and 70% of patients admitted to the intensive care unit (ICU) have acute kidney injury (AKI), and 10% of these patients will require renal replacement therapy (RRT). A significant number of studies have compared the mortality of patients who require RRT versus those who do not require it, finding an increase in mortality rates in the short and medium term; however, few studies have evaluated the long-term survival in a mixture of patients admitted to the ICU.

Objective

To evaluate the impact of RRT on 5-year survival in patients with AKI admitted to the ICU.

Methods

Using administrative databases of insurers of the Colombian health system, a cohort of patients admitted to the ICU between 1 January 2012 and 31 December 2013 was followed until 31 December 2018. ICD-10 diagnoses, procedure codes, and prescribed medications were used to establish the frequencies of the comorbidities included in the Charlson index. Patients were followed for at least 5 years to evaluate survival and establish the adjusted risks by propensity score matching.

Results

Of the 150,230 patients admitted to the ICU, 4366 (2.9%) required RRT in the ICU. Mortality rates for patients with RRT vs no RRT evaluated at ICU discharge, 1 year, and 5 years were 35%, 57.4%, and 67.9% vs 7.4%, 17.6%, and 30.1%, respectively. After propensity score matching, the hazard ratio was calculated for patients who received RRT and those who did not (HR, 2.46; 95% CI 2.37 to 2.56; p < 0.001), with a lower difference in years of survival for patients with RRT (mean effect in the treated) of - 1.86 (95% CI - 2.01 to to1.65; p < 0.001).

Conclusions

The impact of acute renal failure with the consequent need for RRT in patients admitted to the ICU is reflected in a decrease of approximately one quarter in 5-year survival, regardless of the different comorbidities.

AKI!Now Initiative: Recommendations for Awareness, Recognition, and Management of AKI

The American Society of Nephrology has established a new initiative, AKI!Now, with the goal of promoting excellence in the prevention and treatment of AKI by building a foundational program that transforms education and delivery of AKI care, aiming to reduce morbidity and associated mortality and to improve long-term outcomes. In this article, we describe our current efforts to improve early recognition and management involving inclusive interdisciplinary collaboration between providers, patients, and their families; discuss the ongoing need to change some of our current AKI paradigms and diagnostic methods; and provide specific recommendations to improve AKI recognition and care. In the hospital and the community, AKI is a common and increasingly frequent condition that generates risks of adverse events and high costs. Unfortunately, patients with AKI may frequently have received less than optimal quality of care. New classifications have facilitated understanding of AKI incidence and its impact on outcomes, but they are not always well aligned with AKI pathophysiology. Despite ongoing research efforts, treatments to promote or hasten kidney recovery remain ineffective. To avoid progression, the current approach to AKI emphasizes the promotion of early recognition and timely response. However, a lack of awareness of the importance of early recognition and treatment among health care team members and the heterogeneity of approaches within the health care teams assessing the patient remains a major challenge. Early identification is further complicated by differences in settings where AKI occurs (the community or the hospital), and by differences in patient populations and cultures between the intensive care unit and ward environments. To address these obstacles, we discuss the need to improve education at all levels of care and to generate specific guidance on AKI evaluation and management, including the development of a widely applicable education and an AKI management toolkit, engaging hospital administrators to incorporate AKI as a quality initiative, and raising awareness of AKI as a complication of other disease processes.