Plasma Biomarkers in Predicting Renal Recovery from Acute Kidney Injury in Critically Ill Patients

Assessment of the renal angina index in patients hospitalized in a cardiac intensive care unit

The renal angina index (RAI) is a validated scoring tool for predicting acute kidney injury (AKI). We investigated the efficacy of the RAI in 2436 heterogeneous patients (mean age, 70 years) treated in cardiac intensive care units (CICUs). The RAI was calculated from creatinine and patient condition scores. AKI was diagnosed by the Kidney Disease: Improving Global Outcome criteria. The primary and secondary endpoints were the development of severe AKI and all-cause mortality, respectively. Four hundred thirty-three patients developed AKI, 87 of them severe. In multivariate analyses, the RAI was a significant independent predictor of severe AKI. During the 12-month follow-up period, 210 patients suffered all-cause death. Elevated RAI was independently associated with all-cause mortality, as was NT-proBNP (p < 0.001). The RAI is a potent predictor not only of severe AKI but also of adverse outcomes and substantially improved the 12-month risk stratification of patients hospitalized in CICUs.

Prognostic Value of Natriuretic Peptide Levels for Adverse Renal Outcomes in Patients With Moderate to Severe Acute Kidney Injury With or Without Heart Failure

Background Natriuretic peptides have been recommended as biomarkers for the diagnosis and prognosis of patients with heart failure and are often elevated in the setting of acute kidney injury. We sought to demonstrate the associations between increased baseline NT-proBNP (N-terminal pro-B-type natriuretic peptide) and adverse renal outcomes in patients with moderate-to-severe acute kidney injury. Methods and Results We reviewed electronic medical records of consecutive patients with acute kidney injury stage 2 and 3 admitted to the Cleveland Clinic between September 2011 and December 2021. Patients with NT-proBNP levels collected before renal consultation or dialysis initiation were included. Adverse renal outcomes included dialysis requirement and dialysis dependence defined as patients undergoing dialysis within 72 hours before hospital discharge or in-hospital mortality. In our study cohort (n=3811), 2521 (66%) patients underwent dialysis, 1619 (42%) patients became dialysis dependent, and 1325 (35%) patients had in-hospital mortality. After adjusting for cardiorenal risk factors, compared with the lowest quartile, the highest quartile of NT-proBNP (≥18 215 pg/mL) was associated with increased likelihood of dialysis requirement (adjusted odds ratio [OR], 2.36 [95% CI, 1.87-2.99]), dialysis dependence (adjusted OR, 1.89 [95% CI, 2.53-1.34]), and in-hospital mortality (adjusted OR, 1.34 [95% CI, 1.01-1.34]). Conclusions Increased NT-proBNP was associated with an increased risk of dialysis requirement, becoming dialysis dependent, and in-hospital mortality in patients with moderate-to-severe acute kidney injury.

Subgroups of Patients with Distinct Health Utility Profiles after AKI

Key Points

Health utility profiles can be identified at 60 days after AKI. Patient subgroups with distinct health utility profiles have different characteristics at index hospitalization and outcomes at 1 year. These profiles may be useful when considering resources to improve the physical and emotional health of patients after AKI.

Background

A large amount of interindividual variability exists in health-related quality of life outcomes after AKI. This study aimed to determine whether subgroups of early AKI survivors could be identified on the basis of distinct health utility impairment profiles ascertained at 60 days after AKI and whether these subgroups differed in clinical and biomarker characteristics at index hospitalization and outcomes at 1-year follow-up.

Methods

This retrospective analysis used data from the Biologic Markers of Renal Recovery for the Kidney study, an observational subcohort of the Acute Renal Failure Trial Network study. Of 402 patients who survived to 60 days after AKI, 338 completed the Health Utility Index 3 survey, which measures impairments in eight health attributes. Latent class analysis was used to identify subgroups of patients with distinct health utility profiles.

Results

Three subgroups with distinct health utility impairment profiles were identified: Low (28% of participants), Moderate (58%), and High (14%) with a median of one, four, and six impairments across the eight health attributes at 60 days after AKI, respectively. Patient subgroups differed in weight, history of cerebrovascular disease, intensity of dialysis, hospital length of stay, and dialysis dependence. Serum creatinine and blood urea nitrogen at index hospitalization did not differ among the three subgroups. The High impairment subgroup had higher levels of IL-6 and soluble TNF receptor 2 at study day 1. The three subgroups had different 1-year mortality rates: 5% in the Low, 21% in the Moderate, and 52% in the High impairment subgroup.

Conclusion

Patient subgroups with distinct health utility impairment profiles can be identified 60 days after AKI. These subgroups have different characteristics at index hospitalization. A higher level of impairment at 60 days was associated with decreased 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.

Application of Machine Learning to Predict Acute Kidney Disease in Patients With Sepsis Associated Acute Kidney Injury

Background: Sepsis-associated acute kidney injury (AKI) is frequent in patients admitted to intensive care units (ICU) and may contribute to adverse short-term and long-term outcomes. Acute kidney disease (AKD) reflects the adverse events developing after AKI. We aimed to develop and validate machine learning models to predict the occurrence of AKD in patients with sepsis-associated AKI. Methods: Using clinical data from patients with sepsis in the ICU at Beijing Friendship Hospital (BFH), we studied whether the following three machine learning models could predict the occurrence of AKD using demographic, laboratory, and other related variables: Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM), decision trees, and logistic regression. In addition, we externally validated the results in the Medical Information Mart for Intensive Care III (MIMIC III) database. The outcome was the diagnosis of AKD when defined as AKI prolonged for 7-90 days according to Acute Disease Quality Initiative-16. Results: In this study, 209 patients from BFH were included, with 55.5% of them diagnosed as having AKD. Furthermore, 509 patients were included from the MIMIC III database, of which 46.4% were diagnosed as having AKD. Applying machine learning could successfully achieve very high accuracy (RNN-LSTM AUROC = 1; decision trees AUROC = 0.954; logistic regression AUROC = 0.728), with RNN-LSTM showing the best results. Further analyses revealed that the change of non-renal Sequential Organ Failure Assessment (SOFA) score between the 1st day and 3rd day (Δnon-renal SOFA) is instrumental in predicting the occurrence of AKD. Conclusion: Our results showed that machine learning, particularly RNN-LSTM, can accurately predict AKD occurrence. In addition, Δ SOFAnon-renal plays an important role in predicting the occurrence of AKD.

Current Approach to Successful Liberation from Renal Replacement Therapy in Critically Ill Patients with Severe Acute Kidney Injury: The Quest for Biomarkers Continues

Recovery of sufficient kidney function to liberate patients with severe acute kidney injury (AKI-D) from renal replacement therapy (RRT) is recognized as a vital patient-centred outcome. However, no clinical consensus guideline provides specific recommendations on when and how to stop RRT in anticipation of renal recovery from AKI-D. Currently, wide variations in clinical practice regarding liberation from RRT result in early re-start of RRT to treat uraemia after premature liberation or in the unnecessary prolonged exposure of unwell patients after late liberation. Observational studies, predominantly retrospective in nature, have attempted to assess numerous surrogate markers of kidney function or of biomarkers of kidney damage to predict successful liberation from RRT. However, a substantial heterogeneity in the timing of measurement and cut-off values of most biomarkers across studies allows no pooling of data, and impedes the comparison of outcomes from such studies. The accuracy of most traditional and novel biomarkers cannot be assessed reliably. Currently, the decision to discontinue RRT in AKI-D patients relies on daily clinical assessments of the patient’s status supplemented by measurement of creatinine clearance (> 15 ml/min) and 24-h urine output (> 2000 ml/min with diuretics). Clinical trials objectively comparing the success of validated biomarkers for guiding optimal timed liberation from RRT in AKI-D will be required to provide high-quality evidence for guidelines.