New diagnostics for AKI in critically ill patients: what to expect in the future

Identification and validation of an explainable prediction model of acute kidney injury with prognostic implications in critically ill children: a prospective multicenter cohort study

Background

Acute kidney injury (AKI) is a common and serious organ dysfunction in critically ill children. Early identification and prediction of AKI are of great significance. However, current AKI criteria are insufficiently sensitive and specific, and AKI heterogeneity limits the clinical value of AKI biomarkers. This study aimed to establish and validate an explainable prediction model based on the machine learning (ML) approach for AKI, and assess its prognostic implications in children admitted to the pediatric intensive care unit (PICU).

Methods

This multicenter prospective study in China was conducted on critically ill children for the derivation and validation of the prediction model. The derivation cohort, consisting of 957 children admitted to four independent PICUs from September 2020 to January 2021, was separated for training and internal validation, and an external data set of 866 children admitted from February 2021 to February 2022 was employed for external validation. AKI was defined based on serum creatinine and urine output using the Kidney Disease: Improving Global Outcome (KDIGO) criteria. With 33 medical characteristics easily obtained or evaluated during the first 24 h after PICU admission, 11 ML algorithms were used to construct prediction models. Several evaluation indexes, including the area under the receiver-operating-characteristic curve (AUC), were used to compare the predictive performance. The SHapley Additive exPlanation method was used to rank the feature importance and explain the final model. A probability threshold for the final model was identified for AKI prediction and subgrouping. Clinical outcomes were evaluated in various subgroups determined by a combination of the final model and KDIGO criteria.

Findings

The random forest (RF) model performed best in discriminative ability among the 11 ML models. After reducing features according to feature importance rank, an explainable final RF model was established with 8 features. The final model could accurately predict AKI in both internal (AUC = 0.929) and external (AUC = 0.910) validations, and has been translated into a convenient tool to facilitate its utility in clinical settings. Critically ill children with a probability exceeding or equal to the threshold in the final model had a higher risk of death and multiple organ dysfunctions, regardless of whether they met the KDIGO criteria for AKI.

Interpretation

Our explainable ML model was not only successfully developed to accurately predict AKI but was also highly relevant to adverse outcomes in individual children at an early stage of PICU admission, and it mitigated the concern of the "black-box" issue with an undirect interpretation of the ML technique.

Funding

The National Natural Science Foundation of China, Jiangsu Province Science and Technology Support Program, Key talent of women's and children's health of Jiangsu Province, and Postgraduate Research & Practice Innovation Program of Jiangsu Province.

Association between triglyceride-glucose index and AKI in ICU patients based on MIMICIV database: a cross-sectional study

BACKGROUND

Methods for early prediction of the occurrence of acute kidney injury (AKI) were limited. The relationship between triglyceride glucose index (TyG) and the incidence of acute kidney injury in ICU patients is unclear. This study aims to explore the relationship between the two.

METHODS

Based on their TyG index, participants from the Intensive Care Medical Information Market IV (MIMIC-IV) were divided into quartiles. A logistic regression model was constructed based on the risk of acute kidney injury as the main outcome, in order to detect a potential relationship that may exist between the TyG index and acute kidney injury in ICU patients. Finally, in order to confirm the relationship existing between the TyG index and the results, a restricted cubic spline model was used.

RESULTS

In total, 54,263 patients were involved in our present study, of whom 48.2% were male. The occurrence of acute kidney injury was 25.1%. An independent relationship was observed between the TyG index and an increased risk of acute kidney injury through multivariate logistic regression analysis (OR, 1.28 [95% CI 1.22-1.35] p < 0.001). Q4 (5.344-9.911) of the TyG index quartiles was independently associated with an increase in the risk of acute kidney injury (OR, 1.43 [95% CI (1.32-1.54)] p < 0.001). Through the restricted cubic spline regression model, the risk of acute kidney injury was also demonstrated to increase linearly with an increase in the TyG index.

CONCLUSION

The triglyceride glucose index is related to the risk of acute kidney injury in ICU patients. In the future, in order to further validate this finding, larger prospective studies are needed.

Subclinical and clinical acute kidney injury share similar urinary peptide signatures and prognosis

PURPOSE

Acute kidney injury (AKI) is a frequent and severe condition in intensive care units (ICUs). In 2020, the Acute Dialysis Quality Initiative (ADQI) group proposed a new stage of AKI, referred to as stage 1S, which represents subclinical disease (sAKI) defined as a positive biomarker but no increase in serum creatinine (sCr). This study aimed to determine and compare the urinary peptide signature of sAKI as defined by biomarkers.

METHODS

This is an ancillary analysis of the prospective, observational, multinational FROG-ICU cohort study. AKI was defined according to the Kidney Disease Improving Global Outcome definition (AKIKDIGO). sAKI was defined based on the levels of the following biomarkers, which exceeded the median value: neutrophil gelatinase-associated lipocalin (pNGAL, uNGAL), cystatin C (pCysC, uCysC), proenkephalin A 119-159 (pPENKID) and liver fatty acid binding protein (uLFABP). Urinary peptidomics analysis was performed using capillary electrophoresis-mass spectrometry. Samples were collected at the time of study inclusion.

RESULTS

One thousand eight hundred eighty-five patients had all biomarkers measured at inclusion, which included 1154 patients without AKI (non-AKIKDIGO subgroup). The non-AKIKDIGO subgroup consisted of individuals at a median age of 60 years [48, 71], among whom 321 (27.8%) died. The urinary peptide signatures of sAKI, regardless of the biomarkers used for its definition, were similar to the urinary peptide signatures of AKIKDIGO (inflammation, haemolysis, and endothelial dysfunction). These signatures were also associated with 1-year mortality.

CONCLUSION

Biomarker-defined sAKI is a common and severe condition observed in patients within intensive care units with a urinary peptide signature that is similar to that of AKI, along with a comparable prognosis.

Epidemiology and outcomes of early-onset AKI in COVID-19-related ARDS in comparison with non-COVID-19-related ARDS: insights from two prospective global cohort studies

BACKGROUND

Acute kidney injury (AKI) is a frequent and severe complication of both COVID-19-related acute respiratory distress syndrome (ARDS) and non-COVID-19-related ARDS. The COVID-19 Critical Care Consortium (CCCC) has generated a global data set on the demographics, management and outcomes of critically ill COVID-19 patients. The LUNG-SAFE study was an international prospective cohort study of patients with severe respiratory failure, including ARDS, which pre-dated the pandemic.

METHODS

The incidence, demographic profile, management and outcomes of early AKI in patients undergoing invasive mechanical ventilation for COVID-19-related ARDS were described and compared with AKI in a non-COVID-19-related ARDS cohort.

RESULTS

Of 18,964 patients in the CCCC data set, 1699 patients with COVID-19-related ARDS required invasive ventilation and had relevant outcome data. Of these, 110 (6.5%) had stage 1, 94 (5.5%) had stage 2, 151 (8.9%) had stage 3 AKI, while 1214 (79.1%) had no AKI within 48 h of initiating invasive mechanical ventilation. Patients developing AKI were older and more likely to have hypertension or chronic cardiac disease. There were geo-economic differences in the incidence of AKI, with lower incidence of stage 3 AKI in European high-income countries and a higher incidence in patients from middle-income countries. Both 28-day and 90-day mortality risk was increased for patients with stage 2 (HR 2.00, p < 0.001) and stage 3 AKI (HR 1.95, p < 0.001). Compared to non-COVID-19 ARDS, the incidence of shock was reduced with lower cardiovascular SOFA score across all patient groups, while hospital mortality was worse in all groups [no AKI (30 vs 50%), Stage 1 (38 vs 58%), Stage 2 (56 vs 74%), and Stage 3 (52 vs 72%), p < 0.001]. The time profile of onset of AKI also differed, with 56% of all AKI occurring in the first 48 h in patients with COVID-19 ARDS compared to 89% in the non-COVID-19 ARDS population.

CONCLUSION

AKI is a common and serious complication of COVID-19, with a high mortality rate, which differs by geo-economic location. Important differences exist in the profile of AKI in COVID-19 versus non-COVID-19 ARDS in terms of their haemodynamic profile, time of onset and clinical outcomes.

Contrast-enhanced ultrasound in evaluating the severity of acute kidney injury: An animal experimental study

PURPOSE

Early assessment of the severity of acute kidney injury (AKI) is critical to the prognosis of patients. Renal microcirculation hemodynamic changes and inflammatory response are the essential links of AKI induced by ischemia-reperfusion injury (IRI). This study aims to explore the value of contrast-enhanced ultrasound (CEUS) based on vascular cell adhesion molecule-1 (VCAM-1) targeted microbubbles (TM) in evaluating the renal microcirculation hemodynamics and inflammatory response of different severity of AKI.

METHODS

Eighteen male C57BL/6J mice were randomly divided into three groups (n = 6): sham operation (sham) group, mild IRI-AKI (m-AKI) group, and severe IRI-AKI (s-AKI) group. CEUS based on VCAM-1 TM was used to evaluate renal microcirculation perfusion and inflammatory response. Pearson's correlation was used to analyze the correlation between ultrasonic variables and pro-inflammatory factors.

RESULTS

Compared with the sham group, AUC in m-AKI and s-AKI groups was significantly decreased, and s-AKI group was lower than m-AKI group (P < 0.05). NID of m-AKI and s-AKI groups was significantly higher than that of the sham group, and s-AKI group was higher than that of m-AKI group (P < 0.05). There was a linear positive correlation between NID and VCAM-1 protein expression (r = 0.7384, P < 0.05). NID and AUC were correlated with TNF-α and IL-6 levels (P < 0.05). Compared with early AKI biomarkers, CEUS based on VCAM-1 TM has higher sensitivity in evaluating the severity of AKI.

CONCLUSIONS

CEUS based on VCAM-1 TM can evaluate renal microcirculation perfusion and inflammatory response in mild and severe AKI, which may provide helpful information for assessing the severity of AKI.