Using kinetic eGFR to identify acute kidney injury risk in children undergoing cardiac transplantation

[Current clinical application of glomerular filtration rate assessment methods in pediatric populations]

Glomerular filtration rate (GFR) is a critical indicator of renal function assessment, which exhibits age-dependency in children and may differ from adults under various disease conditions. In recent years, there has been a growing focus on GFR among scholars, with an increasing number of clinical studies dedicated to refining and optimizing GFR estimation to span all pediatric age groups. However, the methods and assessment equations for estimating GFR may vary under different disease conditions, affecting the accuracy and applicability of assessments. This article reviews the peculiarities of renal function in children, explores GFR measurement methods, and evaluates the application of various GFR assessment equations in pediatric clinical practice, providing a reference for clinical assessment of renal function in children.

Kinetic Estimated Glomerular Filtration Rate in Predicting Paediatric Acute Kidney Disease

Kinetic estimation of glomerular filtration rate (KeGFR) has proved its utility in predicting acute kidney injury (AKI) in both adults and children. Our objective is to assess the clinical utility of KeGFR in predicting AKI severity and progression to acute kidney disease (AKD) in patients already diagnosed with AKI and to examine major adverse kidney events at 30 days (MAKE30). We retrospectively calculated the KeGFR within the first 24 h of identified AKI (KeGFR1) and in the 24 h prior to AKD (KeGFR2) in all admitted children under 18 years old. The cohort consisted of 803 patients with AKI. We proposed a new classification of KeGFR stages, from 1 to 5, and assessed the predictive value of KeGFR stages for AKD development and MAKE30. AKI severity was associated with lower KeGFRs. KeGFR1 and KeGFR2 predicted AKD with AUC values between 0.777 and 0.841 respectively, p < 0.001. KeGFR2 had the best performance in predicting MAKE30 (AUC of 0.819) with a sensitivity of 66.67% and specificity 87.7%. KeGFR1 stage 3, 4 and 5 increased the risk of AKD by 3.07, 6.56 and 28.07 times, respectively, while KeGFR2 stage 2, 3, 4 and 5 increased the risk of AKD 2.79, 3.58, 32.75 and 80.14 times. Stage 5 KeGFR1 and KeGFR2 stages 3, 4 and 5 increased the risk of MAKE30 by 7.77, 4.23. 5.89 and 69.42 times in the adjusted models. KeGFR proved to be a useful tool in AKI settings. KeGFR dynamics can predict AKI severity, duration and outcomes.

Machine learning in predicting cardiac surgery-associated acute kidney injury: A systemic review and meta-analysis

Background

Cardiac surgery-associated acute kidney injury (CSA-AKI) is a common complication following cardiac surgery. Early prediction of CSA-AKI is of great significance for improving patients' prognoses. The aim of this study is to systematically evaluate the predictive performance of machine learning models for CSA-AKI.

Methods

Cochrane Library, PubMed, EMBASE, and Web of Science were searched from inception to 18 March 2022. Risk of bias assessment was performed using PROBAST. Rsoftware (version 4.1.1) was used to calculate the accuracy and C-index of CSA-AKI prediction. The importance of CSA-AKI prediction was defined according to the frequency of related factors in the models.

Results

There were 38 eligible studies included, with a total of 255,943 patients and 60 machine learning models. The models mainly included Logistic Regression (n = 34), Neural Net (n = 6), Support Vector Machine (n = 4), Random Forest (n = 6), Extreme Gradient Boosting (n = 3), Decision Tree (n = 3), Gradient Boosted Machine (n = 1), COX regression (n = 1), κNeural Net (n = 1), and Naïve Bayes (n = 1), of which 51 models with intact recording in the training set and 17 in the validating set. Variables with the highest predicting frequency included Logistic Regression, Neural Net, Support Vector Machine, and Random Forest. The C-index and accuracy wer 0.76 (0.740, 0.780) and 0.72 (0.70, 0.73), respectively, in the training set, and 0.79 (0.75, 0.83) and 0.73 (0.71, 0.74), respectively, in the test set.

Conclusion

The machine learning-based model is effective for the early prediction of CSA-AKI. More machine learning methods based on noninvasive or minimally invasive predictive indicators are needed to improve the predictive performance and make accurate predictions of CSA-AKI. Logistic regression remains currently the most commonly applied model in CSA-AKI prediction, although it is not the one with the best performance. There are other models that would be more effective, such as NNET and XGBoost.

Systematic review registration

https://www.crd.york.ac.uk/; review registration ID: CRD42022345259.

Utility of Kinetic GFR for Predicting Severe Persistent AKI in Critically Ill Children and Young Adults

Kinetic eGFR can be part of a multidimensional approach for AKI prediction combined with biomarkers, fluid corrected creatinine, and renal angina.Kinetic eGFR on day 1 is not independently associated with severe day-3 AKI in children and young adults who are critically ill.