The predictive value of the intraoperative Renal Pulsatility Index for acute kidney injury in patients undergoing cardiac surgery

Current Insights into the Significance of the Renal Resistive Index in Kidney and Cardiovascular Disease

Initially, the renal resistive index (RRI) was investigated with the aim of improving diagnosis in kidney diseases, but this goal was not met. Recently, many papers have highlighted the prognostic significance of the RRI in chronic kidney disease: specifically, in estimating the revascularization success of renal artery stenoses or the evolution of the graft and the recipients in renal transplantation. Moreover, the RRI has become significant in the prediction of acute kidney injury in critically ill patients. Studies in renal pathology have revealed correlations of this index with parameters of systemic circulation. The theoretical and experimental premises of this connection were then reconsidered, and studies analyzing the link between RRI and arterial stiffness, central and peripheral pressure, and left ventricular flow were conducted with this purpose. Many data currently indicate that RRI is influenced more by pulse pressure and vascular compliance than by renal vascular resistance-assuming that RRI reflects the complex interplay between systemic circulation and renal microcirculation and should be considered a marker of systemic cardiovascular risk beyond its prognostic relevance for kidney disease. In this review, we overview the clinical research that reveals the implications of RRI in renal and cardiovascular disease.

Doppler ultrasound in the assessment of renal perfusion before and during continuous kidney replacement therapy in the pediatric intensive care unit

BACKGROUND

This study aimed to assess observer variability and describe renal resistive index (RRI) and pulsatility index (PI) before and after onset of continuous kidney replacement therapy (CKRT). A secondary objective was to correlate Doppler ultrasound findings with those from direct measurement of renal blood flow (RBF).

METHODS

This is a prospective observational study in hemodynamically stable Maryland piglets with and without acute kidney injury (AKI) and in hemodynamically unstable critically ill children requiring CKRT. Doppler-based RRI and PI were assessed for each subject. Measurements were made by two different operators (pediatric intensivists) before and after CKRT onset.

RESULTS

Observer variability assessment in the measurement of RRI and PI rendered a moderate correlation for both RRI (ICC 0.65, IQR 0.51-0.76) and PI (ICC 0.63, IQR 0.47-0.75). RRI and PI showed no correlation with RBF or urine output. Baseline RRI and PI were normal in control piglets [RRI 0.68 (SD 0.02), PI 1.25 (SD 0.09)] and those with AKI [RRI 0.68 (SD 0.03), PI 1.20 (SD 0.13)]. Baseline RRI and PI were elevated in critically ill children (RRI 0.85, PI 2.0). PI and RRI did not change with CKRT in any study group.

CONCLUSIONS

Observer variability between inexperienced pediatric intensivists was comparable with that between senior and junior operators. Doppler-based calculations did not correlate with invasive measurements of RBF. RRI and PI were normal in hemodynamically stable piglets with and without AKI. RRI and PI were high in hemodynamically unstable patients requiring CKRT. RRI and PI did not change after CKRT onset, despite changes in hemodynamic status. A higher resolution version of the Graphical abstract is available as Supplementary information.

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.