Renal Hemodynamics, Function, and Oxygenation in Critically Ill Patients and after Major Surgery

Continuous bladder urinary oxygen tension as a new tool to monitor medullary oxygenation in the critically ill

Acute kidney injury (AKI) is common in the critically ill. Inadequate renal medullary tissue oxygenation has been linked to its pathogenesis. Moreover, renal medullary tissue hypoxia can be detected before biochemical evidence of AKI in large mammalian models of critical illness. This justifies medullary hypoxia as a pathophysiological biomarker for early detection of impending AKI, thereby providing an opportunity to avert its evolution. Evidence from both animal and human studies supports the view that non-invasively measured bladder urinary oxygen tension (PuO₂) can provide a reliable estimate of renal medullary tissue oxygen tension (tPO₂), which can only be measured invasively. Furthermore, therapies that modify medullary tPO₂ produce corresponding changes in bladder PuO₂. Clinical studies have shown that bladder PuO₂ correlates with cardiac output, and that it increases in response to elevated cardiopulmonary bypass (CPB) flow and mean arterial pressure. Clinical observational studies in patients undergoing cardiac surgery involving CPB have shown that bladder PuO₂ has prognostic value for subsequent AKI. Thus, continuous bladder PuO₂ holds promise as a new clinical tool for monitoring the adequacy of renal medullary oxygenation, with its implications for the recognition and prevention of medullary hypoxia and thus AKI.

Developing an ensemble machine learning model for early prediction of sepsis-associated acute kidney injury

Sepsis-associated acute kidney injury (S-AKI) is very common and early prediction is beneficial. This study aiming to develop an accurate ensemble model to predict the risk of S-AKI based on easily available clinical information. Patients with sepsis from the United States (US) database Medical Information Mart for Intensive Care-IV were used as a modeling cohort to predict the occurrence of AKI by combining Support Vector Machine, Random Forest, Neural Network, and Extreme Gradient Boost as four first-level learners via stacking algorithm. The external validation databases were the eICU Collaborative Research Database from US and Critical Care Database comprising infection patients at Zigong Fourth People's Hospital from China, whose AUROC values for the ensemble model 48-12 h before the onset of AKI were 0.774-0.788 and 0.756-0.813, respectively. In this study, an ensemble model for early prediction of S-AKI onset was developed and it demonstrated good performance in multicenter external datasets.