The impact of urine flow on urine oxygen partial pressure monitoring during cardiac surgery

Urinary oxygen tension and its role in predicting acute kidney injury: A narrative review

Acute kidney injury occurs frequently in the perioperative setting. The renal medulla often endures hypoxia or hypoperfusion and is susceptible to the imbalance between oxygen supply and demand due to the nature of renal blood flow distribution and metabolic rate in the kidney. The current available evidence demonstrated that the urine oxygen pressure is proportional to the variations of renal medullary tissue oxygen pressure. Thus, urine oxygenation can be a candidate for reflecting the change of oxygen in the renal medulla. In this review, we discuss the basic physiology of acute kidney injury, as well as techniques for monitoring urine oxygen tension, confounding factors affecting the reliable measurement of urine oxygen tension, and its clinical use, highlighting its potential role in early detection and prevention of acute kidney injury.

Combining Machine Learning and Urine Oximetry: Towards an Intraoperative AKI Risk Prediction Algorithm

Acute kidney injury (AKI) affects up to 50% of cardiac surgery patients. The definition of AKI is based on changes in serum creatinine relative to a baseline measurement or a decrease in urine output. These monitoring methods lead to a delayed diagnosis. Monitoring the partial pressure of oxygen in urine (PuO2) may provide a method to assess the patient's AKI risk status dynamically. This study aimed to assess the predictive capability of two machine learning algorithms for AKI in cardiac surgery patients. One algorithm incorporated a feature derived from PuO2 monitoring, while the other algorithm solely relied on preoperative risk factors. The hypothesis was that the model incorporating PuO2 information would exhibit a higher area under the receiver operator characteristic curve (AUROC). An automated forward variable selection method was used to identify the best preoperative features. The AUROC for individual features derived from the PuO2 monitor was used to pick the single best PuO2-based feature. The AUROC for the preoperative plus PuO2 model vs. the preoperative-only model was 0.78 vs. 0.66 (p-value < 0.01). In summary, a model that includes an intraoperative PuO2 feature better predicts AKI than one that only includes preoperative patient data.