A machine learning model incorporating an intraoperative PuO2 feature better predicted AKI than a preoperative-only model (AUROC 0.78 vs. 0.66; p<0.01).
Observational
Does a machine learning algorithm incorporating intraoperative PuO2 monitoring improve the prediction of AKI in cardiac surgery patients compared to preoperative risk factors alone?
Incorporating intraoperative urine oximetry (PuO2) into a machine learning model significantly improves the prediction of acute kidney injury in cardiac surgery patients compared to using preoperative risk factors alone.
Absolute Event Rate: 0.78% vs 0.66%
p-value: p=<0.01
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.
Lofgren et al. (Sat,) conducted a observational in Acute kidney injury (AKI) in cardiac surgery patients. Machine learning algorithm incorporating intraoperative PuO2 feature vs. Machine learning algorithm relying solely on preoperative risk factors was evaluated on Prediction of AKI (AUROC) (p=<0.01). A machine learning model incorporating an intraoperative PuO2 feature better predicted AKI than a preoperative-only model (AUROC 0.78 vs. 0.66; p<0.01).