Pre-operative proteinuria, postoperative acute kidney injury and mortality: A systematic review and meta-analysis

Development of a Machine Learning Model of Postoperative Acute Kidney Injury Using Non-Invasive Time-Sensitive Intraoperative Predictors

Acute kidney injury (AKI) is a major postoperative complication that lacks established intraoperative predictors. Our objective was to develop a prediction model using preoperative and high-frequency intraoperative data for postoperative AKI. In this retrospective cohort study, we evaluated 77,428 operative cases at a single academic center between 2016 and 2022. A total of 11,212 cases with serum creatinine (sCr) data were included in the analysis. Then, 8519 cases were randomly assigned to the training set and the remainder to the validation set. Fourteen preoperative and twenty intraoperative variables were evaluated using elastic net followed by hierarchical group least absolute shrinkage and selection operator (LASSO) regression. The training set was 56% male and had a median [IQR] age of 62 (51-72) and a 6% AKI rate. Retained model variables were preoperative sCr values, the number of minutes meeting cutoffs for urine output, heart rate, perfusion index intraoperatively, and the total estimated blood loss. The area under the receiver operator characteristic curve was 0.81 (95% CI, 0.77-0.85). At a score threshold of 0.767, specificity was 77% and sensitivity was 74%. A web application that calculates the model score is available online. Our findings demonstrate the utility of intraoperative time series data for prediction problems, including a new potential use of the perfusion index. Further research is needed to evaluate the model in clinical settings.

Perioperative acute kidney injury: impact and recent update

PURPOSE OF REVIEW

Acute kidney injury (AKI) is common in hospitalized patients and is a major risk factor for increased length of stay, morbidity, and mortality in postoperative patients. There are multiple barriers to reducing perioperative AKI - the etiology is multi-factorial and the diagnosis is fraught with issues. We review the recent literature on perioperative AKI and some considerations for anesthesiologists that examine the far-reaching effects of AKI on multiple organ systems.

RECENT FINDINGS

This review will discuss recent literature that addresses the epidemiology, use of novel biomarkers in risk stratification, and therapeutic modalities for AKI in burn, pediatrics, sepsis, trauma, cardiac, and liver disease, contrast-induced AKI, as well as the evidence assessing goal-directed fluid therapy.

SUMMARY

Recent studies address the use of risk stratification models and biomarkers, more sensitive than creatinine, in the preoperative identification of patients at risk for AKI. Although exciting, these scores and models need validation. There is a need for research assessing whether early AKI detection improves outcomes. Enhanced recovery after surgery utilizing goal-directed fluid therapy has not been shown to make an appreciable difference in the incidence of AKI. Reducing perioperative AKI requires a multi-pronged and possibly disease-specific approach.