Association between left ventricular diastolic dysfunction and septic acute kidney injury in severe sepsis and septic shock: A multicenter retrospective study

Clinical outcomes of severe sepsis and septic shock patients with left ventricular dysfunction undergoing continuous renal replacement therapy

Baseline left ventricular (LV) dysfunction is associated with subsequent risks of acute kidney injury (AKI) and mortality in patients with sepsis. This study investigated the therapeutic effects of continuous renal replacement therapy (CRRT) in hemodynamically unstable patients with severe sepsis and septic shock combined with LV dysfunction. In this multicenter retrospective study, severe sepsis and septic shock patients with LV dysfunction were classified into one of two groups according to the timing of CRRT: the early group (before AKI was detected) or the control group (patients with AKI). Patients from the control group received an accelerated strategy or a standard strategy of CRRT. The primary outcome was all-cause intensive care unit (ICU) mortality. Patients were weighted by stabilized inverse probability of treatment weights (sIPTW) to overcome differences in baseline characteristics. After sIPTW analysis, the ICU mortality was significantly lower in the early group than the control group (27.7% vs. 63.5%, p < 0.001). Weighted multivariable analysis showed that early CRRT initiation was a protective factor for the risk of ICU mortality (OR 0.149; 95% CI 0.051–0.434; p < 0.001). The ICU mortality was not different between the accelerated- and standard-strategy group (52.5% vs. 52.9%, p = 0.970). Early CRRT in the absence of AKI is suggested for hemodynamically unstable patients with severe sepsis and septic shock combined with LV dysfunction since it benefits survival outcomes.

Advances in artificial intelligence and deep learning systems in ICU-related acute kidney injury

PURPOSE OF REVIEW

Acute kidney injury (AKI) affects nearly 60% of all patients admitted to ICUs. Large volumes of clinical, monitoring and laboratory data produced in ICUs allow the application of artificial intelligence analytics. The purpose of this article is to assimilate and critically evaluate recently published literature regarding artificial intelligence applications for predicting, diagnosing and subphenotyping AKI among critically ill patients.

RECENT FINDINGS

Among recent studies regarding artificial intelligence implementations for predicting, diagnosing and subphenotyping AKI among critically ill patients, there are many promising models, but few had external validation, clinical interpretability and high predictive performance. Deep learning techniques leveraging multimodal clinical data show great potential to provide continuous, accurate, early predictions of AKI risk, which could be implemented clinically to optimize preventive and early therapeutic management strategies.

SUMMARY

Use of consensus criteria, standard definitions and common data models could facilitate access to machine learning-ready data sets for external validation. The lack of interpretability, explainability, fairness and transparency of artificial intelligence models hinder their entrustment and clinical implementation; compliance with standardized reporting guidelines can mitigate these challenges.