Critical care : the official journal of the Critical Care Forum
-
Observational Study
Machine learning versus physicians' prediction of acute kidney injury in critically ill adults: a prospective evaluation of the AKIpredictor.
Early diagnosis of acute kidney injury (AKI) is a major challenge in the intensive care unit (ICU). The AKIpredictor is a set of machine-learning-based prediction models for AKI using routinely collected patient information, and accessible online. In order to evaluate its clinical value, the AKIpredictor was compared to physicians' predictions. ⋯ The machine-learning-based AKIpredictor achieved similar discriminative performance as physicians for prediction of AKI-23, and higher net benefit overall, because physicians overestimated the risk of AKI. This suggests an added value of the systematic risk stratification by the AKIpredictor to physicians' predictions, in particular to select high-risk patients or reduce false positives in studies evaluating new and potentially harmful therapies. Due to the low event rate, future studies are needed to validate these findings.
-
Observational Study
Capillary refill time variation induced by passive leg raising predicts capillary refill time response to volume expansion.
A peripheral perfusion-targeted resuscitation during early septic shock has shown encouraging results. Capillary refill time, which has a prognostic value, was used. Adding accuracy and predictability on capillary refill time (CRT) measurement, if feasible, would benefit to peripheral perfusion-targeted resuscitation. We assessed whether a reduction of capillary refill time during passive leg raising (ΔCRT-PLR) predicted volume-induced peripheral perfusion improvement defined as a significant decrease of capillary refill time following volume expansion. ⋯ ΔCRT-PLR predicted peripheral perfusion response following volume expansion. This simple low-cost and non-invasive diagnostic method could be used in peripheral perfusion-targeted resuscitation protocols.
-
Thrombomodulin plays a vital role in maintaining intravascular patency due to its anticoagulant, antiinflammatory, and cytoprotective properties. However, under pathological conditions such as sepsis and systemic inflammation, endothelial thrombomodulin expression is downregulated and its function impaired. As a result, administering thrombomodulin represents a potential therapeutic modality. ⋯ Favorable effects of thrombomodulin administration have been reported not only in sepsis-induced coagulopathy but also in disseminated intravascular coagulations with various backgrounds. Interestingly, beneficial effects of recombinant thrombomodulin in respiratory, renal, and cardiovascular diseases might depend on its anti-inflammatory mechanisms. In this review, we summarize the accumulated knowledge of endogenous as well as recombinant thrombomodulin from basic to clinical aspects and suggest future directions for this novel therapeutic agent.
-
Observational Study
A deep learning model for real-time mortality prediction in critically ill children.
The rapid development in big data analytics and the data-rich environment of intensive care units together provide unprecedented opportunities for medical breakthroughs in the field of critical care. We developed and validated a machine learning-based model, the Pediatric Risk of Mortality Prediction Tool (PROMPT), for real-time prediction of all-cause mortality in pediatric intensive care units. ⋯ PROMPT is a deep model-based, data-driven early warning score tool that can predict mortality in critically ill children and may be useful for the timely identification of deteriorating patients.
-
Meta Analysis
Interventions to prevent iatrogenic anemia: a Laboratory Medicine Best Practices systematic review.
As many as 90% of patients develop anemia by their third day in an intensive care unit (ICU). We evaluated the efficacy of interventions to reduce phlebotomy-related blood loss on the volume of blood lost, hemoglobin levels, transfusions, and incidence of anemia. ⋯ Moderate, consistent evidence indicated that devices that return blood from testing or flushing lines to the patient reduce the volume of blood loss by approximately 25% among ICU patients. The results of this systematic review support the use of blood conservation systems with arterial or venous catheters to eliminate blood waste when drawing blood for testing. The evidence was insufficient to conclude the devices impacted hemoglobin levels or transfusion rates. The use of small volume tubes may reduce the risk of anemia.