Articles: intensive-care-units.
-
Observational Study
Comparing machine learning and logistic regression for acute kidney injury prediction in trauma patients: A retrospective observational study at a single tertiary medical center.
Acute kidney injury (AKI) is common in patients with trauma and is associated with poor outcomes. Therefore, early prediction of AKI in patients with trauma is important for risk stratification and the provision of optimal intensive care unit treatment. This study aimed to compare 2 models, machine learning (ML) techniques and logistic regression, in predicting AKI in patients with trauma. ⋯ The accuracy score showed no differences between the 2 groups; however, the recall and F1 score were significantly higher in the ML model (.94 vs 56 and.75 vs 64, respectively). The ML model performed better than the logistic regression model in predicting AKI in patients with trauma. ML techniques can aid in risk stratification and the provision of optimal care.
-
Observational Study
Variables associated to intensive care unit (ICU)-mortality among patients admitted to surgical intensive care unit in Ethiopia: a retrospective observational study.
The present study aimed to assess variables associated to ICU-mortality among patients admitted to surgical intensive care unit in Ethiopia. ⋯ The overall ICU-mortality of patients admitted to our surgical intensive care unit was higher compared to patients admitted to similar intensive care unit in developed countries. The variables associated to ICU-mortality among patients admitted to surgical intensive care unit were abnormal serum potassium level, lower GCS score, mechanical support, hypoxia, absence of thromboprophylaxis, and enteral feeding.
-
Randomized Controlled Trial
Differential effect on mortality of the timing of initiation of renal replacement therapy according to the criteria used to diagnose acute kidney injury: an IDEAL-ICU substudy.
This substudy of the randomized IDEAL-ICU trial assessed whether the timing of renal replacement therapy (RRT) initiation has a differential effect on 90-day mortality, according to the criteria used to diagnose acute kidney injury (AKI), in patients with early-stage septic shock. ⋯ The timing of RRT initiation has a differential impact on outcome according to AKI diagnostic criteria. In patients with elevated creatinine only, early RRT initiation was associated with significantly increased mortality. In patients with reduced urine output only, late RRT initiation was associated with a nonsignificant, 10% absolute increase in mortality.
-
Thoracic endovascular aortic repair (TEVAR) is a new alternative surgical treatment for aortic pathologies, which is more minimally invasive. The aim of current study was to summarize the single-center experience of general anesthesia for patients undergoing TEVAR. In adult patients undergoing surgery for congenital heart disease, the strategy of "fast-track" anesthesia with early extubation in theater is associated with a shorter intensive care unit (ICU) stay, and lower health-care-related costs. ⋯ Fast-track anesthesia is feasible and safe in patients underwent TEVAR. This management strategy is associated with shorter LOS of ICU and total postoperative hospital stays. An early extubation strategy should be implemented for hemodynamically stable patients.
-
Anesthesia and analgesia · Aug 2023
Data and Metrics for Patient Blood Management: A Narrative Review and Practical Guide.
Data collection, analysis, and reporting are fundamental for a successful hospital-based patient blood management program; however, very little has been published on the topic. Our aim was to synthesize evidence from a literature review to provide a detailed, practical list of outcome metrics, and the required data collection(s) to inform implementation. Ovid MEDLINE and PubMed were searched for any full-text original research articles published from inception to the year 2020. ⋯ We compiled a list of 65 relevant data elements to collect, and their potential source hospital information systems: patient administration, laboratory, transfusion/blood bank, operating room, pharmacy, emergency department, and intensive care unit. We further categorized patient blood management data systems into basic, intermediate, and advanced based on the combination of different information systems sourced. The results of this review can be used to inform patient blood management programs in planning what data collection(s) are needed, where these data can be sourced from, and how they can be analyzed.