Articles: critical-illness.
-
Early data suggest use of a mixed lipid emulsion (LE) with a soybean oil reduction strategy in parenteral nutrition (PN) may improve clinical outcomes. Duke University Hospital made a full switch to a Soybean oil/MCT/Olive/Fish Oil lipid (4-OLE) from pure soybean oil-based LE (Intralipid, Baxter Inc) in May 2017. Since 4-OLE has limited evidence related to its effects on clinical outcome parameters in US hospitals, evidence for clinical benefits of switching to 4-OLE is needed. Therefore, we examined the clinical utility of a hospital-wide switch to 4-OLE and its effect on patient outcomes. ⋯ 4-OLE was successfully implemented and reduced soybean oil LE exposure in a large academic hospital setting. The introduction of 4-OLE was associated with reduced LOS, UTI rates, and mitigated hepatic dysfunction in critically ill patients. Overall, these findings prove a switch to a soybean oil-LE sparing strategy using 4-OLE is feasible and safe and is associated with improved clinical outcomes in adult PN patients.
-
The sublingual microcirculation presumably exhibits disease-specific changes in function and morphology. Algorithm-based quantification of functional microcirculatory hemodynamic variables in handheld vital microscopy (HVM) has recently allowed identification of hemodynamic alterations in the microcirculation associated with COVID-19. In the present study we hypothesized that supervised deep machine learning could be used to identify previously unknown microcirculatory alterations, and combination with algorithmically quantified functional variables increases the model's performance to differentiate critically ill COVID-19 patients from healthy volunteers. ⋯ We successfully trained a deep learning-based model to differentiate critically ill COVID-19 patients from heathy volunteers in sublingual HVM image sequences. Internally validated, deep learning was superior to the algorithmic approach. However, combining the deep learning method with an algorithm-based approach to quantify the functional state of the microcirculation markedly increased the sensitivity and specificity as compared to either approach alone, and enabled successful external validation of the identification of the presence of microcirculatory alterations associated with COVID-19 status.
-
Postintensive care syndrome in COVID-19. Unicentric pilot study. Calm does not come after the storm.
Postintensive care syndrome (PICS) is the physical, cognitive or psychiatric deterioration that appears after a critical illness and persists beyond hospital admission. The objective of this study was to describe the prevalence of PICS in the patients with coronavirus disease 2019 (COVID-19) admitted to the intensive care unit of the Consorcio Hospital General Universitario de Valencia. ⋯ We found that 9 out of 10 survivors of SARS-CoV-2 admitted had at least one PICS alteration at 4-6 weeks from discharge from the Hospital. Six out of 19 patients presented with two or more affected evaluated areas.
-
Changes in diastolic blood pressure (DBP) are common in patients with acute myocardial infarction (AMI). The relationship between the dynamic change of DBP and in-hospital mortality among patients with AMI remains unclear. This study aimed to explore the importance of DBP during disease development among patients with AMI. ⋯ DBP significantly contributed to in-hospital mortality among patients with AMI. There was a nonlinear correlation between baseline DBP and in-hospital mortality among patients with AMI, and the DBP of the non-survivors decreased within the first 3 days after ICU admission. However, the causality cannot be deduced from our data.
-
J Clin Monit Comput · Oct 2022
Multicenter StudyPredicting hypoglycemia in critically Ill patients using machine learning and electronic health records.
Hypoglycemia is a common occurrence in critically ill patients and is associated with significant mortality and morbidity. We developed a machine learning model to predict hypoglycemia by using a multicenter intensive care unit (ICU) electronic health record dataset. Machine learning algorithms were trained and tested on patient data from the publicly available eICU Collaborative Research Database. ⋯ The best-performing predictive model was the eXtreme gradient boosting model (XGBoost), which achieved an area under the received operating curve (AUROC) of 0.85, a sensitivity of 0.76, and a specificity of 0.76. The machine learning model developed has strong discrimination and calibration for the prediction of hypoglycemia in ICU patients. Prospective trials of these models are required to evaluate their clinical utility in averting hypoglycemia within critically ill patient populations.