Search

Infection-related consultations on intensive care units (ICU) have a positive impact on quality of care and clinical outcome. However, timing of these consultations is essential and to date they are typically event-triggered and reactive. Here, we investigate a proactive approach to identify patients in need for infection-related consultations by machine learning models using routine electronic health records. Data was retrieved from a mixed ICU at a large academic tertiary care hospital including 9684 admissions. Infection-related consultations were predicted using logistic regression, random forest, gradient boosting machines, and long short-term memory neural networks (LSTM). Overall, 7.8% of admitted patients received an infection-related consultation. Time-sensitive modelling approaches performed better than static approaches. Using LSTM resulted in the prediction of infection-related consultations in the next clinical shift (up to eight hours in advance) with an area under the receiver operating curve (AUROC) of 0.921 and an area under the precision recall curve (AUPRC) of 0.541. The successful prediction of infection-related consultations for ICU patients was done without the use of classical triggers, such as (interim) microbiology reports. Predicting this key event can potentially streamline ICU and consultant workflows and improve care as well as outcome for critically ill patients with (suspected) infections. [ABSTRACT FROM AUTHOR]

Background: Normothermic machine perfusion (NMP) is used for preservation and assessment of human donor livers prior to transplantation. During NMP, the liver is metabolically active, which allows detailed studies on the physiology of human livers., Objectives: To study the production of hemostatic proteins in human donor livers during NMP for up to 7 days., Methods: In this observational study, nine livers underwent NMP for up to 7 days with a heparinised perfusate based on red blood cells and colloids using a modified Liver Assist device. Perfusate samples were collected before NMP and daily thereafter for measurement of antigen and activity levels of comprehensive panel of hemostatic proteins after heparin neutralization., Results: Within one day, perfusate samples displayed the potential for coagulation activation as evidenced by international normalized ratio and activated partial thromboplastin assays. This was accompanied by detection of substantial quantities of functionally active coagulation proteins and inhibitors, although the specific activity of many proteins was decreased, compared to that in normal plasma. Perfusate levels of hemostatic proteins increased in the first days, reaching a stable level after 3-4 days of perfusion., Conclusion: During long-term NMP of human livers, functionally active hemostatic proteins are released into the perfusate in substantial quantities, but some proteins appear to have decreased functional properties compared to proteins in normal human plasma. We propose that NMP may be used as a platform to test efficacy of drugs that stimulate or inhibit the production of coagulation factors, or to test liver-mediated clearance of prohemostatic protein therapeutics., (Copyright © 2024 The Author(s). Published by Elsevier Inc. All rights reserved.)