Objective: Critically ill patients with liver cirrhosis generally have a poor prognosis due to complications such as multiple organ failure. This study aims to develop a machine learning-based prediction model to forecast short-term mortality in critically ill cirrhotic patients in the intensive care unit (ICU), thereby assisting clinical decision-making for intervention and treatment.
Methods: Machine learning models were developed using clinical data from critically ill cirrhotic patients in the MIMIC database, with multicenter validation performed using data from the eICU database and Qinghai University Affiliated Hospital(QUAH). Various machine learning models, including a Stacking ensemble model, were employed, with the SHAP method used to enhance model interpretability.
Results: The Stacking ensemble model demonstrated superior predictive performance through internal and external validation, with AUC and AP values surpassing those of individual algorithms. The AUC values were 0.845 in the internal validation set, 0.819 in the eICU external validation, and 0.761 in the QUAH validation set. Additionally, the SHAP method highlighted key prognostic variables such as INR, bilirubin, and urine output. The model was ultimately deployed as a web-based calculator for bedside decision-making.
Conclusion: The machine learning model effectively predicts short-term mortality risk in critically ill cirrhotic patients in the ICU, showing strong predictive performance and generalizability. The model's robust interpretability and its deployment as a web-based calculator suggest its potential as a valuable tool for assessing the prognosis of cirrhotic patients.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1016/j.clinre.2024.102507 | DOI Listing |
BMC Infect Dis
December 2024
Clinical Pharmacy Department, College of Pharmacy, King Saud University, Riyadh, Saudi Arabia.
Background: The World Health Organization (WHO) has identified carbapenem-resistant Pseudomonas aeruginosa (CRPA) as one of the three critical priority pathogens. There is scarce literature evaluating the treatment outcomes in patients with CRPA infections treated with traditional non-carbapenem β-lactam (NCBL) agents. Thus, this study aims to assess the effectiveness of traditional NCBL compared to novel β-lactam agents (NVL) for treating non-carbapenem β-lactam -susceptible CRPA.
View Article and Find Full Text PDFAPMIS
January 2025
Laboratory Sciences Research Center, Golestan University of Medical Sciences, Gorgan, Iran.
Colistin is a last-resort treatment for multidrug-resistant Gram-negative bacterial infections, particularly in critically ill patients. Nevertheless, it remains a major threat to public health. We assessed the proportion of colistin-resistant Gram-negative isolates from intensive care unit (ICU) infections in different years, areas, pathogens, and antimicrobial susceptibility tests (AST).
View Article and Find Full Text PDFJ Food Prot
December 2024
Division of Foodborne, Waterborne, and Environmental Diseases, National Center for Emerging and Zoonotic Infectious Diseases, Centers for Disease Control and Prevention. 1600 Clifton Rd NE MS-H24-10, Atlanta, GA 30333, USA. Electronic address:
Listeria monocytogenes causes listeriosis, a serious infection, with a high mortality rate for persons at higher risk for listeriosis. The first Listeria outbreak linked to frozen vegetables occurred in 2016 and resulted in three deaths. Many frozen vegetables are intended to be consumed after cooking.
View Article and Find Full Text PDFChest
December 2024
Louisiana State University School of Medicine, New Orleans - Baton Rouge Regional Campus. Electronic address:
When an understanding of pathogenesis exists, skin lesions that have the appearance of blood in the skin can provide insight into the mechanisms leading to a systemic process that results in cutaneous manifestations. Of the vascular disturbances of the skin that occur in critically ill patients, some result from a non-hemorrhagic process while occurs represent bleeding into the skin. The lesions of livedo, petechiae, purpura, and ecchymoses can be approached from such a perspective.
View Article and Find Full Text PDFInt J Antimicrob Agents
December 2024
Department of Translational and Precision Medicine, Sapienza University of Rome.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!