AI Article Synopsis
- Real-time risk monitoring is essential in ICUs but often struggles with a lack of updates for clinical variables, prompting the development of a new framework that incorporates uncertainties into existing risk assessment systems like the SOFA score.
- The study analyzed data from 5,351 patients in a Cardiothoracic ICU, utilizing machine learning models to enhance real-time SOFA scores and account for uncertainties, with validation showing improved predictive capabilities for mortality and readmission.
- Results demonstrated that the new model outperformed traditional SOFA scores and quick SOFA in predicting outcomes, suggesting it could lead to more efficient testing and better patient care in clinical settings.
Article Abstract
Purpose: Real-time risk monitoring is critical but challenging in intensive care units (ICUs) due to the lack of real-time updates for most clinical variables. Although real-time predictions have been integrated into various risk monitoring systems, existing systems do not address uncertainties in risk assessments. We developed a novel framework based on commonly used systems like the Sequential Organ Failure Assessment (SOFA) score by incorporating uncertainties to improve the effectiveness of real-time risk monitoring.
Methods: This study included 5351 patients admitted to the Cardiothoracic ICU in the National University Hospital in Singapore. We developed machine learning models to predict long lead-time variables and computed real-time SOFA scores using predictions. We calculated intervals to capture uncertainties in risk assessments and validated the association of the estimated real-time scores and intervals with mortality and readmission.
Results: Our model outperforms SOFA score in predicting 24-h mortality: Nagelkerke's R-squared (0.224 vs. 0.185, p < 0.001) and the area under the receiver operating characteristic curve (AUC) (0.870 vs. 0.843, p < 0.001), and significantly outperforms quick SOFA (Nagelkerke's R-squared = 0.125, AUC = 0.778). Our model also performs better in predicting 30-day readmission. We confirmed a positive net reclassification improvement (NRI) of our model over the SOFA score (0.184, p < 0.001). Similarly, we enhanced two additional scoring systems.
Conclusions: Incorporating uncertainties improved existing scores in real-time monitoring, which could be used to trigger on-demand laboratory tests, potentially improving early detection, reducing unnecessary testing, and thereby lowering healthcare expenditures, mortality, and readmission rates in clinical practice.
Supplementary Information: The online version contains supplementary material available at 10.1007/s13755-024-00331-5.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11688259 | PMC |
| http://dx.doi.org/10.1007/s13755-024-00331-5 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The expression of MALAT1, plasma brain natriuretic peptide, and Tei index in sepsis-induced myocardial injury.
J Cardiothorac Surg
January 2025
Emergency and Critical Care Center, Renmin Hospital, Hubei University of Medicine, Shiyan, Hubei, China.
Purpose: We sought to investigate the expression of MALAT1, plasma brain natriuretic peptide, and Tei index in sepsis-induced myocardial injury.
Methods: The current retrospective analysis focused on 146 sepsis patients admitted to our hospital from February 2021 to March 2023. Based on the presence or absence of myocardial injury, the patients were divided into two groups: the sepsis group (n = 80) and the sepsis-induced myocardial injury group (n = 66).
Norepinephrine titration in patients with sepsis-induced encephalopathy: cerebral pulsatility index compared to mean arterial pressure guided protocol: randomized controlled trial.
BMC Anesthesiol
January 2025
Department of Anesthesia, Surgical Intensive Care and Pain Medicine, Faculty of Medicine, Tanta University Hospitals, Tanta, Gharbya, Egypt.
Background: Although surviving sepsis campaign (SSC) guidelines are the standard for sepsis and septic shock management, outcomes are still unfavourable. Given that perfusion pressure in sepsis is heterogeneous among patients and within the same patient; we evaluated the impact of individualized hemodynamic management via the transcranial Doppler (TCD) pulsatility index (PI) on mortality and outcomes among sepsis-induced encephalopathy (SIE) patients.
Methods: In this prospective, single-center randomized controlled study, 112 patients with SIE were randomly assigned.
Prediction of the need for surgery in patients with unruptured abdominal aortic aneurysm based on SOFA score.
PLoS One
January 2025
General Surgery, Cancer Center, Department of Vascular Surgery, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, China.
Objective: This retrospective study aimed to explore the association and clinical value of sequential organ failure assessment (SOFA) score on the predictors of adverse events in patients with unruptured abdominal aortic aneurysms (AAA).
Methods: A total of 322 patients from Medical Information Mart for Intensive Care IV database were enrolled. Logistic regression was conducted to explore the association between SOFA and primary outcome (need for surgery, NFS).
Putative biomarkers of hepatic dysfunction in critically ill sepsis patients.
Clin Exp Med
January 2025
Pediatrics, Western University, London, ON, Canada.
Sepsis is a major cause of morbidity and mortality worldwide. Among the various types of end-organ damage associated with sepsis, hepatic injury is linked to significantly higher mortality rates compared to dysfunction in other organ systems. This study aimed to investigate potential biomarkers of hepatic injury in sepsis patients through a multi-center, case-control approach.
View Article and Find Full Text PDFReal-time estimated Sequential Organ Failure Assessment (SOFA) score with intervals: improved risk monitoring with estimated uncertainty in health condition for patients in intensive care units.
Health Inf Sci Syst
December 2025
Department of Cardiac, Thoracic and Vascular Surgery, National University Hospital, Singapore, Singapore.
Article Synopsis
- Real-time risk monitoring is essential in ICUs but often struggles with a lack of updates for clinical variables, prompting the development of a new framework that incorporates uncertainties into existing risk assessment systems like the SOFA score.
- The study analyzed data from 5,351 patients in a Cardiothoracic ICU, utilizing machine learning models to enhance real-time SOFA scores and account for uncertainties, with validation showing improved predictive capabilities for mortality and readmission.
- Results demonstrated that the new model outperformed traditional SOFA scores and quick SOFA in predicting outcomes, suggesting it could lead to more efficient testing and better patient care in clinical settings.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!