Universitätspublikationen
Refine
Document Type
- Article (2)
Language
- English (2) (remove)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- ARDS (1)
- COVID-19 (1)
- Clinical frailty scale (1)
- Critical care (1)
- Frailty (1)
- Intensive care outcome (1)
- Outcome (1)
- Prognostic models (1)
- VIP1 (1)
Institute
- Medizin (2) (remove)
Background: In intensive care units (ICU) octogenarians become a routine patients group with aggravated therapeutic and diagnostic decision-making. Due to increased mortality and a reduced quality of life in this high-risk population, medical decision-making a fortiori requires an optimum of risk stratification. Recently, the VIP-1 trial prospectively observed that the clinical frailty scale (CFS) performed well in ICU patients in overall-survival and short-term outcome prediction. However, it is known that healthcare systems differ in the 21 countries contributing to the VIP-1 trial. Hence, our main focus was to investigate whether the CFS is usable for risk stratification in octogenarians admitted to diversified and high tech German ICUs.
Methods: This multicentre prospective cohort study analyses very old patients admitted to 20 German ICUs as a sub-analysis of the VIP-1 trial. Three hundred and eight patients of 80 years of age or older admitted consecutively to participating ICUs. CFS, cause of admission, APACHE II, SAPS II and SOFA scores, use of ICU resources and ICU- and 30-day mortality were recorded. Multivariate logistic regression analysis was used to identify factors associated with 30-day mortality.
Results: Patients had a median age of 84 [IQR 82–87] years and a mean CFS of 4.75 (± 1.6 standard-deviation) points. More than half of the patients (53.6%) were classified as frail (CFS ≥ 5). ICU-mortality was 17.3% and 30-day mortality was 31.2%. The cause of admission (planned vs. unplanned), (OR 5.74) and the CFS (OR 1.44 per point increase) were independent predictors of 30-day survival.
Conclusions: The CFS is an easy determinable valuable tool for prediction of 30-day ICU survival in octogenarians, thus, it may facilitate decision-making for intensive care givers in Germany.
Trial registration: The VIP-1 study was retrospectively registered on ClinicalTrials.gov (ID: NCT03134807) on May 1, 2017.
Background: Intensive Care Resources are heavily utilized during the COVID-19 pandemic. However, risk stratification and prediction of SARS-CoV-2 patient clinical outcomes upon ICU admission remain inadequate. This study aimed to develop a machine learning model, based on retrospective & prospective clinical data, to stratify patient risk and predict ICU survival and outcomes. Methods: A Germany-wide electronic registry was established to pseudonymously collect admission, therapeutic and discharge information of SARS-CoV-2 ICU patients retrospectively and prospectively. Machine learning approaches were evaluated for the accuracy and interpretability of predictions. The Explainable Boosting Machine approach was selected as the most suitable method. Individual, non-linear shape functions for predictive parameters and parameter interactions are reported. Results: 1039 patients were included in the Explainable Boosting Machine model, 596 patients retrospectively collected, and 443 patients prospectively collected. The model for prediction of general ICU outcome was shown to be more reliable to predict “survival”. Age, inflammatory and thrombotic activity, and severity of ARDS at ICU admission were shown to be predictive of ICU survival. Patients’ age, pulmonary dysfunction and transfer from an external institution were predictors for ECMO therapy. The interaction of patient age with D-dimer levels on admission and creatinine levels with SOFA score without GCS were predictors for renal replacement therapy. Conclusions: Using Explainable Boosting Machine analysis, we confirmed and weighed previously reported and identified novel predictors for outcome in critically ill COVID-19 patients. Using this strategy, predictive modeling of COVID-19 ICU patient outcomes can be performed overcoming the limitations of linear regression models. Trial registration “ClinicalTrials” (clinicaltrials.gov) under NCT04455451.