Refine
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- ARDS (1)
- Biomarkers (1)
- COVID-19 (1)
- Critical care (1)
- MR-proADM (1)
- Mortality (1)
- Outcome (1)
- Prognostic models (1)
- SOFA (1)
- Sepsis (1)
Institute
- Medizin (2)
Background: This study assessed the ability of mid-regional proadrenomedullin (MR-proADM) in comparison to conventional biomarkers (procalcitonin (PCT), lactate, C-reactive protein) and clinical scores to identify disease severity in patients with sepsis.
Methods: This is a secondary analysis of a randomised controlled trial in patients with severe sepsis or septic shock across 33 German intensive care units. The association between biomarkers and clinical scores with mortality was assessed by Cox regression analysis, area under the receiver operating characteristic and Kaplan-Meier curves. Patients were stratified into three severity groups (low, intermediate, high) for all biomarkers and scores based on cutoffs with either a 90% sensitivity or specificity.
Results: 1089 patients with a 28-day mortality rate of 26.9% were analysed. According to the Sepsis-3 definition, 41.2% and 58.8% fulfilled the criteria for sepsis and septic shock, with respective mortality rates of 20.0% and 32.1%. MR-proADM had the strongest association with mortality across all Sepsis-1 and Sepsis-3 subgroups and could facilitate a more accurate classification of low (e.g. MR-proADM vs. SOFA: N = 265 vs. 232; 9.8% vs. 13.8% mortality) and high (e.g. MR-proADM vs. SOFA: N = 161 vs. 155; 55.9% vs. 41.3% mortality) disease severity. Patients with decreasing PCT concentrations of either ≥ 20% (baseline to day 1) or ≥ 50% (baseline to day 4) but continuously high MR-proADM concentrations had a significantly increased mortality risk (HR (95% CI): 19.1 (8.0–45.9) and 43.1 (10.1–184.0)).
Conclusions: MR-proADM identifies disease severity and treatment response more accurately than established biomarkers and scores, adding additional information to facilitate rapid clinical decision-making and improve personalised sepsis treatment.
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.