Refine
Year of publication
- 2021 (2) (remove)
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- ARDS (2) (remove)
Institute
- Medizin (2)
Background: Extracorporeal life support (ECLS) has become an integral part of modern intensive therapy. The choice of support mode depends largely on the indication. Patients with respiratory failure are predominantly treated with a venovenous (VV) approach. We hypothesized that mortality in Germany in ECLS therapy did not differ from previously reported literature
Methods: Inpatient data from Germany from 2007 to 2018 provided by the Federal Statistical Office of Germany were analysed. The international statistical classification of diseases and related health problems codes (ICD) and process keys (OPS) for extracorporeal membrane oxygenation (ECMO) types, acute respiratory distress syndrome (ARDS) and hospital mortality were used.
Results: In total, 45,647 hospitalized patients treated with ECLS were analysed. In Germany, 231 hospitals provided ECLS therapy, with a median of 4 VV-ECMO and 9 VA-ECMO in 2018. Overall hospital mortality remained higher than predicted in comparison to the values reported in the literature. The number of VV-ECMO cases increased by 236% from 825 in 2007 to 2768 in 2018. ARDS was the main indication for VV-ECMO in only 33% of the patients in the past, but that proportion increased to 60% in 2018. VA-ECMO support is of minor importance in the treatment of ARDS in Germany. The age distribution of patients undergoing ECLS has shifted towards an older population. In 2018, the hospital mortality decreased in VV-ECMO patients and VV-ECMO patients with ARDS to 53.9% (n = 1493) and 54.4% (n = 926), respectively.
Conclusions: ARDS is a severe disease with a high mortality rate despite ECLS therapy. Although endpoints and timing of the evaluations differed from those of the CESAR and EOLIA studies and the Extracorporeal Life Support Organization (ELSO) Registry, the reported mortality in these studies was lower than in the present analysis. Further prospective analyses are necessary to evaluate outcomes in ECMO therapy at the centre volume level.
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.