Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- ARDS (1)
- COVID-19 (1)
- colorectal carcinoma (1)
- critical care (1)
- microparticles (1)
- outcome (1)
- prognostic models (1)
- red blood cells (1)
- transfusion (1)
Institute
EU-Project number / Contract (GA) number
- 101015930 (2) (remove)
The biomedical consequences of allogeneic blood transfusions and the possible pathomechanisms of transfusion-related morbidity and mortality are still not entirely understood. In retrospective studies, allogeneic transfusion was associated with increased rates of cancer recurrence, metastasis and death in patients with colorectal cancer. However, correlation does not imply causation. The purpose of this study was to elucidate this empirical observation further in order to address insecurity among patients and clinicians. We focused on the in vitro effect of microparticles derived from red blood cell units (RMPs). We incubated different colon carcinoma cells with RMPs and analyzed their effects on growth, invasion, migration and tumor marker expression. Furthermore, effects on Wnt, Akt and ERK signaling were explored. Our results show RMPs do not seem to affect functional and phenotypic characteristics of different colon carcinoma cells and did not induce or inhibit Wnt, Akt or ERK signaling, albeit in cell culture models lacking tumor microenvironment. Allogeneic blood transfusions are associated with poor prognosis, but RMPs do not seem to convey tumor-enhancing effects. Most likely, the circumstances that necessitate the transfusion, such as preoperative anemia, tumor stage, perioperative blood loss and extension of surgery, take center stage.
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.