Refine
Document Type
- Article (4)
Language
- English (4)
Has Fulltext
- yes (4)
Is part of the Bibliography
- no (4)
Keywords
- Outcome (4) (remove)
Institute
- Medizin (4)
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.
Purpose: Anaemia is one of the leading causes of death among severely injured patients. It is also known to increase the risk of death and prolong the length of hospital stay in various surgical groups. The main objective of this study is to analyse the anaemia rate on admission to the emergency department and the impact of anaemia on in-hospital mortality.
Methods: Data from the TraumaRegister DGU® (TR-DGU) between 2015 and 2019 were analysed. Inclusion criteria were age ≥ 16 years and most severe Abbreviated Injury Scale (AIS) score ≥ 3. Patients were divided into three anaemia subgroups: no or mild anaemia (NA), moderate anaemia (MA) and severe anaemia (SA). Pre-hospital data, patient characteristics, treatment in the emergency room (ER), outcomes, and differences between trauma centres were analysed.
Results: Of 67,595 patients analysed, 94.9% (n = 64,153) exhibited no or mild anaemia (Hb ≥ 9 g/dl), 3.7% (n = 2478) displayed moderate anaemia (Hb 7–8 g/dl) and 1.4% (n = 964) presented with severe anaemia (Hb < 7 g/dl). Haemoglobin (Hb) values ranged from 3 to 18 g/dl with a mean Hb value of 12.7 g/dl. In surviving patients, anaemia was associated with prolonged length of stay (LOS). Multivariate logistic regression analyses revealed moderate (p < 0.001 OR 1.88 (1.66–2.13)) and severe anaemia (p < 0.001 OR 4.21 (3.46–5.12)) to be an independent predictor for mortality. Further significant predictors are ISS score per point (OR 1.0), age 70–79 (OR 4.8), age > 80 (OR 12.0), severe pre-existing conditions (ASA 3/4) (OR 2.26), severe head injury (AIS 5/6) (OR 4.8), penetrating trauma (OR 1.8), unconsciousness (OR 4.8), shock (OR 2.2) and pre-hospital intubation (OR 1.6).
Conclusion: The majority of severely injured patients are admitted without anaemia to the ER. Injury-associated moderate and severe anaemia is an independent predictor of mortality in severely injured patients.
Purpose: Trauma is the leading cause of death in children. In adults, blood transfusion and fluid resuscitation protocols changed resulting in a decrease of morbidity and mortality over the past 2 decades. Here, transfusion and fluid resuscitation practices were analysed in severe injured children in Germany.
Methods: Severely injured children (maximum Abbreviated Injury Scale (AIS) ≥ 3) admitted to a certified trauma-centre (TraumaZentrum DGU®) between 2002 and 2017 and registered at the TraumaRegister DGU® were included and assessed regarding blood transfusion rates and fluid therapy.
Results: 5,118 children (aged 1–15 years) with a mean ISS 22 were analysed. Blood transfusion rates administered until ICU admission decreased from 18% (2002–2005) to 7% (2014–2017). Children who are transfused are increasingly seriously injured. ISS has increased for transfused children aged 1–15 years (2002–2005: mean 27.7–34.4 in 2014–2017). ISS in non-transfused children has decreased in children aged 1–15 years (2002–2005: mean 19.6 to mean 17.6 in 2014–2017). Mean prehospital fluid administration decreased from 980 to 549 ml without affecting hemodynamic instability.
Conclusion: Blood transfusion rates and amount of fluid resuscitation decreased in severe injured children over a 16-year period in Germany. Restrictive blood transfusion and fluid management has become common practice in severe injured children. A prehospital restrictive fluid management strategy in severely injured children is not associated with a worsened hemodynamic state, abnormal coagulation or base excess but leads to higher hemoglobin levels.
Background: Every year, ~ 210,000 initial implantations of hip endoprostheses are carried out in Germany alone. The “bone cement implantation syndrome” (BCIS) is considered a severe peri- and early-postoperative complication when implanting cemented prostheses. The origin of the BCIS and its impact on the clinical outcome are still uncertain. This study investigates the clinical progression after BCIS cases in patients with cemented hemiarthroplasty. Risk factors for the occurrence of BCIS are evaluated.
Material and methods* Clinical data of all patients with a proximal femur fracture and which received a cemented hemiarthroplasty within a period of 9.5 years have been collected. BCIS (+) patients and BCIS (−) patients were compared with respect to their demographics and clinical outcome. Risk factors for the development of BCIS were identified.
Results: A total of 208 patients could be included with complete data sets. The mean age was 81.1 ± 10.0 years. Overall, 37% of the patients showed symptoms of BCIS. In comparison to BCIS (−) patients there was a significantly higher rate of cardiovascular complications (27.3% vs. 13.7%, p = 0.016) and a higher in-hospital mortality rate (15.6% vs. 4.6%, p = 0.006) in BCIS (+) patients. Age, absence of a femoral borehole and ASA status were identified as statistically significant risk factors of BCIS.
Conclusion: BCIS is frequently observed and in some cases severe complication. The therapy is exclusively symptomatic; identifying preventional measures might reduce the occurrence of BCIS.