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.

The recently observed consistent loss of β-diversity across ecosystems indicates increasingly homogeneous communities in patches of landscapes, mainly caused by increasing land-use intensity. Biodiversity is related to numerous ecosystem functions and stability. Therefore, decreasing β-diversity is also expected to reduce multifunctionality. To assess the impact of homogenization and to develop guidelines to reverse its potentially negative effects, we combine expertise from forest science, ecology, remote sensing, chemical ecology and statistics in a collaborative and experimental β-diversity approach. Specifically, we will address the question whether the Enhancement of Structural Beta Complexity (ESBC) in forests by silviculture or natural disturbances will increase biodiversity and multifunctionality in formerly homogeneously structured production forests. Our approach will identify potential mechanisms behind observed homogenization-diversity-relationships and show how these translate into effects on multifunctionality. At eleven forest sites throughout Germany, we selected two districts as two types of small ‘forest landscapes’. In one of these two districts, we established ESBC treatments (nine differently treated 50x50 m patches with a focus on canopy cover and deadwood features). In the second, the control district, we will establish nine patches without ESBC. By a comprehensive sampling, we will monitor 18 taxonomic groups and measure 21 ecosystem functions, including key functions in temperate forests, on all patches. The statistical framework will allow a comprehensive biodiversity assessment by quantifying the different aspects of multitrophic biodiversity (taxonomical, functional and phylogenetic diversity) on different levels of biodiversity (α-, β-, γ-diversity). To combine overall diversity, we will apply the concept of multidiversity across the 18 taxa. We will use and develop new approaches for quantification and partitioning of multifunctionality at α- and β- scales. Overall, our study will herald a new research avenue, namely by experimentally describing the link between β-diversity and multifunctionality. Furthermore, we will help to develop guidelines for improved silvicultural concepts and concepts for management of natural disturbances in temperate forests reversing past homogenization effects.