External Validation of COVID-19 Risk Scores during Three Waves of Pandemic in a German Cohort-A Retrospective Study.

Several risk scores were developed during the COVID-19 pandemic to identify patients at risk for critical illness as a basic step to personalizing medicine even in pandemic circumstances. However, the generalizability of these scores with regard to different populations, clinical settings, healthcare systems, and new epidemiological circumstances is unknown. The aim of our study was to compare the predictive validity of qSOFA, CRB65, NEWS, COVID-GRAM, and 4C-Mortality score. In a monocentric retrospective cohort, consecutively hospitalized adults with COVID-19 from February 2020 to June 2021 were included; risk scores at admission were calculated. The area under the receiver operating characteristic curve and the area under the precision-recall curve were compared using DeLong's method and a bootstrapping approach. A total of 347 patients were included; 23.6% were admitted to the ICU, and 9.2% died in a hospital. NEWS and 4C-Score performed best for the outcomes ICU admission and in-hospital mortality. The easy-to-use bedside score NEWS has proven to identify patients at risk for critical illness, whereas the more complex COVID-19-specific scores 4C and COVID-GRAM were not superior. Decreasing mortality and ICU-admission rates affected the discriminatory ability of all scores. A further evaluation of risk assessment is needed in view of new and rapidly changing epidemiological evolution.

Machine learning identifies ICU outcome predictors in a multicenter COVID-19 cohort.

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.

Longitudinal Isolation of Potent Near-Germline SARS-CoV-2-Neutralizing Antibodies from COVID-19 Patients.

The SARS-CoV-2 pandemic has unprecedented implications for public health, social life, and the world economy. Because approved drugs and vaccines are limited or not available, new options for COVID-19 treatment and prevention are in high demand. To identify SARS-CoV-2-neutralizing antibodies, we analyzed the antibody response of 12 COVID-19 patients from 8 to 69 days after diagnosis. By screening 4,313 SARS-CoV-2-reactive B cells, we isolated 255 antibodies from different time points as early as 8 days after diagnosis. Of these, 28 potently neutralized authentic SARS-CoV-2 with IC100 as low as 0.04 µg/mL, showing a broad spectrum of variable (V) genes and low levels of somatic mutations. Interestingly, potential precursor sequences were identified in naive B cell repertoires from 48 healthy individuals who were sampled before the COVID-19 pandemic. Our results demonstrate that SARS-CoV-2-neutralizing antibodies are readily generated from a diverse pool of precursors, fostering hope for rapid induction of a protective immune response upon vaccination.

Investigating the effect of dependence between conditions with Bayesian Linear Mixed Models for motif activity analysis.

MOTIVATION: Cellular identity and behavior is controlled by complex gene regulatory networks. Transcription factors (TFs) bind to specific DNA sequences to regulate the transcription of their target genes. On the basis of these TF motifs in cis-regulatory elements we can model the influence of TFs on gene expression. In such models of TF motif activity the data is usually modeled assuming a linear relationship between the motif activity and the gene expression level. A commonly used method to model motif influence is based on Ridge Regression. One important assumption of linear regression is the independence between samples. However, if samples are generated from the same cell line, tissue, or other biological source, this assumption may be invalid. This same assumption of independence is also applied to different yet similar experimental conditions, which may also be inappropriate. In theory, the independence assumption between samples could lead to loss in signal detection. Here we investigate whether a Bayesian model that allows for correlations results in more accurate inference of motif activities. RESULTS: We extend the Ridge Regression to a Bayesian Linear Mixed Model, which allows us to model dependence between different samples. In a simulation study, we investigate the differences between the two model assumptions. We show that our Bayesian Linear Mixed Model implementation outperforms Ridge Regression in a simulation scenario where the noise, which is the signal that can not be explained by TF motifs, is uncorrelated. However, we demonstrate that there is no such gain in performance if the noise has a similar covariance structure over samples as the signal that can be explained by motifs. We give a mathematical explanation to why this is the case. Using four representative real datasets we show that at most ∼â€<40% of the signal is explained by motifs using the linear model. With these data there is no advantage to using the Bayesian Linear Mixed Model, due to the similarity of the covariance structure. AVAILABILITY & IMPLEMENTATION: The project implementation is available at https://github.com/Sim19/SimGEXPwMotifs.

Additive Dose Response Models: Defining Synergy.

In synergy studies, one focuses on compound combinations that promise a synergistic or antagonistic effect. With the help of high-throughput techniques, a huge amount of compound combinations can be screened and filtered for suitable candidates for a more detailed analysis. Those promising candidates are chosen based on the deviance between a measured response and an expected non-interactive response. A non-interactive response is based on a principle of no interaction, such as Loewe Additivity or Bliss Independence. In a previous study, we introduced, an explicit formulation of the hitherto implicitly defined Loewe Additivity, the so-called Explicit Mean Equation. In the current study we show that this Explicit Mean Equation outperforms the original implicit formulation of Loewe Additivity and Bliss Independence when measuring synergy in terms of the deviance between measured and expected response, called the lack-of-fit. Further, we show that computing synergy as lack-of-fit outperforms a parametric approach. We show this on two datasets of compound combinations that are categorized into synergistic, non-interactive, and antagonistic.

Additive Dose Response Models: Explicit Formulation and the Loewe Additivity Consistency Condition.

High-throughput techniques allow for massive screening of drug combinations. To find combinations that exhibit an interaction effect, one filters for promising compound combinations by comparing to a response without interaction. A common principle for no interaction is Loewe Additivity which is based on the assumption that no compound interacts with itself and that two doses from different compounds having the same effect are equivalent. It then should not matter whether a component is replaced by the other or vice versa. We call this assumption the Loewe Additivity Consistency Condition (LACC). We derive explicit and implicit null reference models from the Loewe Additivity principle that are equivalent when the LACC holds. Of these two formulations, the implicit formulation is the known General Isobole Equation (Loewe, 1928), whereas the explicit one is the novel contribution. The LACC is violated in a significant number of cases. In this scenario the models make different predictions. We analyze two data sets of drug screening that are non-interactive (Cokol et al., 2011; Yadav et al., 2015) and show that the LACC is mostly violated and Loewe Additivity not defined. Further, we compare the measurements of the non-interactive cases of both data sets to the theoretical null reference models in terms of bias and mean squared error. We demonstrate that the explicit formulation of the null reference model leads to smaller mean squared errors than the implicit one and is much faster to compute.