Clinical prediction models for mortality in patients with covid-19: external validation and individual participant data meta-analysis.

OBJECTIVE: To externally validate various prognostic models and scoring rules for predicting short term mortality in patients admitted to hospital for covid-19. DESIGN: Two stage individual participant data meta-analysis. SETTING: Secondary and tertiary care. PARTICIPANTS: 46 914 patients across 18 countries, admitted to a hospital with polymerase chain reaction confirmed covid-19 from November 2019 to April 2021. DATA SOURCES: Multiple (clustered) cohorts in Brazil, Belgium, China, Czech Republic, Egypt, France, Iran, Israel, Italy, Mexico, Netherlands, Portugal, Russia, Saudi Arabia, Spain, Sweden, United Kingdom, and United States previously identified by a living systematic review of covid-19 prediction models published in The BMJ, and through PROSPERO, reference checking, and expert knowledge. MODEL SELECTION AND ELIGIBILITY CRITERIA: Prognostic models identified by the living systematic review and through contacting experts. A priori models were excluded that had a high risk of bias in the participant domain of PROBAST (prediction model study risk of bias assessment tool) or for which the applicability was deemed poor. METHODS: Eight prognostic models with diverse predictors were identified and validated. A two stage individual participant data meta-analysis was performed of the estimated model concordance (C) statistic, calibration slope, calibration-in-the-large, and observed to expected ratio (O:E) across the included clusters. MAIN OUTCOME MEASURES: 30 day mortality or in-hospital mortality. RESULTS: Datasets included 27 clusters from 18 different countries and contained data on 46 914patients. The pooled estimates ranged from 0.67 to 0.80 (C statistic), 0.22 to 1.22 (calibration slope), and 0.18 to 2.59 (O:E ratio) and were prone to substantial between study heterogeneity. The 4C Mortality Score by Knight et al (pooled C statistic 0.80, 95% confidence interval 0.75 to 0.84, 95% prediction interval 0.72 to 0.86) and clinical model by Wang et al (0.77, 0.73 to 0.80, 0.63 to 0.87) had the highest discriminative ability. On average, 29% fewer deaths were observed than predicted by the 4C Mortality Score (pooled O:E 0.71, 95% confidence interval 0.45 to 1.11, 95% prediction interval 0.21 to 2.39), 35% fewer than predicted by the Wang clinical model (0.65, 0.52 to 0.82, 0.23 to 1.89), and 4% fewer than predicted by Xie et al's model (0.96, 0.59 to 1.55, 0.21 to 4.28). CONCLUSION: The prognostic value of the included models varied greatly between the data sources. Although the Knight 4C Mortality Score and Wang clinical model appeared most promising, recalibration (intercept and slope updates) is needed before implementation in routine care.

Lower plasma calcium associated with COVID-19, but not with disease severity: a two-centre retrospective cohort study.

BACKGROUND: Previous studies indicate hypocalcaemia as a potential diagnostic and prognostic marker of corona-virus disease 2019 (COVID-19). Our aim was to investigate these relations in more detail in a large test cohort and an independent validation cohort. METHODS: We retrospectively included 2792 COVID-19 suspected patients that presented to the emergency department (ED) of two hospitals. Plasma calcium and ionized plasma calcium levels were compared between COVID-19 positive and negative patients, and between severe and non-severe COVID-19 patients using univariate and multivariate analyses in the first hospital (N = 1363). Severe COVID-19 was defined as intensive care unit (ICU) admission or death within 28 d after admission. The results were validated by repeating the same analyses in the second hospital (N = 1429). RESULTS: A total of 693 (24.8%) of the enrolled patients were COVID-19 positive, of whom 238 (34.3%) had severe COVID-19. In both hospitals, COVID-19 positive patients had lower plasma calcium levels than COVID-19 negative patients, regardless of correction for albumin, in univariate and multivariate analysis (Δ0.06-0.13 mmol/L, p < .001). Ionized plasma calcium concentrations, with and without correction for pH, were also lower in COVID-19 positive patients in multivariate analyses (Δ0.02-0.05 mmol/L, N = 567, p < .001). However, we did not find a significant association between COVID-19 disease severity and plasma calcium in multivariate analyses. CONCLUSIONS: Plasma calcium concentrations were lower in COVID-19 positive than COVID-19 negative patients but we found no association with disease severity in multivariate analyses. Further understanding of plasma calcium perturbation may facilitate the development of new preventive and therapeutic modalities for the current pandemic.

Deep learning with robustness to missing data: A novel approach to the detection of COVID-19.

In the context of the current global pandemic and the limitations of the RT-PCR test, we propose a novel deep learning architecture, DFCN (Denoising Fully Connected Network). Since medical facilities around the world differ enormously in what laboratory tests or chest imaging may be available, DFCN is designed to be robust to missing input data. An ablation study extensively evaluates the performance benefits of the DFCN as well as its robustness to missing inputs. Data from 1088 patients with confirmed RT-PCR results are obtained from two independent medical facilities. The data includes results from 27 laboratory tests and a chest x-ray scored by a deep learning model. Training and test datasets are taken from different medical facilities. Data is made publicly available. The performance of DFCN in predicting the RT-PCR result is compared with 3 related architectures as well as a Random Forest baseline. All models are trained with varying levels of masked input data to encourage robustness to missing inputs. Missing data is simulated at test time by masking inputs randomly. DFCN outperforms all other models with statistical significance using random subsets of input data with 2-27 available inputs. When all 28 inputs are available DFCN obtains an AUC of 0.924, higher than any other model. Furthermore, with clinically meaningful subsets of parameters consisting of just 6 and 7 inputs respectively, DFCN achieves higher AUCs than any other model, with values of 0.909 and 0.919.

Rapid identification of SARS-CoV-2-infected patients at the emergency department using routine testing.

Objectives: The novel coronavirus disease 19 (COVID-19), caused by SARS-CoV-2, spreads rapidly across the world. The exponential increase in the number of cases has resulted in overcrowding of emergency departments (ED). Detection of SARS-CoV-2 is based on an RT-PCR of nasopharyngeal swab material. However, RT-PCR testing is time-consuming and many hospitals deal with a shortage of testing materials. Therefore, we aimed to develop an algorithm to rapidly evaluate an individual's risk of SARS-CoV-2 infection at the ED. Methods: In this multicenter retrospective study, routine laboratory parameters (C-reactive protein, lactate dehydrogenase, ferritin, absolute neutrophil and lymphocyte counts), demographic data and the chest X-ray/CT result from 967 patients entering the ED with respiratory symptoms were collected. Using these parameters, an easy-to-use point-based algorithm, called the corona-score, was developed to discriminate between patients that tested positive for SARS-CoV-2 by RT-PCR and those testing negative. Computational sampling was used to optimize the corona-score. Validation of the model was performed using data from 592 patients. Results: The corona-score model yielded an area under the receiver operating characteristic curve of 0.91 in the validation population. Patients testing negative for SARS-CoV-2 showed a median corona-score of 3 vs. 11 (scale 0-14) in patients testing positive for SARS-CoV-2 (p<0.001). Using cut-off values of 4 and 11 the model has a sensitivity and specificity of 96 and 95%, respectively. Conclusions: The corona-score effectively predicts SARS-CoV-2 RT-PCR outcome based on routine parameters. This algorithm provides the means for medical professionals to rapidly evaluate SARS-CoV-2 infection status of patients presenting at the ED with respiratory symptoms.