RESUMO
It has recently been hypothesised that Vitamin K could play a role in COVID-19. We aimed to test the hypothesis that low vitamin K status is a common characteristic of patients hospitalized with COVID-19 compared to population controls; and that low vitamin K status predicts mortality in COVID-19 patients. In a cohort of 138 COVID-19 patients and 140 population controls, we measured plasma dephosphorylated-uncarboxylated Matrix Gla Protein (dp-ucMGP), which reflects the functional Vitamin K status in peripheral tissue. Fourty-three patients died within 90-days from admission. In patients, levels of dp-ucMGP differed significantly between survivors (mean 877; 95% CI: 778; 995) and non-survivors (mean 1445; 95% CI: 1148; 1820). Furthermore, levels of dp-ucMGP (pmol/L) were considerably higher in patients (mean 1022; 95% CI: 912; 1151) compared to controls (mean 509; 95% CI: 485; 540). Cox regression survival analysis showed that increasing levels of dp-ucMGP (reflecting low Vitamin K status) were associated with higher mortality risk (sex- and age-adjusted hazard ratio per doubling of dp-ucMGP was 1.50, 95% CI: 1.03; 2.18). In conclusion, we found that low Vitamin K status predicted mortality in patients with COVID-19 supporting a potential role of Vitamin K in COVID-19.
RESUMO
BackgroundPatients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that Machine Learning (ML) models could be used to predict risks at different stages of management (at diagnosis, hospital admission and ICU admission) and thereby provide insights into drivers and prognostic markers of disease progression and death. MethodsFrom a cohort of approx. 2.6 million citizens in the two regions of Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. A cohort of SARS- CoV-2 positive cases from the United Kingdom Biobank was used for external validation. FindingsThe ML models predicted the risk of death (Receiver Operation Characteristics - Area Under the Curve, ROC-AUC) of 0.904 at diagnosis, 0.818, at hospital admission and 0.723 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. We identified some common risk factors, including age, body mass index (BMI) and hypertension as driving factors, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. InterpretationML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. Prognostic features included age, BMI and hypertension, although markers of shock and organ dysfunction became more important in more severe cases. We provide access to an online risk calculator based on these findings. FundingThe study was funded by grants from the Novo Nordisk Foundation to MS (#NNF20SA0062879 and #NNF19OC0055183) and MN (#NNF20SA0062879). The foundation took no part in project design, data handling and manuscript preparation.
