Abstract
Background: The symptoms of coronavirus disease 2019 (COVID-19) range from moderate to critical conditions, leading to death in some patients, and the early warning indicators of the COVID-19 progression and the occurrence of its serious complications such as myocardial injury are limited. Methods: We carried out a multi-center, prospective cohort study in three hospitals in Wuhan. Genome-wide 5-hydroxymethylcytosine (5hmC) profiles in plasma cell-free DNA (cfDNA) was used to identify risk factors for COVID-19 pneumonia and develop a machine learning model using samples from 53 healthy volunteers, 66 patients with moderate COVID-19, 99 patients with severe COVID-19, and 38 patients with critical COVID-19. Results: Our warning model demonstrated that an area under the curve (AUC) for 5hmC warning moderate patients developed into severe status was 0.81 (95% CI 0.77-0.85) and for severe patients developed into critical status was 0.92 (95% CI 0.89-0.96). We further built a warning model on patients with and without myocardial injury with the AUC of 0.89 (95% CI 0.84-0.95). Conclusion: This is the first study showing the utility of 5hmC as an accurate early warning marker for disease progression and myocardial injury in patients with COVID-19. Our results show that phosphodiesterase 4D and ten-eleven translocation 2 may be important markers in the progression of COVID-19 disease.