COVID-19 is characterised by dysregulated immune responses, metabolic dysfunction and adverse effects on the function of multiple organs. To understand how host responses contribute to COVID-19 pathophysiology, we used a multi-omics approach to identify molecular markers in peripheral blood and plasma samples that distinguish COVID-19 patients experiencing a range of disease severities. A large number of expressed genes, proteins, metabolites and extracellular RNAs (exRNAs) were identified that exhibited strong associations with various clinical parameters. Multiple sets of tissue-specific proteins and exRNAs varied significantly in both mild and severe patients, indicative of multi-organ damage. The continuous activation of IFN-I signalling and neutrophils, as well as a high level of inflammatory cytokines, were observed in severe disease patients. In contrast, COVID-19 in mild patients was characterised by robust T cell responses. Finally, we show that some of expressed genes, proteins and exRNAs can be used as biomarkers to predict the clinical outcomes of SARS-CoV-2 infection. These data refine our understanding of the pathophysiology and clinical progress of COVID-19 and will help guide future studies in this area.