COVID-19 has been a significant public health concern for the last four years; however, not much is known about the mechanisms that lead to severe COVID-19. In this multicenter study, we combine quantitative urinary proteomics and machine learning to predict severe outcomes in hospitalized COVID-19 patients. We further combine multiple omics datasets to understand the mechanisms that drive severe COVID-19 associated kidney injury. Functional overlap and network analysis of urinary proteomics, plasma proteomics and urine sediment single cell RNA sequencing analysis show extracellular matrix and autophagy associated pathways are highly impacted in severe COVID-19. Differentially abundant proteins associated with these pathways showed high expression in cells in the juxtamedullary nephron, endothelial cells, and podocytes, indicating these kidney cell types to be potentially impacted. Further, single cell transcriptomic analysis of kidney organoids infected with SARS-CoV-2 showed dysregulation of extracellular matrix organization indicating a cohesive fibrotic response across multiomic datasets. Receptor ligand interaction analysis of the podocyte and tubule clusters in the kidney organoids showed significant reduction and loss of integrin and glomerular basement membrane receptors in the infected kidney organoids. Collectively, these data uncover extracellular matrix, degradation and adhesion associated mechanisms as a driver of COVID associated kidney injury.