Early prediction of COVID-19 patient survival by targeted plasma multi-omics and machine learning

Abstract The recent surge of COVID-19 hospitalizations severely challenges healthcare systems around the globe and demands for reliable tests predictive of disease severity and mortality. Using multiplexed targeted mass spectrometry assays on a robust triple quadrupole MS setup which is available in many clinical laboratories, we determined the precise concentrations of 100s of proteins and metabolites in plasma from hospitalized COVID-19 patients. We observed a clear distinction between COVID-19 patients and controls and, strikingly, a significant difference between survivors and non-survivors. With increasing length of hospitalization, the survivors’ samples showed a trend towards normal concentrations, indicating a potential sensitive readout of treatment success. Building a machine learning multi-omic model that considers the concentrations of ten proteins and five metabolites we could predict patient survival with 92% accuracy (AUC 0.97) at the day of hospitalization. Hence, our standardized assays represent a unique opportunity for the early stratification of hospitalized COVID-19 patients.