SARS-CoV-2 infection poses a worldwide public health problem affecting millions of people worldwide. There is a critical need for improvements in the noninvasive prognosis of COVID-19. We hypothesized that matrix-assisted laser desorption ionization mass spectrometry (MALDI-TOF MS) analysis combined with molecular-weight directed bottom-up proteomic analysis of plasma proteins may predict high and low risk cases of COVID-19. Patients and Methods: We used MALDI MS to analyze plasma small proteins and peptides isolated using C18 micro-columns from a cohort containing a total of 117 cases of high and low risk cases split into training (n = 88) and validation sets (n= 29). The plasma protein/peptide fingerprint obtained was used to train the algorithm before validation using a blinded test cohort. Several sample preparation, MS and data analysis parameters were optimized to achieve an overall accuracy of 85%, a sensitivity of 90%, and a specificity of 81% in the training set. In the blinded test set, this signature reached an overall accuracy of 93.1%, a sensitivity of 87.5%, and a specificity of 100%. From this signature, we identified two distinct regions corresponding to the single and doubly protonated proteins in the MALDI-TOF profile belonging to the same proteoforms. A combination of 1D SDS-PAGE and quantitative bottom-up proteomic analysis allowed the identification of intact and truncated forms of serum amyloid A-1 and A-2 proteins. We found a plasma proteomic profile that discriminates against patients with high and low risk COVID-19. Proteomic analysis of C18-fractionated plasma may have a role in the noninvasive prognosis of COVID-19. Further validation will be important to consolidate its clinical utility.