{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Su CY"],"funding":["Cancer Research UK","NIDDK NIH HHS","Medical Research Council","National Institute for Health Research (NIHR)","NCI NIH HHS","Wellcome Trust","NIH HHS","Canadian Institutes of Health Research"],"pagination":["6236"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10107586"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["13(1)"],"pubmed_abstract":["Predicting COVID-19 severity is difficult, and the biological pathways involved are not fully understood. To approach this problem, we measured 4701 circulating human protein abundances in two independent cohorts totaling 986 individuals. We then trained prediction models including protein abundances and clinical risk factors to predict COVID-19 severity in 417 subjects and tested these models in a separate cohort of 569 individuals. For severe COVID-19, a baseline model including age and sex provided an area under the receiver operator curve (AUC) of 65% in the test cohort. Selecting 92 proteins from the 4701 unique protein abundances improved the AUC to 88% in the training cohort, which remained relatively stable in the testing cohort at 86%, suggesting good generalizability. Proteins se"],"journal":["Scientific reports"],"pubmed_title":["Circulating proteins to predict COVID-19 severity."],"pmcid":["PMC10107586"],"funding_grant_id":["365825","U24 CA224319","S10 OD030463","P30 CA196521","S10 OD026880","C18281/A29019","MC_UU_00006/1","U01 DK124165"],"pubmed_authors":["Laurent L","Del Valle DM","Mount Sinai COVID-19 Biobank Team","Adeleye O","Kimchi N","Nakanishi T","Richards JB","Tselios C","Greenwood CMT","Hinterberg MA","Su CY","Xie H","Paterson C","Schadt E","Morrison DR","Vulesevic B","Durand M","Chen Y","Patel M","Brassard N","Cedillo MA","Marvin R","Kim-Schulze S","Gnjatic S","Argueta K","Xue X","Brunet-Ratnasingham E","Charney AW","Carrasco-Zanini J","Mooser V","Jeon W","Marron T","Henry D","Butler-Laporte G","Tuballes K","Beckmann ND","Kaufmann DE","Rezk N","Merad M","Duggan N","Schurr E","Farjoun Y","Pietzner M","Zaki N","Scott I","Pineau J","Almamlouk N","Simons NW","Bouab M","Mouskas K","Guzman C","Moussa Y","Abdullah T","Gonzalez-Kozlova E","Cheng E","Zhou S","Afrasiabi Z","Nie K","Forgetta V","Langenberg C","Thompson R","Afilalo M","Harris J","Afilalo J","Petitjean L","DeLuca C"],"additional_accession":[]},"is_claimable":false,"name":"Circulating proteins to predict COVID-19 severity.","description":"Predicting COVID-19 severity is difficult, and the biological pathways involved are not fully understood. To approach this problem, we measured 4701 circulating human protein abundances in two independent cohorts totaling 986 individuals. We then trained prediction models including protein abundances and clinical risk factors to predict COVID-19 severity in 417 subjects and tested these models in a separate cohort of 569 individuals. For severe COVID-19, a baseline model including age and sex provided an area under the receiver operator curve (AUC) of 65% in the test cohort. Selecting 92 proteins from the 4701 unique protein abundances improved the AUC to 88% in the training cohort, which remained relatively stable in the testing cohort at 86%, suggesting good generalizability. Proteins se","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Apr","modification":"2026-06-04T05:00:18.916Z","creation":"2025-02-19T03:59:56.975Z"},"accession":"S-EPMC10107586","cross_references":{"pubmed":["37069249"],"doi":["10.1038/s41598-023-31850-y"]}}