Circulating proteins to predict adverse COVID-19 outcomes
Su, C.-Y.; Zhou, S.; Gonzalez-Kozlova, E.; Butler-Laporte, G.; Brunet-Ratnasingham, E.; Nakanishi, T.; Jeon, W.; Morrison, D.; Laurent, L.; Afilalo, J.; Afilalo, M.; Henry, D.; Chen, Y.; Carrasco-Zanini, J.; Farjoun, Y.; Pietzner, M.; Kimchi, N.; Afrasiabi, Z.; Rezk, N.; Bouab, M.; Petitjean, L.; Guzman, C.; Xue, X.; Tselios, C.; Vulesevic, B.; Adeleye, O.; Abdullah, T.; Almamlouk, N.; Moussa, Y.; DeLuca, C.; Duggan, N.; Schurr, E.; Brassard, N.; Durand, M.; Marie Del Valle, D.; Thompson, R.; Cedillo, M. A.; Schadt, E.; Nie, K.; Simons, N. W.; Mouskas, K.; Zaki, N.; Patel, M.; Xie, H.; Harris,
Show abstract
Predicting COVID-19 severity is difficult, and the biological pathways involved are not fully understood. To approach this problem, we measured 4,701 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 adverse COVID-19 outcomes 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 4,701 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 selected from different adverse COVID-19 outcomes were enriched for cytokine and cytokine receptors, but more than half of the enriched pathways were not immune-related. Taken together, these findings suggest that circulating proteins measured at early stages of disease progression are reasonably accurate predictors of adverse COVID-19 outcomes. Further research is needed to understand how to incorporate protein measurement into clinical care.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study 94%
- Developing And Validating COVID-19 Adverse Outcome Risk Prediction Models From A Bi-National European Cohort Of 5594 Patients 94%
- Results of an early second PCR test performed on SARS-CoV-2 positive patients may indicate risk for severe COVID-19 93%
Similar papers in this journal
- Antibody therapy reverses biological signatures of COVID-19 progression 94%
- Longitudinal Metabolomics of Human Plasma Reveals Robust Prognostic Markers of COVID-19 Disease Severity 93%
- Integrated plasma proteomic and single-cell immune signaling network signatures demarcate mild, moderate, and severe COVID-19 93%
Similar papers in this journal
- A Neanderthal OAS1 isoform Protects Against COVID-19 Susceptibility and Severity: Results from Mendelian Randomization and Case-Control Studies 94%
- Actionable druggable genome-wide Mendelian randomization identifies repurposing opportunities for COVID-19 92%
- An inflammatory cytokine signature helps predict COVID-19 severity and death 91%
Similar papers in this journal
- Novel clinical subphenotypes in COVID-19: derivation, validation, prediction, temporal patterns, and interaction with social determinants of health 95%
- Development of a predictive risk model for severe COVID-19 disease using population-based administrative data 93%
- Improving Pre-eclampsia Risk Prediction by Modeling Individualized Pregnancy Trajectories Derived from Routinely Collected Electronic Medical Record Data 92%
Similar papers in this journal
- Multi-omics identify LRRC15 as a COVID-19 severity predictor and persistent pro-thrombotic signals in convalescence 94%
- The relationship between autoantibodies targeting GPCRs and the renin-angiotensin system associates with COVID-19 severity 93%
- Dissecting tumor cell programs through group biology estimation in clinical single-cell transcriptomics 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.