tetano
Editor, Senior Moderator
BMC Infect Dis
. 2025 May 8;25(1):677.
doi: 10.1186/s12879-025-10914-6. Peripheral blood cytokine profiles predict the severity of SARS-CoV-2 infection: an EPIC[SUP]3[/SUP] study analysis
Xumin Li[SUP] 1 2 [/SUP], Vivek Pakanati[SUP] 1 [/SUP], Cindy Liu[SUP] 1 [/SUP], Tracy Wang[SUP] 1 [/SUP], Daniel Morelli[SUP] 1 [/SUP], Anna Korpak[SUP] 1 [/SUP], Aaron Baraff[SUP] 1 [/SUP], Stuart N Isaacs[SUP] 3 4 [/SUP], Amy Vittor[SUP] 5 6 [/SUP], Kyong-Mi Chang[SUP] 3 4 [/SUP], Elizabeth Le[SUP] 7 [/SUP], Nicholas L Smith[SUP] 1 2 [/SUP], Jennifer S Lee[SUP] 7 8 [/SUP], Jennifer M Ross[SUP] 1 9 [/SUP], Javeed A Shah[SUP] 10 11 [/SUP]; EPIC3 Investigators
Collaborators, Affiliations
Background: Predicting which patients will develop severe COVID-19 complications could improve clinical care. Peripheral blood cytokine profiles may predict the severity of SARS-CoV-2 infection, but none have been identified in US Veterans.
Methods: We analyzed peripheral blood cytokine profiles from 202 participants in the EPIC[SUP]3[/SUP] study, a prospective observational cohort of US Veterans tested for SARS-CoV-2 across 15 VA medical centers. Illness severity was assessed based on the highest level documented during the first 60 days after recruitment. We correlated cytokine levels with illness severity using LASSO logistic regression, random forest, and XGBoost models on a 70% training set and calculated the AUC on a 30% test set.
Results: LASSO regression identified 6 cytokines as predictors of SARS-CoV-2 severity with 77.3% AUC in the test set. Random forest and XGBoost models achieved an AUC of 80.4% and 80.7% in the test set, respectively. All models assigned a feature importance to each cytokine, with IP-10, MCP-1, and HGF consistently identified as key markers.
Conclusions: Cytokine profiles are predictive of SARS-CoV-2 severity in US Veterans and may guide tailored interventions for improved patient management.
Keywords: COVID-19; Cytokines; Illness severity; LASSO regression; Predictive biomarkers; Random forest; SARS-CoV-2; Veterans; XGBoost.
. 2025 May 8;25(1):677.
doi: 10.1186/s12879-025-10914-6. Peripheral blood cytokine profiles predict the severity of SARS-CoV-2 infection: an EPIC[SUP]3[/SUP] study analysis
Xumin Li[SUP] 1 2 [/SUP], Vivek Pakanati[SUP] 1 [/SUP], Cindy Liu[SUP] 1 [/SUP], Tracy Wang[SUP] 1 [/SUP], Daniel Morelli[SUP] 1 [/SUP], Anna Korpak[SUP] 1 [/SUP], Aaron Baraff[SUP] 1 [/SUP], Stuart N Isaacs[SUP] 3 4 [/SUP], Amy Vittor[SUP] 5 6 [/SUP], Kyong-Mi Chang[SUP] 3 4 [/SUP], Elizabeth Le[SUP] 7 [/SUP], Nicholas L Smith[SUP] 1 2 [/SUP], Jennifer S Lee[SUP] 7 8 [/SUP], Jennifer M Ross[SUP] 1 9 [/SUP], Javeed A Shah[SUP] 10 11 [/SUP]; EPIC3 Investigators
Collaborators, Affiliations
- PMID: 40340594
- PMCID: PMC12063214
- DOI: 10.1186/s12879-025-10914-6
Background: Predicting which patients will develop severe COVID-19 complications could improve clinical care. Peripheral blood cytokine profiles may predict the severity of SARS-CoV-2 infection, but none have been identified in US Veterans.
Methods: We analyzed peripheral blood cytokine profiles from 202 participants in the EPIC[SUP]3[/SUP] study, a prospective observational cohort of US Veterans tested for SARS-CoV-2 across 15 VA medical centers. Illness severity was assessed based on the highest level documented during the first 60 days after recruitment. We correlated cytokine levels with illness severity using LASSO logistic regression, random forest, and XGBoost models on a 70% training set and calculated the AUC on a 30% test set.
Results: LASSO regression identified 6 cytokines as predictors of SARS-CoV-2 severity with 77.3% AUC in the test set. Random forest and XGBoost models achieved an AUC of 80.4% and 80.7% in the test set, respectively. All models assigned a feature importance to each cytokine, with IP-10, MCP-1, and HGF consistently identified as key markers.
Conclusions: Cytokine profiles are predictive of SARS-CoV-2 severity in US Veterans and may guide tailored interventions for improved patient management.
Keywords: COVID-19; Cytokines; Illness severity; LASSO regression; Predictive biomarkers; Random forest; SARS-CoV-2; Veterans; XGBoost.