Scholarlink

Background <p>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.</p> Methods <p>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&#xa0;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.</p> Results <p>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.</p> Conclusions <p>Cytokine profiles are predictive of SARS-CoV-2 severity in US Veterans and may guide tailored interventions for improved patient management.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Peripheral blood cytokine profiles predict the severity of SARS-CoV-2 infection: an EPIC3 study analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月8日

查看全文
  • Xumin Li,
  • Vivek Pakanati,
  • Cindy Liu,
  • Tracy Wang,
  • Daniel Morelli,
  • Anna Korpak,
  • Aaron Baraff,
  • Stuart N. Isaacs,
  • Amy Vittor,
  • Kyong-Mi Chang,
  • Elizabeth Le,
  • Nicholas L. Smith,
  • Jennifer S. Lee,
  • Jennifer M. Ross,
  • Javeed A. Shah,
  • Mihaela Aslan,
  • Kelly Cho,
  • J. Michael Gaziano,
  • Mark Holodniy,
  • Christine M. Hunt,
  • Anna M. Korpak,
  • Dawn T. Provenzale,
  • Christina Williams,
  • Mary-Claire Roghmann,
  • Karen KC Coffey,
  • Leslie Les Katzel,
  • Michelle Newman,
  • Gwen L. Robinson,
  • Eric Garshick,
  • Emily Wan,
  • Emma Busenkell,
  • Selena Chom,
  • Christina Collins,
  • Colleen Hynes,
  • Demerise Johnston,
  • Erin McHugh,
  • Peter Rivoira,
  • Olivia Sterns,
  • John Jack Sweeney,
  • Caroline Truland,
  • Makaila Wall,
  • Cathy Zhang,
  • Federico Perez,
  • Robin L.P. Jump,
  • Robert Bonomo,
  • David Canaday,
  • Margaret Tiktin,
  • Sara Abdelrahim,
  • Taissa A. Bej,
  • Janet Briggs,
  • Elizabeth Delancey-Niksa,
  • Oteshia Hicks,
  • Corinne Kowal,
  • Alexandria Alex Nguyen,
  • Lisa Padro,
  • Roger Bedimo,
  • Rohit Manaktala,
  • Erik Guajardo,
  • Antoinette Hamilton,
  • Lisa Jones,
  • Marcia Keller-Ray,
  • Angela Dela Llana,
  • Jacob Mathew,
  • Jennifer Jen McClure,
  • Erick Meermans,
  • Erin Messick,
  • Dindi Moore-Matthews,
  • Van Nguyen,
  • Abeer Zein,
  • Lindsay Nicholson,
  • Mary Bessesen,
  • Rosa Cunningham,
  • Teresa Derian,
  • Theresa Dunn,
  • Camila Hanson,
  • Kelsey Moore,
  • Kimberly Owens,
  • Cameron Rogowski,
  • Janel Vigil,
  • Anna Wyrwa,
  • Micah McClain,
  • Ephraim Tsalik,
  • Christopher Woods,
  • James Everhart,
  • Christopher Hostler,
  • Maria Joyce,
  • Jack Anderson,
  • Marline Marlena Brown,
  • Lynette Gehlhausen,
  • Amanda Hittinger,
  • Sara Hoffman,
  • Tyffany Evans Locklear,
  • Maria Miggs,
  • Deborah Murray,
  • Bradly Brad Nicholson,
  • Ashlyn Press,
  • Jaspreet Reen,
  • Delisa Robinson,
  • Gary Wang,
  • Asmita Gupte,
  • Alaina Ritter,
  • Leslie Brown,
  • Tempa Curry,
  • Laura Dixon,
  • Jennifer Gollwitzer,
  • Rebecca Kokot,
  • Debra Robertson

摘要

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 EPIC3 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.