Precision Symptom Phenotyping Identifies Early Clinical and Proteomic Predictors of Distinct COVID-19 Sequelae

Nusrat J. Epsi; Josh G. Chenoweth; Paul W. Blair; David A. Lindholm; Anuradha Ganesan; Tahaniyat Lalani; Alfred Smith; Rupal M. Mody; Milissa U. Jones; Rhonda E. Colombo; Christopher J. Colombo; Christina Schofield; Evan C. Ewers; Derek T. Larson; Catherine M. Berjohn; Ryan C. Maves; Anthony C. Fries; David Chang; Andrew Wyatt; Ann I. Scher; Celia Byrne; Jennifer Rusiecki; David L. Saunders; Jeffrey Livezey; Allison Malloy; Samantha Bazan; Carlos Maldonado; Margaret Sanchez Edwards; Katrin Mende; Mark P. Simons; Robert J. O'connell; David R. Tribble; Brian K. Agan; Timothy H. Burgess; Simon D. Pollett; Stephanie A. Richard

doi:10.1093/infdis/jiae318

Precision Symptom Phenotyping Identifies Early Clinical and Proteomic Predictors of Distinct COVID-19 Sequelae

Nusrat J. Epsi^*, Josh G. Chenoweth, Paul W. Blair, David A. Lindholm, Anuradha Ganesan, Tahaniyat Lalani, Alfred Smith, Rupal M. Mody, Milissa U. Jones, Rhonda E. Colombo, Christopher J. Colombo, Christina Schofield, Evan C. Ewers, Derek T. Larson, Catherine M. Berjohn, Ryan C. Maves, Anthony C. Fries, David Chang, Andrew Wyatt, Ann I. ScherCelia Byrne, Jennifer Rusiecki, David L. Saunders, Jeffrey Livezey, Allison Malloy, Samantha Bazan, Carlos Maldonado, Margaret Sanchez Edwards, Katrin Mende, Mark P. Simons, Robert J. O'connell, David R. Tribble, Brian K. Agan, Timothy H. Burgess, Simon D. Pollett, Stephanie A. Richard^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

Background Post-COVID conditions (PCC) are difficult to characterize, diagnose, predict, and treat due to overlapping symptoms and poorly understood pathology. Identifying inflammatory profiles may improve clinical prognostication and trial endpoints. Methods This analysis included 1988 SARS-CoV-2 positive U.S. Military Health System beneficiaries who had quantitative post-COVID symptom scores. Among participants who reported moderate-to-severe symptoms on surveys collected 6 months post-SARS-CoV-2 infection, principal component analysis followed by k-means clustering identified distinct clusters of symptoms. Results Three symptom-based clusters were identified: a sensory cluster (loss of smell and/or taste), a fatigue/difficulty thinking cluster, and a difficulty breathing/exercise intolerance cluster. Individuals within the sensory cluster were all outpatients during their initial COVID-19 presentation. The difficulty breathing cluster had a higher likelihood of obesity and COVID-19 hospitalization than those with no/mild symptoms at 6 months post-infection. Multinomial regression linked early post-infection D-dimer and IL-1RA elevation to fatigue/difficulty thinking and elevated ICAM-1 concentrations to sensory symptoms. Conclusions We identified three distinct symptom-based PCC phenotypes with specific clinical risk factors and early post-infection inflammatory predictors. With further validation and characterization, this framework may allow more precise classification of PCC cases and potentially improve the diagnosis, prognostication, and treatment of PCC.

Original language	English
Pages (from-to)	39-49
Number of pages	11
Journal	Journal of Infectious Diseases
Volume	232
Issue number	1
DOIs	https://doi.org/10.1093/infdis/jiae318
State	Published - 15 Jul 2025

Keywords

COVID-19 symptoms
SARS-CoV-2
long COVID
machine learning
post-COVID conditions

Access to Document

10.1093/infdis/jiae318

Cite this

Epsi, N. J., Chenoweth, J. G., Blair, P. W., Lindholm, D. A., Ganesan, A., Lalani, T., Smith, A., Mody, R. M., Jones, M. U., Colombo, R. E., Colombo, C. J., Schofield, C., Ewers, E. C., Larson, D. T., Berjohn, C. M., Maves, R. C., Fries, A. C., Chang, D., Wyatt, A., ... Richard, S. A. (2025). Precision Symptom Phenotyping Identifies Early Clinical and Proteomic Predictors of Distinct COVID-19 Sequelae. Journal of Infectious Diseases, 232(1), 39-49. https://doi.org/10.1093/infdis/jiae318

@article{2cacac22a2de4d5c9edf2df4a1250a33,

title = "Precision Symptom Phenotyping Identifies Early Clinical and Proteomic Predictors of Distinct COVID-19 Sequelae",

abstract = "Background Post-COVID conditions (PCC) are difficult to characterize, diagnose, predict, and treat due to overlapping symptoms and poorly understood pathology. Identifying inflammatory profiles may improve clinical prognostication and trial endpoints. Methods This analysis included 1988 SARS-CoV-2 positive U.S. Military Health System beneficiaries who had quantitative post-COVID symptom scores. Among participants who reported moderate-to-severe symptoms on surveys collected 6 months post-SARS-CoV-2 infection, principal component analysis followed by k-means clustering identified distinct clusters of symptoms. Results Three symptom-based clusters were identified: a sensory cluster (loss of smell and/or taste), a fatigue/difficulty thinking cluster, and a difficulty breathing/exercise intolerance cluster. Individuals within the sensory cluster were all outpatients during their initial COVID-19 presentation. The difficulty breathing cluster had a higher likelihood of obesity and COVID-19 hospitalization than those with no/mild symptoms at 6 months post-infection. Multinomial regression linked early post-infection D-dimer and IL-1RA elevation to fatigue/difficulty thinking and elevated ICAM-1 concentrations to sensory symptoms. Conclusions We identified three distinct symptom-based PCC phenotypes with specific clinical risk factors and early post-infection inflammatory predictors. With further validation and characterization, this framework may allow more precise classification of PCC cases and potentially improve the diagnosis, prognostication, and treatment of PCC.",

keywords = "COVID-19 symptoms, SARS-CoV-2, long COVID, machine learning, post-COVID conditions",

author = "Epsi, {Nusrat J.} and Chenoweth, {Josh G.} and Blair, {Paul W.} and Lindholm, {David A.} and Anuradha Ganesan and Tahaniyat Lalani and Alfred Smith and Mody, {Rupal M.} and Jones, {Milissa U.} and Colombo, {Rhonda E.} and Colombo, {Christopher J.} and Christina Schofield and Ewers, {Evan C.} and Larson, {Derek T.} and Berjohn, {Catherine M.} and Maves, {Ryan C.} and Fries, {Anthony C.} and David Chang and Andrew Wyatt and Scher, {Ann I.} and Celia Byrne and Jennifer Rusiecki and Saunders, {David L.} and Jeffrey Livezey and Allison Malloy and Samantha Bazan and Carlos Maldonado and Edwards, {Margaret Sanchez} and Katrin Mende and Simons, {Mark P.} and O'connell, {Robert J.} and Tribble, {David R.} and Agan, {Brian K.} and Burgess, {Timothy H.} and Pollett, {Simon D.} and Richard, {Stephanie A.}",

note = "Publisher Copyright: {\textcopyright} 2024 Infectious Diseases Society of America.",

year = "2025",

month = jul,

day = "15",

doi = "10.1093/infdis/jiae318",

language = "English",

volume = "232",

pages = "39--49",

journal = "Journal of Infectious Diseases",

issn = "0022-1899",

publisher = "Oxford University Press",

number = "1",

}

Epsi, NJ, Chenoweth, JG, Blair, PW, Lindholm, DA , Ganesan, A , Lalani, T, Smith, A, Mody, RM, Jones, MU, Colombo, RE , Colombo, CJ , Schofield, C, Ewers, EC, Larson, DT, Berjohn, CM, Maves, RC, Fries, AC, Chang, D, Wyatt, A, Scher, AI, Byrne, C , Rusiecki, J, Saunders, DL, Livezey, J, Malloy, A, Bazan, S, Maldonado, C, Edwards, MS, Mende, K , Simons, MP , O'connell, RJ , Tribble, DR , Agan, BK , Burgess, TH , Pollett, SD & Richard, SA 2025, 'Precision Symptom Phenotyping Identifies Early Clinical and Proteomic Predictors of Distinct COVID-19 Sequelae', Journal of Infectious Diseases, vol. 232, no. 1, pp. 39-49. https://doi.org/10.1093/infdis/jiae318

TY - JOUR

T1 - Precision Symptom Phenotyping Identifies Early Clinical and Proteomic Predictors of Distinct COVID-19 Sequelae

AU - Epsi, Nusrat J.

AU - Chenoweth, Josh G.

AU - Blair, Paul W.

AU - Lindholm, David A.

AU - Ganesan, Anuradha

AU - Lalani, Tahaniyat

AU - Smith, Alfred

AU - Mody, Rupal M.

AU - Jones, Milissa U.

AU - Colombo, Rhonda E.

AU - Colombo, Christopher J.

AU - Schofield, Christina

AU - Ewers, Evan C.

AU - Larson, Derek T.

AU - Berjohn, Catherine M.

AU - Maves, Ryan C.

AU - Fries, Anthony C.

AU - Chang, David

AU - Wyatt, Andrew

AU - Scher, Ann I.

AU - Byrne, Celia

AU - Rusiecki, Jennifer

AU - Saunders, David L.

AU - Livezey, Jeffrey

AU - Malloy, Allison

AU - Bazan, Samantha

AU - Maldonado, Carlos

AU - Edwards, Margaret Sanchez

AU - Mende, Katrin

AU - Simons, Mark P.

AU - O'connell, Robert J.

AU - Tribble, David R.

AU - Agan, Brian K.

AU - Burgess, Timothy H.

AU - Pollett, Simon D.

AU - Richard, Stephanie A.

PY - 2025/7/15

Y1 - 2025/7/15

N2 - Background Post-COVID conditions (PCC) are difficult to characterize, diagnose, predict, and treat due to overlapping symptoms and poorly understood pathology. Identifying inflammatory profiles may improve clinical prognostication and trial endpoints. Methods This analysis included 1988 SARS-CoV-2 positive U.S. Military Health System beneficiaries who had quantitative post-COVID symptom scores. Among participants who reported moderate-to-severe symptoms on surveys collected 6 months post-SARS-CoV-2 infection, principal component analysis followed by k-means clustering identified distinct clusters of symptoms. Results Three symptom-based clusters were identified: a sensory cluster (loss of smell and/or taste), a fatigue/difficulty thinking cluster, and a difficulty breathing/exercise intolerance cluster. Individuals within the sensory cluster were all outpatients during their initial COVID-19 presentation. The difficulty breathing cluster had a higher likelihood of obesity and COVID-19 hospitalization than those with no/mild symptoms at 6 months post-infection. Multinomial regression linked early post-infection D-dimer and IL-1RA elevation to fatigue/difficulty thinking and elevated ICAM-1 concentrations to sensory symptoms. Conclusions We identified three distinct symptom-based PCC phenotypes with specific clinical risk factors and early post-infection inflammatory predictors. With further validation and characterization, this framework may allow more precise classification of PCC cases and potentially improve the diagnosis, prognostication, and treatment of PCC.

AB - Background Post-COVID conditions (PCC) are difficult to characterize, diagnose, predict, and treat due to overlapping symptoms and poorly understood pathology. Identifying inflammatory profiles may improve clinical prognostication and trial endpoints. Methods This analysis included 1988 SARS-CoV-2 positive U.S. Military Health System beneficiaries who had quantitative post-COVID symptom scores. Among participants who reported moderate-to-severe symptoms on surveys collected 6 months post-SARS-CoV-2 infection, principal component analysis followed by k-means clustering identified distinct clusters of symptoms. Results Three symptom-based clusters were identified: a sensory cluster (loss of smell and/or taste), a fatigue/difficulty thinking cluster, and a difficulty breathing/exercise intolerance cluster. Individuals within the sensory cluster were all outpatients during their initial COVID-19 presentation. The difficulty breathing cluster had a higher likelihood of obesity and COVID-19 hospitalization than those with no/mild symptoms at 6 months post-infection. Multinomial regression linked early post-infection D-dimer and IL-1RA elevation to fatigue/difficulty thinking and elevated ICAM-1 concentrations to sensory symptoms. Conclusions We identified three distinct symptom-based PCC phenotypes with specific clinical risk factors and early post-infection inflammatory predictors. With further validation and characterization, this framework may allow more precise classification of PCC cases and potentially improve the diagnosis, prognostication, and treatment of PCC.

KW - COVID-19 symptoms

KW - SARS-CoV-2

KW - long COVID

KW - machine learning

KW - post-COVID conditions

UR - http://www.scopus.com/inward/record.url?scp=105012384012&partnerID=8YFLogxK

U2 - 10.1093/infdis/jiae318

DO - 10.1093/infdis/jiae318

M3 - Article

C2 - 38916431

AN - SCOPUS:105012384012

SN - 0022-1899

VL - 232

SP - 39

EP - 49

JO - Journal of Infectious Diseases

JF - Journal of Infectious Diseases

IS - 1

ER -