Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Apr 10;4(4):e0000747.
doi: 10.1371/journal.pdig.0000747. eCollection 2025 Apr.

Pediatric Long COVID Subphenotypes: An EHR-based study from the RECOVER program

Vitaly Lorman  1 , L Charles Bailey  1 , Xing Song  2 , Suchitra Rao  3 , Mady Hornig  4 , Levon Utidjian  1 , Hanieh Razzaghi  1 , Asuncion Mejias  5 , John Erik Leikauf  6 , Seuli Bose Brill  7 , Andrea Allen  1 , H Timothy Bunnell  8 , Cara Reedy  8 , Abu Saleh Mohammad Mosa  9 , Benjamin D Horne  10 , Carol Reynolds Geary  11 , Cynthia H Chuang  12 , David A Williams  13 , Dimitri A Christakis  14 , Elizabeth A Chrischilles  15 , Eneida A Mendonca  16 , Lindsay G Cowell  17 , Lisa McCorkell  4 , Mei Liu  18 , Mollie R Cummins  19 , Ravi Jhaveri  20 , Saul Blecker  21 , Christopher B Forrest  1 ; RECOVER Consortium
Affiliations

Pediatric Long COVID Subphenotypes: An EHR-based study from the RECOVER program

Vitaly Lorman et al. PLOS Digit Health. .

Abstract

Pediatric Long COVID has been associated with a wide variety of symptoms, conditions, and organ systems, but distinct clinical presentations, or subphenotypes, are still being elucidated. In this exploratory analysis, we identified a cohort of pediatric (age <21) patients with evidence of Long COVID and no pre-existing complex chronic conditions using electronic health record data from 38 institutions and used an unsupervised machine learning-based approach to identify subphenotypes. Our method, an extension of the Phe2Vec algorithm, uses tens of thousands of clinical concepts from multiple domains to represent patients' clinical histories to then identify groups of patients with similar presentations. The results indicate that cardiorespiratory presentations are most common (present in 54% of patients) followed by subphenotypes marked (in decreasing order of frequency) by musculoskeletal pain, neuropsychiatric conditions, gastrointestinal symptoms, headache, and fatigue.

PubMed Disclaimer

Conflict of interest statement

Dr. Jhaveri is a consultant for AstraZeneca, Seqirus, Dynavax, receives an editorial stipend from Elsevier and Pediatric Infectious Diseases Society and royalties from Up To Date/Wolters Kluwer. Dr. Rao reports prior grant support from GSK and Biofire and is a consultant for Sequiris. Dr Bailey has received grants from Patient-Centered Outcomes Research Institute. Dr. Brill received support from Novartis and Regeneron Pharmaceuticals within the last year. Dr. Horne is a member of the advisory boards of Opsis Health and Lab Me Analytics, a consultant to Pfizer regarding risk scores (funds paid to Intermountain), and an inventor of risk scores licensed by Intermountain to Alluceo and CareCentra and is site PI of a COVID-19 grant from the Task Force for Global Health, site PI of grants from the Patient-Centered Outcomes Research Institute, a member of the advisory board of Opsis Health, and previously consulted for Pfizer regarding risk scores (funds paid to Intermountain). All other authors have no conflicts of interest to disclose.

Figures

Fig 1
Fig 1. Subphenotype model flowchart.
Fig 2
Fig 2. Subphenotype embeddings of PASC cohort B clinical histories.
Fig 3
Fig 3. Heatmap of incident post-acute diagnoses, cohort B.
Legend Summary of clusters by presence of incident PASC-associated diagnoses. To be counted, diagnoses in the respective clusters had to occur in the 28-179 post-acute period following infection and not have been present in the 18 months prior. Cells display proportions of patients in the cluster with the corresponding PASC-associated diagnosis group, and the results of Compact Letter Display (CLD) analysis are represented in superscripts. For a given incident PASC-associated diagnosis group (row), two clusters share the same letter when proportions did not differ significantly (via multiple-testing adjusted chi squared testing) between the two clusters.
See this image and copyright information in PMC

Update of

References

    1. Huerne K, Filion KB, Grad R, Ernst P, Gershon AS, Eisenberg MJ. Epidemiological and clinical perspectives of long COVID syndrome. Am J Med Open. 2023;9:100033. doi: 10.1016/j.ajmo.2023.100033 - DOI - PMC - PubMed
    1. Zheng Y-B, Zeng N, Yuan K, Tian S-S, Yang Y-B, Gao N, et al. Prevalence and risk factor for long COVID in children and adolescents: A meta-analysis and systematic review. J Infect Public Health. 2023;16(5):660–72. doi: 10.1016/j.jiph.2023.03.005 - DOI - PMC - PubMed
    1. Rao S, Gross RS, Mohandas S, Stein CR, Case A, Dreyer B, et al. Postacute sequelae of SARS-CoV-2 in children. Pediatrics. 2024;153(3):e2023062570. doi: 10.1542/peds.2023-062570 - DOI - PMC - PubMed
    1. Rao S, Lee GM, Razzaghi H, Lorman V, Mejias A, Pajor NM, et al. Clinical features and burden of post-acute sequelae of SARS-CoV-2 infection in children and adolescents: an exploratory EHR-based cohort study from the RECOVER program. medRxiv. 2022:2022.05.24.22275544. doi: 10.1101/2022.05.24.22275544 - DOI - PMC - PubMed
    1. Lorman V, Rao S, Jhaveri R, Case A, Mejias A, Pajor NM, et al. Understanding pediatric long COVID using a tree-based scan statistic approach: an EHR-based cohort study from the RECOVER Program. JAMIA Open. 2023;6(1):ooad016. doi: 10.1093/jamiaopen/ooad016 - DOI - PMC - PubMed

LinkOut - more resources