Download PDF
Open Access
CC BY 4.0 · Appl Clin Inform 2025; 16(05): 1445-1456
DOI: 10.1055/a-2702-1574
Research Article

Identifying Pediatric Long COVID: Comparing an EHR Algorithm to Manual Review

Authors

  • Morgan Botdorf   *

    1   Applied Clinical Research Center, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States

  • Kimberley Dickinson   *

    1   Applied Clinical Research Center, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States

  • Vitaly Lorman

    1   Applied Clinical Research Center, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States

  • Hanieh Razzaghi

    1   Applied Clinical Research Center, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States

  • Nicole Marchesani

    1   Applied Clinical Research Center, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States

  • Suchitra Rao

    2   Department of Pediatrics, University of Colorado School of Medicine and Children's Hospital Colorado, Denver, Colorado, United States

  • Colin Rogerson

    3   Division of Critical Care, Department of Pediatrics, Indiana University School of Medicine, Indianapolis, Indiana, United States

  • Miranda Higginbotham

    1   Applied Clinical Research Center, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States

  • Asuncion Mejias

    4   Division of Infectious Diseases, Department of Pediatrics, Nationwide Children's Hospital and The Ohio State University, Columbus, Ohio, United States

  • Daria Salyakina

    5   Center for Precision Medicine, Nicklaus Children's Hospital, Miami, Florida, United States

  • Deepika Thacker

    6   Nemours Cardiac Center, Alfred I. duPont Hospital for Children, Wilmington, Delaware, United States

  • Dima Dandachi

    7   Division of Infectious Diseases, Department of Medicine, University of Missouri-Columbia, Columbia, Missouri, United States

  • Dimitri A. Christakis

    8   Center for Child Health, Behavior and Development, Seattle Children's Research Institute, Seattle, Washington, United States

  • Emily Taylor

    9   New York University Grossman School of Medicine, RECOVER Patient, Caregiver, or Community Representative, New York, New York, United States

  • Hayden T. Schwenk

    10   Division of Pediatric Infectious Diseases, Stanford School of Medicine, Palo Alto, California, United States

  • Hiroki Morizono

    11   Center for Genetic Medicine Research, Children's National Hospital, Washington, District of Columbia, United States

  • Jonathan D. Cogen

    12   Division of Pulmonary and Sleep Medicine, Department of Pediatrics, Seattle Children's Hospital, University of Washington, Seattle, Washington, United States

  • Nathan M. Pajor

    13   Division of Pulmonary Medicine, Cincinnati Children's Hospital Medical Center and University of Cincinnati College of Medicine, Cincinnati, Ohio, United States

  • Ravi Jhaveri

    14   Division of Infectious Diseases, Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, Illinois, United States

  • Christopher B. Forrest

    1   Applied Clinical Research Center, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States

  • L. Charles Bailey

    1   Applied Clinical Research Center, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States
    • on behalf of the RECOVER Consortium

Funding The research reported in this publication was conducted using PEDSnet, A Pediatric Clinical Research Network. PEDSnet has been developed with funding from the Patient-Centered Outcomes Research Institute (PCORI); PEDSnet's participation in PCORnet is funded through PCORI award RI-CHOP-01-PS10. This publication includes data from the following PEDSnet institutions: Ann & Robert H. Lurie Children's Hospital of Chicago, Children's Hospital of Philadelphia, Children's Hospital Colorado, Cincinnati Children's Hospital Medical Center, Children's National Medical Center, Nationwide Children's Hospital, Nemours Children's Health, Seattle Children's Hospital, and Stanford Medicine Children's Health. This study is funded by NIH Researching COVID to Enhance Recovery (RECOVER) Initiative (Agreement no.: OT2HL161847-01), which seeks to understand, treat, and prevent the postacute sequelae of SARS-CoV-2 infection (PASC). For more information on RECOVER, visit https://recovercovid.org/
Further Information
Also available at
  Permissions and Reprints

Abstract

Background

Long COVID, characterized by persistent or recurring symptoms post-COVID-19 infection, poses challenges for pediatric care and research due to the lack of a standardized clinical definition. Adult-focused phenotypes do not translate well to children, given developmental and physiological differences, and pediatric-specific phenotypes have not been compared with chart review.

Objective

This study introduces and evaluates a pediatric-specific rule-based computable phenotype (CP) to identify long COVID using electronic health record data. We compare its performance to manual chart review.

Methods

We applied the CP, composed of diagnostic codes empirically associated with long COVID, to 339,467 pediatric patients with SARS-CoV-2 infection in the RECOVER PCORnet EHR database. The CP identified 31,781 patients with long COVID. Clinicians conducted chart reviews on a subset of patients across 16 hospital systems to assess performance. We qualitatively reviewed discordant cases to understand differences between CP and clinician identification.

Results

Among the 651 reviewed patients (339 females, M age = 10.10 years), the CP showed moderate agreement with clinician identification (accuracy = 0.62, positive predictive value [PPV] = 0.49, negative predictive value [NPV] = 0.75, sensitivity = 0.52, specificity = 0.84). Performance was largely consistent across age and dominant variant but varied by symptom cluster count. Most discrepancies between the CP and chart review occurred when the CP identified a case, but the clinician did not, often because clinicians attributed symptoms to preexisting conditions (73%). When clinicians identified cases missed by the CP, they often used broader symptom or timing criteria (69%). Model performance improved when the CP accounted for preexisting conditions (accuracy = 0.71, PPV = 0.65, NPV = 0.74, sensitivity = 0.59, specificity = 0.79).

Conclusion

This study presents a CP for pediatric long COVID. While agreement with manual review was moderate, most discrepancies were explained by differences in interpreting symptoms when patients had preexisting conditions. Accounting for these conditions improved accuracy and highlights the need for a consensus definition. These findings support the development of reliable, scalable tools for pediatric long COVID research.

Keywords

long COVID - COVID-19 - pediatrics - electronic health records - computable phenotype - PEDSnet

Protection of Human and Animal Subjects

This study constitutes human subjects' research. Institutional Review Board (IRB) approval was obtained under Biomedical Research Alliance of New York (BRANY) protocol #21–08–508. BRANY waived the need for consent and HIPAA authorization.


Note

This content is solely the responsibility of the authors and does not necessarily represent the official views of the RECOVER Initiative, the NIH, or other funders. The views, statements, and opinions presented in this publication are solely the responsibility of the author(s) and do not necessarily represent the views of other organizations participating in, collaborating with, or funding PCORnet or of the Patient-Centered Outcomes Research Institute (PCORI).


* Co-first authors.


# Membership of the RECOVER Consortium is provided in [Supplementary Appendix] (available in the online version only).


Supplementary Material



Publication History

Received: 26 January 2025

Accepted: 09 September 2025

Article published online:
24 October 2025

© 2025. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/)

Georg Thieme Verlag KG
Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany