Abstract: medRxiv preprint doi: https://doi.org/10.1101/2022.12.22.22283791; this version posted December 26, 2022. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-NC-ND 4.0 International license . A machine learning-based phenotype for long COVID in children: an EHR-based study from the RECOVER program Authors Vitaly Lorman, PhD1, Hanieh Razzaghi, MPH1, Xing Song, PhD2, Keith Morse, MD, MBA3, Levon Utidjian, MD1, Andrea J. Allen, MS1, Suchitra Rao, MBBS, MSCS4, Colin Rogerson, MD, MPH5, Tellen D. Bennett, MD, MS6, Hiroki Morizono, PhD7, Daniel Eckrich, MLIS8, Ravi Jhaveri, MD9, Yungui Huang, PhD, MBA10, Daksha Ranade, MPH, MBA11, Nathan Pajor, MD, MS12, Grace M. Lee, MD, MPH13, Christopher B. Forrest, MD, PhD1, L. Charles Bailey, MD, PhD1 Affiliations: 1 Applied Clinical Research Center, Children’s Hospital of Philadelphia, Philadelphia, PA, United States 2 Department of Health Management and Informatics, University of Missouri School of Medicine, Columbia, MO, United States 3 Division of Pediatric Hospital Medicine, Department of Pediatrics, Stanford University School of Medicine, Stanford, California, United States 4 Department of Pediatrics, University of Colorado School of Medicine and Children’s Hospital of Colorado, Aurora, CO, United States 5 Division of Critical Care, Department of Pediatrics, Indiana University School of Medicine, Indianapolis, IN, United States 6 Departments of Biomedical Informatics and Pediatrics, University of Colorado School of Medicine and Children’s Hospital Colorado, Aurora, CO, United States 7 Center for Genetic Medicine Research, Children's National Hospital, Washington DC, United States 8 Biomedical Research Informatics Center, Nemours Children’s Health, Wilmington, DE, United States 9 Division of Infectious Diseases, Ann & Robert H. Lurie Children’s Hospital of Chicago, Chicago, IL, United States 10 IT Research and Innovation, The Research Institute at Nationwide Children’s Hospital, Columbus, OH, United States 11 Research Informatics Department, Seattle Children’s Hospital, Seattle, WA, United States 12 Division of Pulmonary Medicine, Cincinnati Children’s Hospital Medical Center and University of Cincinnati College of Medicine, Cincinnati, OH, United States 13 Division of Infectious Diseases, Department of Pediatrics, Stanford University School of Medicine, Stanford, CA, United States NOTE: This preprint reports new research that has not been certified by peer review and should not be used to guide clinical practice. medRxiv preprint doi: https://doi.org/10.1101/2022.12.22.22283791; this version posted December 26, 2022. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-NC-ND 4.0 International license . Abstract Background As clinical understanding of pediatric Post-Acute Sequelae of SARS CoV-2 (PASC) develops, and hence the clinical definition evolves, it is desirable to have a method to reliably identify patients who are likely to have post-acute sequelae of SARS CoV-2 (PASC) in health systems data. Methods and Findings In this study, we developed and validated a machine learning algorithm to classify which patients have PASC (distinguishing between Multisystem..