TY - UNPB
T1 - Pediatric Long COVID Subphenotypes
T2 - An EHR-based study from the RECOVER program
AU - Lorman, Vitaly
AU - Bailey, L Charles
AU - Song, Xing
AU - Rao, Suchitra
AU - Hornig, Mady
AU - Utidjian, Levon
AU - Razzaghi, Hanieh
AU - Mejias, Asuncion
AU - Leikauf, John Erik
AU - Brill, Seuli Bose
AU - Allen, Andrea
AU - Bunnell, H Timothy
AU - Reedy, Cara
AU - Mosa, Abu Saleh Mohammad
AU - Horne, Benjamin D
AU - Geary, Carol Reynolds
AU - Chuang, Cynthia H
AU - Williams, David A
AU - Christakis, Dimitri A
AU - Chrischilles, Elizabeth A
AU - Mendonca, Eneida A
AU - Cowell, Lindsay G
AU - McCorkell, Lisa
AU - Liu, Mei
AU - Cummins, Mollie R
AU - Jhaveri, Ravi
AU - Blecker, Saul
AU - Forrest, Christopher B
PY - 2024/9/18
Y1 - 2024/9/18
N2 - 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.
AB - 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.
U2 - 10.1101/2024.09.17.24313742
DO - 10.1101/2024.09.17.24313742
M3 - Preprint
C2 - 39371163
T3 - medRxiv : the preprint server for health sciences
BT - Pediatric Long COVID Subphenotypes
ER -