Finding Long-COVID: Temporal Topic Modeling of Electronic Health Records from the N3C and RECOVER Programs

Shawn T O'Neil; Charisse Madlock-Brown; Kenneth J Wilkins; Brenda M McGrath; Hannah E Davis; Gina S Assaf; Hannah Wei; Parya Zareie; Evan T French; Johanna Loomba; Julie A McMurry; Andrea Zhou; Christopher G Chute; Richard A Moffitt; Emily R Pfaff; Yun Jae Yoo; Peter Leese; Robert F Chew; Michael Lieberman; Melissa A Haendel

doi:10.1101/2023.09.11.23295259

Back

Finding Long-COVID: Temporal Topic Modeling of Electronic Health Records from the N3C and RECOVER Programs

Preprint

Open access

Finding Long-COVID: Temporal Topic Modeling of Electronic Health Records from the N3C and RECOVER Programs

Shawn T O'Neil, Charisse Madlock-Brown, Kenneth J Wilkins, Brenda M McGrath, Hannah E Davis, Gina S Assaf, Hannah Wei, Parya Zareie, Evan T French, Johanna Loomba, …

medRxiv : the preprint server for health sciences

Cold Spring Harbor Laboratory

06/11/2024

DOI: 10.1101/2023.09.11.23295259

PMCID: PMC11213052

PMID: 38947087

Files and links (1)

url

https://doi.org/10.1101/2023.09.11.23295259 View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

Post-Acute Sequelae of SARS-CoV-2 infection (PASC), also known as Long-COVID, encompasses a variety of complex and varied outcomes following COVID-19 infection that are still poorly understood. We clustered over 600 million condition diagnoses from 14 million patients available through the National COVID Cohort Collaborative (N3C), generating hundreds of highly detailed clinical phenotypes. Assessing patient clinical trajectories using these clusters allowed us to identify individual conditions and phenotypes strongly increased after acute infection. We found many conditions increased in COVID-19 patients compared to controls, and using a novel method to associate patients with clusters over time, we additionally found phenotypes specific to patient sex, age, wave of infection, and PASC diagnosis status. While many of these results reflect known PASC symptoms, the resolution provided by this unprecedented data scale suggests avenues for improved diagnostics and mechanistic understanding of this multifaceted disease.

Details

Title: Subtitle: Finding Long-COVID: Temporal Topic Modeling of Electronic Health Records from the N3C and RECOVER Programs
Creators: Shawn T O'Neil - University of Colorado Anschutz Medical Campus
Charisse Madlock-Brown - University of Tennessee Health Science Center
Kenneth J Wilkins - National Institute of Diabetes and Digestive and Kidney Diseases
Brenda M McGrath - Ochin
Hannah E Davis - Patient-Led Research Collaborative
Gina S Assaf - Patient-Led Research Collaborative
Hannah Wei - Patient-Led Research Collaborative
Parya Zareie - University of California, Davis
Evan T French - Virginia Commonwealth University
Johanna Loomba - University of Virginia
Julie A McMurry - University of Colorado Anschutz Medical Campus
Andrea Zhou - University of Virginia
Christopher G Chute
Richard A Moffitt - Emory University
Emily R Pfaff - University of North Carolina School of Medicine
Yun Jae Yoo - Emory University
Peter Leese - University of North Carolina School of Medicine
Robert F Chew - RTI International
Michael Lieberman - University of Portland
Melissa A Haendel - University of Colorado Anschutz Medical Campus
Resource Type: Preprint
Publication Details: medRxiv : the preprint server for health sciences
DOI: 10.1101/2023.09.11.23295259
PMID: 38947087
PMCID: PMC11213052
Publisher: Cold Spring Harbor Laboratory; United States
Grant note: UL1 TR002243 / NCATS NIH HHS U54 GM115677 / NIGMS NIH HHS UL1 TR001453 / NCATS NIH HHS UL1 TR003142 / NCATS NIH HHS UL1 TR003107 / NCATS NIH HHS UL1 TR002535 / NCATS NIH HHS UL1 TR001881 / NCATS NIH HHS UL1 TR001857 / NCATS NIH HHS UL1 TR001450 / NCATS NIH HHS UL1 TR002538 / NCATS NIH HHS
Language: English
Date posted: 06/11/2024
Academic Unit: Nursing
Record Identifier: 9984721250502771

Metrics

2 Record Views