Finding Long-COVID: Temporal topic modeling of electronic health records from the N3C and RECOVER programs
O'Neil, ST; Madlock-Brown, C; Wilkins, KJ; et al., NPJ Digital Medicine
Published
October 2024
Journal
NPJ Digital Medicine
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.
Authors
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; N3C and RECOVER Consortia
Keywords
Not available
Short Summary
In this RECOVER study, researchers wanted to find out which health conditions were common in people with long-term effects of COVID-19, known as Long COVID. They looked at the medical records of over 14 million patients who had and did not have COVID using a method called topic modeling. Topic modeling is a method to find patterns in groups of documents. Researchers used topic modeling to look at lists of health problems that millions of patients faced over time, including before and after they had COVID. This allowed them to find the conditions that were more common in people with Long COVID. Researchers found that health problems related to the lungs, heart, brain, and immune system were more common in people with Long COVID compared to those who didn’t have Long COVID or had not had COVID. Common problems included chronic fatigue (feeling tired all the time), headaches, anxiety, and heart issues. They also found that some problems were more common in people of a certain age or sex (whether they are male or female). The study shows that Long COVID can affect many parts of the body and highlights how health problems can differ between groups. It also shows that age and sex can affect the chance of getting certain health conditions after COVID.