Machine learning identifies long COVID patterns from electronic health records
Unknown authors
Abstract
A machine learning algorithm identifies four reproducible clinical subphenotypes of long COVID from the electronic health records of patients with post-acute sequelae of SARS-CoV-2 infection within 30–180 days of infection; these patterns have implications for the treatment and management of long COVID.
Topics & Concepts
Coronavirus disease 2019 (COVID-19)Health records2019-20 coronavirus outbreakSevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2)VirologyBetacoronavirusMedicineData scienceComputer scienceInfectious disease (medical specialty)OutbreakPolitical scienceHealth carePathologyDiseaseLawLong-Term Effects of COVID-19Machine Learning in HealthcareHeart Rate Variability and Autonomic Control