Long COVID or post-acute sequelae of COVID-19 (PASC) is a condition marked by the continuation of COVID-19 symptoms or the emergence of new ones after recovery from the initial phase of acute COVID-19 illness.
The National Institutes of Health (NIH)31 has launched the research initiative, Researching COVID to Enhance Recovery (RECOVER), to understand and prevent long COVID. RECOVER seeks to accurately identify people with long COVID or PASC and develop approaches for its prevention and treatment. This initiative will study critical research questions about the long-term effects of COVID through clinical trials, longitudinal observational studies, and more. Studies of electronic health records are a crucial element of the RECOVER initiative, which addresses the urgent need to understand long COVID and to accurately identify who has it as the aim of this study. The RECOVER program has invested in electronic health record studies to understand the risk factors for and mechanisms behind long COVID, accurately identify individuals with long COVID, and prevent and treat long COVID.
To understand the complexities of long COVID, recruiting a large and diverse cohort of research participants is necessary. The NIH aims to recruit thousands of participants in the USA to answer critical research questions about long COVID, such as understanding pregnancy risk factors, cognitive impairment and mental health, and outcome disparities and co-morbidities. Efficient recruitment of cohorts of this size and scope often entails leveraging computable phenotypes. For long COVID, as with other novel conditions, the absence of an unambiguous consensus definition and the heterogeneity of the condition's presentation poses a substantial challenge to cohort identification.
Machine learning can help to address this challenge by using the rich longitudinal data available in electronic health records to algorithmically identify patients similar to those in a long COVID "gold standard." Using machine learning, researchers find patterns in electronic health record data to identify better those likely to have the condition. A research team supported by the NIH has identified characteristics of people with long COVID and those likely to have it. Using machine learning techniques, scientists analyzed an unprecedented collection of electronic health records (EHRs) available for COVID-19 research to identify better who has long COVID. Exploring de-identified EHR data in the National COVID CohortC collaborative (N3C), a national, centralized public database led by the National Center for Advancing Translational Sciences (NCATS), is one of 27 Institutes and Centers at the NIH where the team used the data to identify more than 100,000 likely long COVID cases as of October 2021. Updated research as of May 2022 reveals that the count is now greater than 200,000 patients.32 On August 5, 2022, the Biden–Harris Administration released two new reports on Long COVID to support patients and further research. The U.S. Department of Health and Human Services (HHS) announced an estimate that 7.7 to 23 million Americans suffer from long COVID.33
31. U.S. Dept of Health and Human Service (HHS). (2022). National Institutes of Health (NIH), National Center for Translation Science: Scientists Identify Characteristics to Better Define Long COVID. https://ncats.nih.gov/news/releases/2022.32. Pfaff, E., Girvin, A., & Bennett, T. (2022). Identifying who has long COVID in the USA: a machine learning approach using N3C data. Lancet, 4(7).33. U.S. Department of Health and Human Service (HHS) Long Covid Estimate. (2022), https://www.hhs.gov/about/news/2022/08/03/biden-harris-administration-releases-two-new-reports-long-covid-support-patients-further-research.html.
