Identifying commonalities and differences between EHR representations of PASC and ME/CFS in the RECOVER EHR cohort

Powers, JP; McIntee, TJ; Bhatia, A; et al., Communications Medicine, April 2025

View Publication on PubMed

April 2025
Communications Medicine

Short Summary

This RECOVER study looked at the similarities and differences between Long COVID and myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) in electronic health records (EHRs). Both illnesses can make people feel exhausted for long periods of time. Researchers studied the EHRs of 6.5 million adults and found some similarities between people who had diagnoses of either Long COVID or ME/CFS. Problems like trouble breathing, feeling very tired, and difficulty focusing were seen in the EHRs of both people with Long COVID diagnoses and those with ME/CFS diagnoses. But there were also some differences. People with a diagnosis of Long COVID were more likely to have problems with their heart and lungs in their EHRs. People with a diagnosis of ME/CFS were more likely to have pain, trouble sleeping, and problems with mood or thinking in their EHRs. Researchers looked at the symptoms listed in people’s EHRs, regardless of diagnosis. They found that about half the people with symptoms that looked like Long COVID also had symptoms that looked like ME/CFS. This research is important because Long COVID and ME/CFS can look similar. That means people with either illness may benefit from some of the same treatments.

This summary was prepared by the RECOVER Initiative.

Publication Details

DOI: 10.1038/s43856-025-00827-5

Abstract

Background: Shared symptoms and biological abnormalities between post-acute sequelae of SARS-CoV-2 infection (PASC) and myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) could suggest common pathophysiological bases and would support coordinated treatment efforts. Empirical studies comparing these syndromes are needed to better understand their commonalities and differences.

Methods: We analyzed electronic health record data from 6.5 million adult patients from the National COVID Cohort Collaborative. PASC and ME/CFS diagnostic groups were defined based on recorded diagnoses, and other recorded conditions within the two groups were used to train separate machine learning-driven computable phenotypes (CPs). The most predictive conditions for each CP were examined and compared, and the overlap of patients labeled by each CP was examined. Condition records from the diagnostic groups were also used to statistically derive condition clusters. Rates of subphenotypes based on these clusters were compared between PASC and ME/CFS groups.

Results: Approximately half of patients labeled by one CP are also labeled by the other. Dyspnea, fatigue, and cognitive impairment are the most-predictive conditions shared by both CPs, whereas other most-predictive conditions are specific to one CP. Recorded conditions separate into cardiopulmonary, neurological, and comorbidity clusters, with the cardiopulmonary cluster showing partial specificity for the PASC groups.

Conclusions: Data-driven approaches indicate substantial overlap in the condition records associated with PASC and ME/CFS diagnoses. Nevertheless, cardiopulmonary conditions are somewhat more commonly associated with PASC diagnosis, whereas other conditions, such as pain and sleep disturbances, are more associated with ME/CFS diagnosis. These findings suggest that symptom management approaches to these illnesses could overlap.

Authors

John P Powers, Tomas J McIntee, Abhishek Bhatia, Charisse R Madlock-Brown, Jaime Seltzer, Anisha Sekar, Nita Jain, Mady Hornig, Elle Seibert, Peter J Leese, Melissa Haendel, Richard Moffitt, Emily R Pfaff, N3C Consortium and RECOVER-EHR

Keywords

Not available