About 1 in 6 patients with COVID-19 has developed long COVID and nearly 9 in 10 of those cases involve chronic conditions requiring ongoing clinical management, according to a study published May 27 in JAMA Network Open.
A team led by researchers at Boston-based Massachusetts General Hospital conducted the study. The team applied a custom AI algorithm to EHR data from 457,950 patients treated across 58 U.S. hospitals between 2017 and 2025. The tool mined longitudinal records for symptom patterns emerging at least three months after a COVID-19 infection.
Four key findings:
1. The prevalence of long COVID was more than twice as high as standard diagnostic coding captures. The algorithm identified long COVID in 16.28% of patients, while standard diagnostic code-based surveillance captured fewer than 7% of cases.
2. Of the 74,560 long COVID patients identified, 89.31% developed at least one chronic condition. Cumulative prevalence continued rising through mid-2024, leading researchers to characterize the burden as accumulating rather than resolving.
3. The study also found significant variation in organ system involvement across regions, with New England showing thyroid-predominant patterns and three other regions showing metabolic-predominant profiles — a finding researchers say may point to distinct biological endotypes requiring precision medicine approaches.
4. Researchers estimated roughly 15 million Americans are living with chronic post-COVID conditions that current surveillance systems cannot see. They derived the figure by applying the study’s 14.54% chronic long COVID rate to about 103 million documented U.S. COVID-19 cases, though the authors cautioned the estimate excludes patients with limited EHR documentation and those with preexisting conditions unlikely to represent true long COVID.
See the full study here.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.
