Using Machine Learning to Investigate Long COVID

April 29, 2022

Many COVID-19 patients are experiencing lingering symptoms long after their initial infection has passed. Studying long COVID, as it is called, is complicated by the wide range of symptoms and lack of consensus of what constitutes the disorder. To address this issue, the National Institutes of Health (NIH) launched the National Covid Cohort Collective (N3C), a centralized database representing over 13 million patients. Researchers at the University of Colorado and other institutions are leveraging machine learning (ML) to understand the complexities of long COVID.

According to Katie Palmer of STAT, “The model performed decently when tested on records from a fourth clinic, differentiating between long Covid clinic patients and non-patients with a 0.82 area under the curve, a measure of accuracy used by machine learning researchers. But it was still based on a small number of patients that could be demographically skewed.“

To learn more, click here.