Cell-Free RNA Test Could Detect Molecular Fingerprints of Chronic Fatigue Syndrome in Blood

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a debilitating condition with symptoms such as exhaustion, dizziness, disturbed sleep, and cognitive impairment. These symptoms often overlap with other illnesses, making an accurate diagnosis challenging. With no existing laboratory tests, doctors must rely on subjective symptom reports. Now, researchers have developed machine-learning models that can sift through cell-free RNA—fragments released into plasma during cell damage and death— to detect ME/CFS.

The machine-learning models developed by researchers at Cornell University (Ithaca, NY, USA) analyze cell-free RNA and identify key biomarkers for ME/CFS. The new approach, published in Proceedings of the National Academy of Sciences, builds on previous work that utilized the same technique to diagnose Kawasaki disease and multisystem inflammatory syndrome in children, providing insight into processes occurring across the nervous, immune, and cardiovascular systems.

Image: Machine-learning models can sift through cell-free RNA to identify key biomarkers for myalgic encephalomyelitis (Photo courtesy of Adobe Stock)

In the study, blood samples were collected from patients with ME/CFS and a control group of healthy, sedentary individuals. The plasma was processed to isolate and sequence RNA molecules, revealing over 700 transcripts that differed significantly between groups. These results were analyzed with multiple machine-learning algorithms, producing classifiers that flagged signs of immune dysregulation, extracellular matrix disorganization, and T cell exhaustion in patients.

Further statistical mapping traced the RNA molecules back to their cell-type origins, identifying six immune cell types with significant differences between cases and controls. The most elevated were plasmacytoid dendritic cells, linked to type 1 interferon production and prolonged antiviral immune responses. Other affected cells included monocytes, platelets, and T cell subsets, suggesting widespread immune dysfunction.

The classifier models achieved 77% accuracy in detecting ME/CFS—an important advance, though not yet sufficient for clinical diagnostics. Researchers see potential for refining the approach to distinguish ME/CFS from similar post-infection syndromes, including long COVID, while deepening understanding of the disease’s underlying biology. Work is ongoing to improve accuracy and explore its utility in other chronic conditions.

"By reading the molecular fingerprints that cells leave behind in blood, we’ve taken a concrete step toward a test for ME/CFS. This study shows that a tube of blood can provide clues about the disease’s biology," said Iwijn De Vlaminck, co-senior author of the study.