Researchers at Cornell University have developed a sophisticated machine-learning model capable of analyzing cell-free RNA (cfRNA) in blood plasma to identify key biomarkers for myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS). This innovative approach, detailed in a study published on August 11, 2025, in the Proceedings of the National Academy of Sciences, offers a significant advancement in the pursuit of diagnostic tools for ME/CFS, a complex illness often challenging to diagnose due to symptom overlap with other conditions.
The study, led by doctoral student Anne Gardella, focused on analyzing RNA molecules released during cellular damage and death. The Cornell team identified over 700 significantly different RNA transcripts between ME/CFS patients and a control group. Machine-learning algorithms processed these findings, successfully pinpointing indicators of immune system dysregulation, extracellular matrix disorganization, and T cell exhaustion in ME/CFS patients. The model demonstrated 77% accuracy in detecting ME/CFS, a notable improvement that, while not yet sufficient for a definitive diagnostic test, represents a substantial step forward. The research received support from the National Institutes of Health and the WE&ME Foundation.