Newly Identified Biomarkers Could Help Diagnose Chronic Fatigue Syndrome
More than 3 million people in the U.S. have chronic fatigue syndrome (CFS), a complex condition characterized by extreme, persistent fatigue. Neither sleep nor rest is shown to relieve their exhaustion, and among the many unknowns associated with CFS is how to accurately diagnose the condition.
Scientists at Cornell University hope to change that. Newly published research in the peer-reviewed journal Proceedings of the National Academy of Sciences describes a “concrete step” toward developing a diagnostic test.
Diagnosing Chronic Fatigue Syndrome
Currently, there is no diagnostic tool for CFS, also known as myalgic encephalomyelitis. Instead, doctors rely on a broad set of patient symptoms — such as exhaustion, dizziness, and brain fog — in tandem with a long and arduous effort to rule out other potential causes of these conditions.
That key is held in RNA, a critical component of human cells that carries instructions from DNA to other proteins in the body. When cells die, they leave behind a genetic record in RNA that is released into the bloodstream, revealing changes that occur over a lifetime. Several mechanisms contribute to the release of RNA from cells into the bloodstream, including normal cell death, physical stress, or cell-to-cell communication.
“Once outside of the cell, these circulating RNA molecules are referred to as cell-free RNA (cfRNA). These cfRNA molecules reflect the dynamics of gene expression in the crucial moment of cell turnover or signaling that led to their release, making them ideal biomarkers for studying complex diseases,” says Anne Gardella, study co-author and molecular biologist.
“By measuring the RNA in our cells at a given point in time, we understand which genes are actively being expressed in response to the current cellular environment,” Gardella adds.
Read More: What Do Your Blood Test Results Mean?
Machine Learning and cfRNA
Gardella’s team created machine-learning models capable of sifting through cfRNA to identify biomarkers, or molecular fingerprints, associated with CFS.
“ME/CFS affects a lot of different parts of the body,” said Maureen Hanson, director of the Cornell Center for Enervating NeuroImmune Disease, in a news release. “The nervous system, immune system, [and] cardiovascular system. Analyzing plasma gives you access to what’s going on in those different parts.”
Researchers collected blood samples from two groups participating in the study: those diagnosed with CFS and a healthy but sedentary group. Because people with CFS typically have limited levels of daily activity, comparing them with sedentary people allowed for the control of differences in physical activity.
“If we compared them to people with normal activity levels, the alterations in cfRNA could reflect differences in physical conditioning rather than true biological effects caused by the disease itself,” says Gardella.
Sampled blood was spun down using a centrifuge to separate and isolate its components. Then, the characteristics of RNA molecules were genetically sequenced to learn which genes in the body coded for cfRNA.
“Essentially, these computer algorithms ‘learn’ which genes best separate the groups and can then classify new samples based on their cfRNA expression profiles,” says Gardella.
Better Diagnostic Tools for the Future
Researchers collected more than 700 RNA transcripts from the two groups, all of which were machine-learning-parsed to develop a classifying tool capable of identifying signs of immune stress and other factors observed in CFS patients. RNA molecules were then mapped, showing there were six cell types unique to CFS patients.
“When there is a disproportionate signal from certain cell types, this suggests that there is underlying dysregulation of those cells in the disease,” says Gardella.
Although the test was 77 percent accurate in detecting CFS using these indicators, this rate is not high enough to be considered a reliable diagnostic tool.
However, it represents a significant advancement in the field of diagnosing chronic illnesses.
“For clinical use, a test would be most useful with an accuracy above 90 percent. However, given the complexity of ME/CFS and the relatively small sample size, this model is a promising start to a non-invasive test,” says Gardella, adding that her team hopes to collect more samples that further improve the performance of these models.
Additionally, the researchers hope to assess how cfRNA changes during different stages of CFS symptoms, like after strenuous exercise. Patients with CFS sometimes feel worse after physical exertion that would otherwise leave a healthy person unbothered.
“Ultimately, we hope this work not only contributes both to a reliable diagnostic tool and a deeper understanding of ME/CFS but also continues to bring understanding of the biological problems that result in the lived experiences of these patients,” says Gardella.
Read More: With No Known Cause Or Cure, Here’s What We Know About Chronic Fatigue Syndrome
Article Sources
Our writers at Discovermagazine.com use peer-reviewed studies and high-quality sources for our articles, and our editors review for scientific accuracy and editorial standards. Review the sources used below for this article: