Huang, Katherine, Lidbury, Brett A, Thomas, Natalie et al. · Journal of translational medicine · 2025 · DOI
This review examines how advanced computer analysis and detailed biological testing could help doctors better understand and treat ME/CFS. Because ME/CFS affects people differently, researchers are exploring ways to look at each patient's unique genetic and molecular makeup to find personalized treatments. The study discusses how combining multiple types of biological data—genes, proteins, and metabolites—along with artificial intelligence could help identify specific patterns that distinguish ME/CFS patients and guide their care.
ME/CFS currently lacks reliable biomarkers and diagnostic tests, leading to delayed diagnosis and ineffective treatments. This review provides a roadmap for how emerging technologies could transform ME/CFS research by identifying patient subgroups and personalized treatment approaches. For patients, this work offers hope that precision medicine could eventually lead to better diagnosis, prognosis, and targeted therapies tailored to individual biological profiles.
This is a review article, not a primary research study, so it does not present new experimental data or clinical outcomes. It does not prove that machine learning approaches will definitively improve ME/CFS diagnosis or treatment in clinical practice—rather, it advocates for their future development. The review does not establish which specific biomarkers are causally responsible for ME/CFS symptoms, only that such biomarkers may exist and be discoverable through these methodologies.
About the PEM badge: “PEM required” means post-exertional malaise was an explicit required diagnostic criterion for participant inclusion in this study — not that PEM was studied, observed, or discussed. Studies using criteria that do not require PEM (e.g. Fukuda, Oxford) are tagged “PEM not required”. How the atlas works →
Contribute
Private, reviewed by a human. Not a public comment thread.