Chen, Yunhua, Liu, Weijian, Zhang, Ling et al. · Computers in biology and medicine · 2015 · DOI
Researchers developed a computer program that analyzes facial features—such as forehead wrinkles, under-eye puffiness, skin color, and mouth shape—to help diagnose ME/CFS. The program was trained using photographs of Chinese patients and achieved about 88% accuracy in identifying who had the condition. This approach could potentially help doctors diagnose ME/CFS more objectively without needing blood tests or other invasive procedures.
ME/CFS currently lacks objective biomarkers, making diagnosis challenging and often delayed. If validated across diverse populations, a non-invasive facial analysis tool could reduce diagnostic barriers, standardize assessment, and accelerate patient diagnosis. This represents an innovative approach to addressing the critical need for objective diagnostic aids in ME/CFS.
This study does not prove that facial features cause ME/CFS or that they are pathognomonic for the condition. The method was tested only in a Chinese population and has not been validated in other ethnic groups or compared to established diagnostic criteria. High accuracy in a development cohort does not guarantee real-world clinical utility or generalizability.
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 →
The first block is for the primary paper and is the citation you should use in research work. The atlas-snapshot line only applies if you are specifically referring to this atlas’s reading of the paper on the date shown.
Primary citation
Chen, Yunhua, Liu, Weijian, Zhang, Ling, Yan, Mingyu, & Zeng, Yanjun (2015). Hybrid facial image feature extraction and recognition for non-invasive chronic fatigue syndrome diagnosis.. Computers in biology and medicine. https://doi.org/10.1016/j.compbiomed.2015.06.005
BibTeX
@article{mecfsatlas-chen-2015-hybrid-facial,
author = {Chen, Yunhua and Liu, Weijian and Zhang, Ling and Yan, Mingyu and Zeng, Yanjun},
title = {Hybrid facial image feature extraction and recognition for non-invasive chronic fatigue syndrome diagnosis.},
journal = {Computers in biology and medicine},
year = {2015},
doi = {10.1016/j.compbiomed.2015.06.005},
note = {PubMed: 26117650},
url = {https://www.mecfsatlas.com/evidence/chen-2015-hybrid-facial},
}Atlas snapshot reference
ME/CFS Atlas. Generator v1 / Scanner v1.4 / policy v0.1. Accessed 2026-05-29. https://www.mecfsatlas.com/evidence/chen-2015-hybrid-facial
Contribute
Private, reviewed by a human. Not a public comment thread.