Pipeline-optimized machine learning for chronic fatigue syndrome diagnosis: A lightweight, interpretable model using blood biochemical and metabolomic data.
Li, Junrong, Cao, Hanyu, Zhu, Zirun et al.·Computational biology and chemistry·2026
Researchers developed a computer program that uses blood tests to help diagnose ME/CFS more accurately and quickly. The program was trained on data from over 1,100 people with ME/CFS and nearly 67,000 control participants, and it correctly identified ME/CFS in about 94% of cases. This tool could help doctors catch the condition earlier and tailor treatment to individual patients.