AI-driven multi-omics modeling of Myalgic Encephalomyelitis / Chronic Fatigue Syndrome, 2025, Xiong et al.

Referencing Fig. 2C, where scores are 1-mean squared error. It just stuck out to me because I’ve previously been part of analyses that tried to predict individual domain scores, on a much bigger cohort, using various supervised models, and only ever came close to those MSEs for maybe one score
Interesting thanks.

I wonder if they split the control group in group A and group B and do the same analysis on these groups (rather than ME/CFS versus healthy controls), how high the predictive power and AUC would be.
 
Archived at https://archive.is/wKiWu

Alan Carson said:
The paper is the latest in a series to find abnormal physical factors relating to ME but a “consistent pattern” of these has yet to emerge, warns Alan Carson, professor of neuropsychiatry at the University of Edinburgh. This raised questions about whether all the patients surveyed in the various studies had ME as opposed to “lookalike conditions”, he added.

“At best, these [studies] are small incremental steps that are not replicating,” said Carson, who has done research into long Covid. “We remain a long way off understanding the biology of ME.”
 
Back
Top Bottom