[amelius]

> Hahn said the difference between the original accuracy rate and that of the new study can likely be attributed to several factors, the most important being that two of the metabolites were unavailable in the second dataset. Each of the two metabolites had been strong indicators in the previous study.

Another issue could be overfitting.

[BadCookie]

It sounds like they were using leave-one-out cross validation. My machine learning is a bit rusty, but I don't think that overfitting is the issue.