New paper out now in Science Advances:
“Generalizable and replicable brain-based predictions of cognitive functioning across common psychiatric illness”
By Sidhant Chopra and Holmes Lab
Read it here: https://www.science.org/doi/10.1126/sciadv.adn1862
This paper demonstrates using ‘meta-matching’ technique to build reliable, generalizable and interpretable models of cognitive functioning without 1000s of subjects/patients.
The key takeaway is You don’t need your own big data to make robust & generalizable brain-based behavioural predictions, especially for cognition. Methods like meta-matching (https://nature.com/articles/s41593-022-01059-9) are effective across diverse small clinical samples.