Neuroimaging has radically improved our understanding of how speech and language abilities map to the brain in normal and impaired participants, including the diverse, graded variations observed in post-stroke aphasia. MRC CBU’s Matt Lambon Ralph and Ajay Halai have been working alongside Anne Williams from University of Manchester, and have begun a handful of studies to explore the reverse inference: creating brain-to-behaviour prediction models.
In this study, the scientists explored the effect of three critical parameters on model performance: (1) brain partitions as predictive features, (2) combination of multimodal neuroimaging and (3) type of machine learning algorithms. They explored the influence of these factors while predicting four principal dimensions of language and cognition variation in post-stroke aphasia.
Across all four behavioural dimensions, they consistently found that prediction models derived from diffusion-weighted data did not improve performance over models using structural measures extracted from T1 scans. Results provide a set of principles to guide future work aiming to predict outcomes in neurological patients from brain imaging data.
You can read the full paper, published in Nature Human Behaviour now: https://www.nature.com/articles/s41562-020-0854-5