Stroke can lead to debilitating consequences, including loss of language. An important goal of stroke research is to use machine learning to predict outcomes and response to therapy. A new study compares different approaches to predicting post-stroke outcomes and highlights the need for systematic optimization and validation to ultimately translate scientific insights to clinical settings.
This is a preview of subscription content, log in via an institution to check access.
References
Engelter, S. T. et al. Stroke 37, 1379–1384 (2006).
Hilari, K. Disabil. Rehabil. 33, 211–218 (2011).
Breitenstein, C. et al. Lancet 389, 1528–1538 (2017).
Halai, A. D. Nat. Hum. Behav. https://doi.org/10.1038/s41562-020-0854-5 (2020).
Hope, T. M. H., Seghier, M. L., Leff, A. P. & Price, C. J. Neuroimage Clin 2, 424–433 (2013).
Yourganov, G., Smith, K. G., Fridriksson, J. & Rorden, C. Cortex 73, 203–215 (2015).
Plowman, E., Hentz, B. & Ellis, C. Jr. J. Eval. Clin. Pract 18, 689–694 (2012).
Halai, A. D., Woollams, A. M. & Lambon Ralph, M. A. Cortex 86, 275–289 (2017).
Halai, A. D., Woollams, A. M. & Lambon Ralph, M. A. Neuroimage Clin 19, 1–13 (2018).
Seghier, M. L. et al. Neuroimage 124 Pt B, 1208–1212 (2016).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Rights and permissions
About this article
Cite this article
Rosenberg, M.D., Song, H. Predicting post-stroke aphasia from brain imaging. Nat Hum Behav 4, 675–676 (2020). https://doi.org/10.1038/s41562-020-0902-1
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41562-020-0902-1
- Springer Nature Limited