Prediction of Long-Term Outcome after Stroke Using Clinically Available Acute Brain Imaging

Predicting stroke outcome early in the course of disease is of major interest to guide therapies and remove the burden of uncertainty.

Aims

We aim to define a multimodal algorithm that predicts the longer-term outcome after stroke from data that is readily available in the acute phase of stroke.

It has been shown that multimodal models, including imaging data, have better predictive validity than single modal models. Yet none of the proposed models have been adopted in clinical practice.

We will investigate the predictive value of clinically available acute neuroimaging data and patient characteristics with decision-trees. By analysing data from the ongoing AVERT trial (n=2,104) we have access to a well-characterised population with standardised follow-ups at 3 and 12 months after stroke.

Design: Retrospective data-analysis

Current status: Analysis ongoing

Site/s:. The Florey Institute of Neuroscience and Mental Health

Key references:

AVERT Trial Collaboration group, Bernhardt J, Langhorne P, Lindley RI, Thrift AG, Ellery F, Collier J, Churilov L, Moodie M, Dewey H, Donnan G., Efficacy and safety of very early mobilisation within 24 h of stroke onset (AVERT): a randomised controlled trial. Lancet. 2015. 386(9988): 46-55.

Yassi N, Churilov L, Campbell BC, Sharma G, Bammer R, Desmond PM, Parsons MW, Albers GW, Donnan GA, Davis SM; EPITHET, and DEFUSE Investigators. The association between lesion location and functional outcome after ischemic stroke. Int J Stroke. 2015. doi: 10.1111/ijs.12537.

Burke, E. and S.C. Cramer, Biomarkers and predictors of restorative therapy effects after stroke. Curr Neurol Neurosci Rep, 2013. 13(2): p. 329.

Macciocchi, S.N., et al., Ischemic stroke: relation of age, lesion location, and initial neurologic deficit to functional outcome. Arch Phys Med Rehabil, 1998. 79(10): p. 1255-7.