Generative lesion pattern decomposition of cognitive impairment after stroke. Issue 2 (22nd May 2021)

• Record Type: Journal Article
• Authors: Bonkhoff, Anna K; Lim, Jae-Sung; Bae, Hee-Joon; Weaver, Nick A; Kuijf, Hugo J; Biesbroek, J Matthijs; Rost, Natalia S; Bzdok, Danilo
• Is Part Of: Brain communications. Volume 3:Issue 2(2021)
• Publication Date: 2021-05-22
• Subjects: ischaemic stroke -- hemisphere-aware analysis -- clinical outcome prediction -- Bayesian hierarchical modelling -- machine learning; 616
• DOI: 10.1093/braincomms/fcab110
• Languages: English
• ISSNs: 2632-1297

Abstract

Abstract: Cognitive impairment is a frequent and disabling sequela of stroke. There is however incomplete understanding of how lesion topographies in the left and right cerebral hemisphere brain interact to cause distinct cognitive deficits. We integrated machine learning and Bayesian hierarchical modelling to enable a hemisphere-aware analysis of 1080 acute ischaemic stroke patients with deep profiling ∼3 months after stroke. We show the relevance of the left hemisphere in the prediction of language and memory assessments and relevance of the right hemisphere in the prediction of visuospatial functioning. Global cognitive impairments were equally well predicted by lesion topographies from both sides. Damage to the hippocampal and occipital regions on the left was particularly informative about lost naming and memory functions, while damage to these regions on the right was linked to lost visuospatial functioning. Global cognitive impairment was predominantly linked to lesioned tissue in the supramarginal and angular gyrus, the post-central gyrus as well as the lateral occipital and opercular cortices of the left hemisphere. Hence, our analysis strategy uncovered that lesion patterns with unique hemispheric distributions are characteristic of how cognitive capacity is lost due to ischaemic brain tissue damage. Abstract : Bonkhoff et al. integrate machine learning and Bayesian hierarchical modelling to enable hemisphere-aware analysis of 1080 stroke patients. They quantify lateralization effects of cortical and subcortical regions, such as the pallidum and hippocampus, of middle and posterior cerebral artery vascular territories to the left for naming/memory and to the right for visuospatial functions. Graphical Abstract: