Predicting language outcomes after stroke: Is structural disconnection a useful predictor?

Abstract

For many years, researchers have sought to understand whether and when stroke survivors with acquired language impairment (aphasia) will recover. There is broad agreement that lesion location information should play some role in these predictions, but still no consensus on the best or right way to encode that information. Here, we address the emerging emphasis on the structural connectome in this work - specifically the claim that disrupted white matter connectivity conveys important, unique prognostic information for stroke survivors with aphasia. Our sample included 818 stroke patients extracted from the PLORAS database, which associates structural MRI from stroke patients with language assessment scores from the Comprehensive Aphasia Test (CAT) and basic demographic. Patients were excluded when their lesions were too diffuse or small (<1 cm3) to be detected by the Automatic Lesion Identification toolbox, which we used to encode patients' lesions as binary lesion images in standard space. Lesions were encoded using the 116 regions defined by the Automatic Anatomical Labelling atlas. We examined prognostic models driven by both "lesion load" in these regions (i.e. the proportion of each region destroyed by each patient's lesion), and by the disconnection of the white matter connections between them which was calculated via the Network Modification toolbox. Using these data, we build a series of prognostic models to predict first one ("naming"), and then all of the language scores defined by the CAT. We found no consistent evidence that connectivity disruption data in these models improved our ability to predict any language score. This may be because the connectivity disruption variables are strongly correlated with the lesion load variables: correlations which we measure both between pairs of variables in their original form, and between principal components of both datasets. Our conclusion is that, while both types of structural brain data do convey useful, prognostic information in this domain, they also appear to convey largely the same variance. We conclude that connectivity disruption variables do not help us to predict patients' language skills more accurately than lesion location (load) data alone.

Keywords: Aphasia; Connectomics; Language; MRI; Outcomes; Stroke; White matter.

Fig. 1

Lesion frequency. Axial slices of a lesion frequency image for 818 patients.

Fig. 2

Predictive performance on naming scores. Model predictive performance is shown for: (a) linear support vector machines (light grey bars); (b) Gaussian processes with a rational quadratic kernel (mid-grey bars); and (c) the best of 16 inducers tried (dark grey bars). Models were trained on each of 7 data configurations: (i) lesion load only, L; (ii) restricted connectivity disruption, C(r); (iii) full connectivity disruption, C(f); (iv) lesion load plus restricted connectivity, LC(r); (v) lesion load plus full connectivity, LC(f); (vi) lesion load stacked with restricted connectivity, LsC(r); and, (vii) lesion load stacked with full connectivity, LsC(f). When produced using a linear support vector machine, there was a marginally significant benefit for the stacked model using lesion load and restricted connectivity (p = 0.04), and non-significant trend for the model which simply replaced lesion load with restricted connectivity (p = 0.07). No significant benefits were observed when predictions were made using either GPMR (all p > 0.1) or the best of 16 inducers (all p > 0.2). Numbers in each bar are prediction error distribution variances: all of the model comparisons are comparisons of these variances.

Fig. 3

Scatter plot of the first principal component of the lesion load data versus the first principal component of the connectivity disruption data.