Artificial grammar learning in vascular and progressive non-fluent aphasias

Abstract

Patients with non-fluent aphasias display impairments of expressive and receptive grammar. This has been attributed to deficits in processing configurational and hierarchical sequencing relationships. This hypothesis had not been formally tested. It was also controversial whether impairments are specific to language, or reflect domain general deficits in processing structured auditory sequences. Here we used an artificial grammar learning paradigm to compare the abilities of controls to participants with agrammatic aphasia of two different aetiologies: stroke and frontotemporal dementia. Ten patients with non-fluent variant primary progressive aphasia (nfvPPA), 12 with non-fluent aphasia due to stroke, and 11 controls implicitly learned a novel mixed-complexity artificial grammar designed to assess processing of increasingly complex sequencing relationships. We compared response profiles for otherwise identical sequences of speech tokens (nonsense words) and tone sweeps. In all three groups the ability to detect grammatical violations varied with sequence complexity, with performance improving over time and being better for adjacent than non-adjacent relationships. Patients performed less well than controls overall, and this was related more strongly to aphasia severity than to aetiology. All groups improved with practice and performed well at a control task of detecting oddball nonwords. Crucially, group differences did not interact with sequence complexity, demonstrating that aphasic patients were not disproportionately impaired on complex structures. Hierarchical cluster analysis revealed that response patterns were very similar across all three groups, but very different between the nonsense word and tone tasks, despite identical artificial grammar structures. Overall, we demonstrate that agrammatic aphasics of two different aetiologies are not disproportionately impaired on complex sequencing relationships, and that the learning of phonological and non-linguistic sequences occurs independently. The similarity of profiles of discriminatory abilities and rule learning across groups suggests that insights from previous studies of implicit sequence learning in vascular aphasia are likely to prove applicable in nfvPPA.

Keywords: Aphasia; Frontotemporal dementia; Grammar; Implicit learning; Stroke.

Graphical abstract

Fig. 1

A) Boston Diagnostic Aphasia Examination Profiles for nfvPPA and stroke groups. Normal values illustrated as broken black line. Colour coding of individual profiles based on Aphasia Severity Rating Scale; 1 = red, 2 = magenta, 3 = yellow, 4= blue. No patients had an ASRS of 0 (no usable speech or auditory comprehension) or 5 (minimal discernible handicap). B) Upper: Voxel based morphometry of nfvPPA vs age-matched healthy controls. Coloured regions demonstrate cluster-wise significance at FWE<0.05 with a cluster defining threshold of 0.001 for either grey or white matter volume. Lower: lesion overlap map for the stroke group. (For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.)

Fig. 2

A: Artificial grammar structure and stimuli. B: Cartoon illustrating the distribution of parametric decision variables for an hypothetical experiment with easy, medium and hard to detect rule violations. d′ represents the single subject discriminability of each rule violation, while c and β represent different measures of bias (i.e. in our case the tendency to say that a sequence is grammatical if there is no evidence to the contrary). Each rule violation has its own d′ measure, reflecting its respective discrimination difficulty, while the bias measures apply to the experimental context as a whole.

Fig. 3

Group performance on sequence identification. Dashed lines represent chance performance. Error bars represent group-wise standard error of the mean. Controls are in blue, nfvPPA in red and stroke in orange. A) Proportion of correct responses for each testing sequence by group and task. Sequences 1–3 were consistent with the grammar and familiar from the exposure phase, while 4–6 were consistent and novel. Sequences 7–12 contained violations of the types indicated (see Table 2). B) Discriminability of each rule type by group for each language type. C) Overall discriminability by group and run number for the CVC language (improving performance by run represents learning over time). D) Overall discriminability by group and run number for the tone language. (For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.)

Fig. 4

A) Spearman rank-order correlation matrices. B) Linkage based on hierarchical cluster analysis of Spearman correlations. Three clusters emerge with a linkage distance cutoff of 0.5, and are indicated in colour groupings (blue, green and red). (For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.)

Fig. S1

A plot for nfvPPA of difficulty ‘Understanding speech in a quiet room’ against ‘Grammatical form’ from the BDAE. Individual patients are shown as blue circles. A boxplot of control ratings is shown in red. The dashed trend line had an r² of 0.778 (p<0.001).

Fig. S2

Composite pure tone audiograms for each group. Red circles joined by lines denote the median auditory threshold in the right ear; blue crosses joined by lines the median auditory threshold in the left ear. Shaded areas represent the inter-quartile range of auditory acuity in the right (red) and left (blue) ears.

Fig. S3

Bias metrics by group for each language type (values less than zero indicate a bias towards classifying sequences as correct).