Computer-assisted analysis of spontaneous speech: quantification of basic parameters in aphasic and unimpaired language

Language analysis of spontaneous descriptions of restless legs syndrome: Gender differences?

Patients with restless legs syndrome (RLS) use various terms when describing their symptoms. Whether gender might influence this has not been investigated so far. The aim of this study was to evaluate possible gender differences in spontaneous descriptions of RLS symptoms. This prospective study, conducted in 100 consecutive German‐speaking RLS patients, used a single standardized question. Answers were digitally recorded and transcribed. A content‐related linguistic analysis of the transcripts was performed by two independent blinded raters. The lengths of the answers and content‐related linguistic features were compared between women and men. Ninety‐eight patients were included in the final analysis, 59 women (60.2%) and 39 men (39.8%), with a median age of 62 (23–94) and 63 (31–82) years, respectively (p = 0.602). Demographic and clinical features, including educational level and RLS treatment class, did not differ between genders (p > 0.05). Total word or sentence count showed no gender differences (p = 0.159 and 0.259, respectively), although men used more words per sentence than women (p = 0.018). More men than women described quiescegenic (i.e., triggered by rest or inactivity) symptoms (p = 0.006) and successful attempts at relief (p = 0.039). There was a non‐significant trend toward a more frequent use of the first‐person perspective in men (median times used = 5 [0–10.5] vs. 3.8 [0–17.5], p = 0.068). The more frequent mention of quiescegenic symptoms and successful attempts at relief in men could indicate differences in phenotypic presentation of RLS between genders, a more precise description of RLS symptoms or a higher experience of self‐efficacy in men compared to women.

Thalamic but Not Subthalamic Neuromodulation Simplifies Word Use in Spontaneous Language

Several investigations have shown language impairments following electrode implantation surgery for Deep Brain Stimulation (DBS) in movement disorders. The impact of the actual stimulation, however, differs between DBS targets with further deterioration in formal language tests induced by thalamic DBS in contrast to subtle improvement observed in subthalamic DBS. Here, we studied speech samples from interviews with participants treated with DBS of the thalamic ventral intermediate nucleus (VIM) for essential tremor (ET), or the subthalamic nucleus (STN) for Parkinson’s disease (PD), and healthy volunteers (each n = 13). We analyzed word frequency and the use of open and closed class words. Active DBS increased word frequency in case of VIM, but not STN stimulation. Further, relative to controls, both DBS groups produced fewer open class words. Whereas VIM DBS further decreased the proportion of open class words, it was increased by STN DBS. Thus, VIM DBS favors the use of relatively common words in spontaneous language, compatible with the idea of lexical simplification under thalamic stimulation. The absence or even partial reversal of these effects in patients receiving STN DBS is of interest with respect to biolinguistic concepts suggesting dichotomous thalamic vs. basal ganglia roles in language processing.

Impact of deep brain stimulation of the subthalamic nucleus on natural language in patients with Parkinson's disease

Background

In addition to the typical motor symptoms, a majority of patients suffering from Parkinson’s disease experience language impairments. Deep Brain Stimulation of the subthalamic nucleus robustly reduces motor dysfunction, but its impact on language skills remains ambiguous.

Method

To elucidate the impact of subthalamic deep brain stimulation on natural language production, we systematically analyzed language samples from fourteen individuals (three female / eleven male, average age 66.43 ± 7.53 years) with Parkinson’s disease in the active (ON) versus inactive (OFF) stimulation condition. Significant ON-OFF differences were considered as stimulation effects. To localize their neuroanatomical origin within the subthalamic nucleus, they were correlated with the volume of tissue activated by therapeutic stimulation.

Results

Word and clause production speed increased significantly under active stimulation. These enhancements correlated with the volume of tissue activated within the associative part of the subthalamic nucleus, but not with that within the dorsolateral motor part, which again correlated with motor improvement. Language error rates were lower in the ON vs. OFF condition, but did not correlate with electrode localization. No significant changes in further semantic or syntactic language features were detected in the current study.

Conclusion

The findings point towards a facilitation of executive language functions occurring rather independently from motor improvement. Given the presumed origin of this stimulation effect within the associative part of the subthalamic nucleus, this could be due to co-stimulation of the prefrontal-subthalamic circuit.

Quantifying the Uncertainty of Parameters Measured in Spontaneous Speech of Speakers With Dementia

Purpose Corpus analyses of spontaneous language fragments of varying length provide useful insights in the language change caused by brain damage, such as caused by some forms of dementia. Sample size is an important experimental parameter to consider when designing spontaneous language analyses studies. Sample length influences the confidence levels of analyses. Machine learning approaches often favor to use as much language as available, whereas language evaluation in a clinical setting is often based on truncated samples to minimize annotation labor and to limit any discomfort for participants. This article investigates, using Bayesian estimation of machine learned models, what the ideal text length should be to minimize model uncertainty. Method We use the Stanford parser to extract linguistic variables and train a statistic model to distinguish samples by speakers with no brain damage from samples by speakers with probable Alzheimer's disease. We compare the results to previously published models that used CLAN for linguistic analysis. Results The uncertainty around six individual variables and its relation to sample length are reported. The same model with linguistic variables that is used in all three experiments can predict group membership better than a model without them. One variable (concept density) is more informative when measured using the Stanford tools than when measured using CLAN. Conclusion For our corpus of German speech, the optimal sample length is found to be around 700 words long. Longer samples do not provide more information.

Effects of thalamic deep brain stimulation on spontaneous language production

The thalamus is thought to contribute to language-related processing, but specifications of this notion remain vague. An assessment of potential effects of thalamic deep brain stimulation (DBS) on spontaneous language may help to delineate respective functions. For this purpose, we analyzed spontaneous language samples from thirteen (six female / seven male) patients with essential tremor treated with DBS of the thalamic ventral intermediate nucleus (VIM) in their respective ON vs. OFF conditions. Samples were obtained from semi-structured interviews and examined on multidimensional linguistic levels. In the VIM-DBS ON condition, participants used a significantly higher proportion of paratactic as opposed to hypotactic sentence structures. This increase correlated negatively with the change in the more global cognitive score, which in itself did not change significantly. In conclusion, VIM-DBS appears to induce the use of a simplified syntactic structure. The findings are discussed in relation to concepts of thalamic roles in language-related cognitive behavior.

The neural correlates of agrammatism: Evidence from aphasic and healthy speakers performing an overt picture description task

Functional brain imaging studies have improved our knowledge of the neural localization of language functions and the functional reorganization after a lesion. However, the neural correlates of agrammatic symptoms in aphasia remain largely unknown. The present fMRI study examined the neural correlates of morpho-syntactic encoding and agrammatic errors in continuous language production by combining three approaches. First, the neural mechanisms underlying natural morpho-syntactic processing in a picture description task were analyzed in 15 healthy speakers. Second, agrammatic-like speech behavior was induced in the same group of healthy speakers to study the underlying functional processes by limiting the utterance length. In a third approach, five agrammatic participants performed the picture description task to gain insights in the neural correlates of agrammatism and the functional reorganization of language processing after stroke. In all approaches, utterances were analyzed for syntactic completeness, complexity, and morphology. Event-related data analysis was conducted by defining every clause-like unit (CLU) as an event with its onset-time and duration. Agrammatic and correct CLUs were contrasted. Due to the small sample size as well as heterogeneous lesion sizes and sites with lesion foci in the insula lobe, inferior frontal, superior temporal and inferior parietal areas the activation patterns in the agrammatic speakers were analyzed on a single subject level. In the group of healthy speakers, posterior temporal and inferior parietal areas were associated with greater morpho-syntactic demands in complete and complex CLUs. The intentional manipulation of morpho-syntactic structures and the omission of function words were associated with additional inferior frontal activation. Overall, the results revealed that the investigation of the neural correlates of agrammatic language production can be reasonably conducted with an overt language production paradigm.

Advances in experimental psychopatholinguistics: What can we learn from simulation of disorder-like symptoms in human volunteers?

For more than a century, work on patients with acquired or developmental language disorders has informed psycholinguistic models of normal linguistic processing in healthy persons. On the other hand, such models of healthy language processing have been used as blue-prints to gain further insights into the impairments of patients with language pathologies. Against the exemplary background of language production, the first part of this paper reflects this relationship and formulates a desideratum for naturalistic albeit controlled experimental settings. Two recent examples of behavioural and neurofunctional research are presented in which aphasia-like speech symptoms were elicited in healthy control subjects. In the second part, this idea to investigate disorder-like symptoms which are being experimentally induced for the course of the study is further pursued in the field of reading and dyslexia research. Here, it is argued, again on the basis of behavioural and neurofunctional data, that such an approach is advantageous in at least two respects:

1. It allows a much more stringent control of experimental factors and confounds than could be potentially achieved in a clinical setting.

2. It allows in-extenso piloting of experiments with healthy volunteers before actually recruiting selected (and sometimes rare) patients.

It will be concluded that the experimental simulation of disorder-like symptoms in easily accessible healthy volunteers may be a useful approach to understand novel aspects of a language disorder on the basis of a human neurocognitive model of this disorder.