How language flows when movements don't: An automated analysis of spontaneous discourse in Parkinson's disease

Toolkit to Examine Lifelike Language v.2.0: Optimizing Speech Biomarkers of Neurodegeneration

INTRODUCTION

The Toolkit to Examine Lifelike Language (TELL) is a web-based application providing speech biomarkers of neurodegeneration. After deployment of TELL v.1.0 in over 20 sites, we now introduce TELL v.2.0.

METHODS

First, we describe the app's usability features, including functions for collecting and processing data onsite, offline, and via videoconference. Second, we summarize its clinical survey, tapping on relevant habits (e.g., smoking, sleep) alongside linguistic predictors of performance (language history, use, proficiency, and difficulties). Third, we detail TELL's speech-based assessments, each combining strategic tasks and features capturing diagnostically relevant domains (motor function, semantic memory, episodic memory, and emotional processing). Fourth, we specify the app's new data analysis, visualization, and download options. Finally, we list core challenges and opportunities for development.

RESULTS

Overall, TELL v.2.0 offers scalable, objective, and multidimensional insights for the field.

CONCLUSION

Through its technical and scientific breakthroughs, this tool can enhance disease detection, phenotyping, and monitoring.

Toolkit to Examine Lifelike Language (TELL): An app to capture speech and language markers of neurodegeneration

Automated speech and language analysis (ASLA) is a promising approach for capturing early markers of neurodegenerative diseases. However, its potential remains underexploited in research and translational settings, partly due to the lack of a unified tool for data collection, encryption, processing, download, and visualization. Here we introduce the Toolkit to Examine Lifelike Language (TELL) v.1.0.0, a web-based app designed to bridge such a gap. First, we outline general aspects of its development. Second, we list the steps to access and use the app. Third, we specify its data collection protocol, including a linguistic profile survey and 11 audio recording tasks. Fourth, we describe the outputs the app generates for researchers (downloadable files) and for clinicians (real-time metrics). Fifth, we survey published findings obtained through its tasks and metrics. Sixth, we refer to TELL's current limitations and prospects for expansion. Overall, with its current and planned features, TELL aims to facilitate ASLA for research and clinical aims in the neurodegeneration arena. A demo version can be accessed here:  https://demo.sci.tellapp.org/ .

Unveiling the Diagnostic Potential of Linguistic Markers in Identifying Individuals with Parkinson's Disease through Artificial Intelligence: A Systematic Review

While extensive research has documented the cognitive changes associated with Parkinson's disease (PD), a relatively small portion of the empirical literature investigated the language abilities of individuals with PD. Recently, artificial intelligence applied to linguistic data has shown promising results in predicting the clinical diagnosis of neurodegenerative disorders, but a deeper investigation of the current literature available on PD is lacking. This systematic review investigates the nature of language disorders in PD by assessing the contribution of machine learning (ML) to the classification of patients with PD. A total of 10 studies published between 2016 and 2023 were included in this review. Tasks used to elicit language were mainly structured or unstructured narrative discourse. Transcriptions were mostly analyzed using Natural Language Processing (NLP) techniques. The classification accuracy (%) ranged from 43 to 94, sensitivity (%) ranged from 8 to 95, specificity (%) ranged from 3 to 100, AUC (%) ranged from 32 to 97. The most frequent optimal linguistic measures were lexico-semantic (40%), followed by NLP-extracted features (26%) and morphological consistency features (20%). Artificial intelligence applied to linguistic markers provides valuable insights into PD. However, analyzing measures derived from narrative discourse can be time-consuming, and utilizing ML requires specialized expertise. Moving forward, it is important to focus on facilitating the integration of both narrative discourse analysis and artificial intelligence into clinical practice.

Neurocognitive correlates of semantic memory navigation in Parkinson's disease

Cognitive studies on Parkinson's disease (PD) reveal abnormal semantic processing. Most research, however, fails to indicate which conceptual properties are most affected and capture patients' neurocognitive profiles. Here, we asked persons with PD, healthy controls, and individuals with behavioral variant frontotemporal dementia (bvFTD, as a disease control group) to read concepts (e.g., 'sun') and list their features (e.g., hot). Responses were analyzed in terms of ten word properties (including concreteness, imageability, and semantic variability), used for group-level comparisons, subject-level classification, and brain-behavior correlations. PD (but not bvFTD) patients produced more concrete and imageable words than controls, both patterns being associated with overall cognitive status. PD and bvFTD patients showed reduced semantic variability, an anomaly which predicted semantic inhibition outcomes. Word-property patterns robustly classified PD (but not bvFTD) patients and correlated with disease-specific hypoconnectivity along the sensorimotor and salience networks. Fine-grained semantic assessments, then, can reveal distinct neurocognitive signatures of PD.

Speech and language markers of neurodegeneration: a call for global equity

In the field of neurodegeneration, speech and language assessments are useful for diagnosing aphasic syndromes and for characterizing other disorders. As a complement to classic tests, scalable and low-cost digital tools can capture relevant anomalies automatically, potentially supporting the quest for globally equitable markers of brain health. However, this promise remains unfulfilled due to limited linguistic diversity in scientific works and clinical instruments. Here we argue for cross-linguistic research as a core strategy to counter this problem. First, we survey the contributions of linguistic assessments in the study of primary progressive aphasia and the three most prevalent neurodegenerative disorders worldwide-Alzheimer's disease, Parkinson's disease, and behavioural variant frontotemporal dementia. Second, we address two forms of linguistic unfairness in the literature: the neglect of most of the world's 7000 languages and the preponderance of English-speaking cohorts. Third, we review studies showing that linguistic dysfunctions in a given disorder may vary depending on the patient's language and that English speakers offer a suboptimal benchmark for other language groups. Finally, we highlight different approaches, tools and initiatives for cross-linguistic research, identifying core challenges for their deployment. Overall, we seek to inspire timely actions to counter a looming source of inequity in behavioural neurology.

Ecological Meanings: A Consensus Paper on Individual Differences and Contextual Influences in Embodied Language

Embodied theories of cognition consider many aspects of language and other cognitive domains as the result of sensory and motor processes. In this view, the appraisal and the use of concepts are based on mechanisms of simulation grounded on prior sensorimotor experiences. Even though these theories continue receiving attention and support, increasing evidence indicates the need to consider the flexible nature of the simulation process, and to accordingly refine embodied accounts. In this consensus paper, we discuss two potential sources of variability in experimental studies on embodiment of language: individual differences and context. Specifically, we show how factors contributing to individual differences may explain inconsistent findings in embodied language phenomena. These factors include sensorimotor or cultural experiences, imagery, context-related factors, and cognitive strategies. We also analyze the different contextual modulations, from single words to sentences and narratives, as well as the top-down and bottom-up influences. Similarly, we review recent efforts to include cultural and language diversity, aging, neurodegenerative diseases, and brain disorders, as well as bilingual evidence into the embodiment framework. We address the importance of considering individual differences and context in clinical studies to drive translational research more efficiently, and we indicate recommendations on how to correctly address these issues in future research. Systematically investigating individual differences and context may contribute to understanding the dynamic nature of simulation in language processes, refining embodied theories of cognition, and ultimately filling the gap between cognition in artificial experimental settings and cognition in the wild (i.e., in everyday life).

Narrative discourse production in Parkinson's disease: Decoupling the role of cognitive-linguistic and motor speech changes

Introduction

the interplay between neuropsychological and communicative abilities in Parkinson's disease (PD) has been relatively overlooked, and it is not entirely understood which difficulties are consequent to impaired motor control, and which have a linguistic/cognitive basis. Here, we examined narrative discourse in PD using a multi-level analysis procedure considering sentence-level (productivity, lexical-grammatical processing) and discourse-level processes (narrative organization, informativeness), and partialling out patients' motor speech impairments. The interaction between cognitive (i.e. linguistic and executive) and communication abilities was also investigated.

Methods

Twenty-nine PD subjects in the mild stage of the disease were compared to 29 matched healthy comparators (HC) on quantitative measures of narrative discourse derived from two picture description tasks. Multivariate (considering articulation rate and educational attainment as covariates) and univariate (with group membership as independent variable) analyses of variance were conducted on separate linguistic domains. The contribution of executive/linguistic abilities to PD's narrative performance was explored by multiple regression analyses on narrative measures significantly differentiating patients from HC.

Results

significant reductions in patients were observed on measures of productivity (less well-formed words, shorter sentences) and informativeness (fewer conceptual units, less informative elements, lower number of details) and these alterations were explained by variations in linguistic abilities (action and object naming) rather than executive abilities. Articulation rate and educational attainment did not impact the observed reduced productivity and under-informativeness.

Conclusion

referential narrative discourse is altered in PD, regardless of motor impairments in speech production. The observed reductions in productivity/informativeness aspects of narratives were related to naming abilities and in particular to verbs processing, consistently with the neurocognitive model of motor language coupling. Since narratives are amenable to recurrent and automated analysis for the identification of linguistic patterns potentially anticipating the development of PD and the onset of cognitive deterioration, discourse abilities should be quantitatively and repeatedly profiled in the disorder.

Deep Learning and Artificial Intelligence Applied to Model Speech and Language in Parkinson's Disease

Parkinson's disease (PD) is the second most prevalent neurodegenerative disorder in the world, and it is characterized by the production of different motor and non-motor symptoms which negatively affect speech and language production. For decades, the research community has been working on methodologies to automatically model these biomarkers to detect and monitor the disease; however, although speech impairments have been widely explored, language remains underexplored despite being a valuable source of information, especially to assess cognitive impairments associated with non-motor symptoms. This study proposes the automatic assessment of PD patients using different methodologies to model speech and language biomarkers. One-dimensional and two-dimensional convolutional neural networks (CNNs), along with pre-trained models such as Wav2Vec 2.0, BERT, and BETO, were considered to classify PD patients vs. Healthy Control (HC) subjects. The first approach consisted of modeling speech and language independently. Then, the best representations from each modality were combined following early, joint, and late fusion strategies. The results show that the speech modality yielded an accuracy of up to 88%, thus outperforming all language representations, including the multi-modal approach. These results suggest that speech representations better discriminate PD patients and HC subjects than language representations. When analyzing the fusion strategies, we observed that changes in the time span of the multi-modal representation could produce a significant loss of information in the speech modality, which was likely linked to a decrease in accuracy in the multi-modal experiments. Further experiments are necessary to validate this claim with other fusion methods using different time spans.

Latin American women in dementia research: outstanding contributions, barriers, and opportunities from Argentinian, Chilean, and Colombian colleagues

Women's contributions to science have been consistently underrepresented throughout history. Despite many efforts and some progresses being made to reduce gender inequity in science, pursuing an academic career across disciplines, including Alzheimer's disease (AD) and other dementias, remains challenging for women. Idiosyncratic difficulties of Latin American countries likely accentuate the gender gap. In this Perspective, we celebrate outstanding contributions from Argentinian, Chilean, and Colombian colleagues in dementia research and discuss barriers and opportunities identified by them. We aim to acknowledge Latin American women's work and bring visibility to the challenges they face throughout their careers in order to inform potential solutions. Also, we highlight the need to perform a systematic assessment of the gender gap in the Latin American dementia community of researchers.

Reduced syntactic recursion in spontaneous speech of Parkinson's disease patients

Although characterized as a movement disorder, Parkinson's disease (PD) affects more than just the motor system. Within the heterogenous non-motor symptoms, language impairment is frequent but poorly understood beyond semantic processing. This study investigates the impact of PD on syntactic subordination in spontaneous language production. Fifteen PD patients in ON levodopa status narrated a short story guided by a set of pictures. Thirteen PD patients were also assessed in OFF levodopa status. Narrations were digitally recorded, subsequently transcribed and annotated, making the produced speech accessible to systematical quantitative analysis. Compared to a healthy matched control group, PD patients showed a significant reduction of subordinating structures while the number of non-embedding sentences remained unaffected. No significant effect comparing ON versus OFF levodopa status emerged. Our results suggest a contribution of the basal ganglia to language processing, such as syntactic composition, which, however, does not seem to be dopamine dependent.

Predictive language comprehension in Parkinson's disease

Verb and action knowledge deficits are reported in persons with Parkinson's disease (PD), even in the absence of dementia or mild cognitive impairment. However, the impact of these deficits on combinatorial semantic processing is less well understood. Following on previous verb and action knowledge findings, we tested the hypothesis that PD impairs the ability to integrate event-based thematic fit information during online sentence processing. Specifically, we anticipated persons with PD with age-typical cognitive abilities would perform more poorly than healthy controls during a visual world paradigm task requiring participants to predict a target object constrained by the thematic fit of the agent-verb combination. Twenty-four PD and 24 healthy age-matched participants completed comprehensive neuropsychological assessments. We recorded participants' eye movements as they heard predictive sentences (The fisherman rocks the boat) alongside target, agent-related, verb-related, and unrelated images. We tested effects of group (PD/control) on gaze using growth curve models. There were no significant differences between PD and control participants, suggesting that PD participants successfully and rapidly use combinatory thematic fit information to predict upcoming language. Baseline sentences with no predictive information (e.g., Look at the drum) confirmed that groups showed equivalent sentence processing and eye movement patterns. Additionally, we conducted an exploratory analysis contrasting PD and controls' performance on low-motion-content versus high-motion-content verbs. This analysis revealed fewer predictive fixations in high-motion sentences only for healthy older adults. PD participants may adapt to their disease by relying on spared, non-action-simulation-based language processing mechanisms, although this conclusion is speculative, as the analyses of high- vs. low-motion items was highly limited by the study design. These findings provide novel evidence that individuals with PD match healthy adults in their ability to use verb meaning to predict upcoming nouns despite previous findings of verb semantic impairment in PD across a variety of tasks.

Neuropsychological endpoints for clinical trials in methylmalonic acidemia and propionic acidemia: A pilot study

Introduction

This pilot study assessed instruments measuring relatively discrete neuropsychological domains to inform the selection of clinical outcome assessments that may be considered for interventional trials in methylmalonic acidemia (MMA) and propionic acidemia (PA).

Methods

Tests and questionnaires were selected for their possible relevance to MMA and PA and potential sensitivity to modest changes in functioning and behavior.

Results

Twenty-one patients (<18 years, n = 10;>18 years, n = 11) and/or their caregivers responded to video interviews and paper tests. Language deficits and significant motor deficits in some participants impacted scoring, especially in the verbal and processing speed sections of the Wechsler Intelligence Scale for Children, Fifth Edition (WISC-V) and the Wechsler Adult Intelligence Scale, Fourth Edition (WAIS-IV). However, all participants ≥12 years of age were able to complete the Cookie Theft Picture Task. Thus, verbal discourse remains a potentially useful endpoint for participants in this age group. The Vineland Adaptive Behavior Scales (VABS-3) Adaptive Behavior Composite and Communication Scores confirmed delayed or immature functioning in day-to-day activities in these participants. Significant motor deficits prevented completion of some tests. Computerized processing speed tasks, which require pressing a button or tapping a computer screen, may be easier than writing or checking off boxes on paper in this cohort. Sleep characteristics among MMA participants were within normative ranges of the Child and Adolescent Sleep Checklist (CASC), indicating that this measurement would not provide valuable data in a clinical trial. Despite their challenges, responses to the Metabolic Quality of Life Questionnaire indicated these patients and their caregivers perceive an overall high quality of life.

Conclusion

Overall, test and questionnaire results were notably different between participants with MMA and participants with PA. The study demonstrates that pilot studies can detect instruments that may not be appropriate for individuals with language or motor deficits and that may not provide a broad range of scores reflecting disease severity. It also provides a rationale for focusing on discrete neuropsychological domains since some aspects of functioning were less affected than others and some were more closely related to disease severity. When global measures are used, overall scores may mask specific deficits. A pilot study like this one cannot ensure that scores will change over time in response to a specific treatment in a clinical trial. However, it can avert the selection of instruments that do not show associations with severity or biomedical parameters likely to be the target of a clinical trial. A pilot study can also identify when differences in diagnoses and baseline functioning need to be addressed prior to developing the analytical plan for the trial.

Detecting Parkinson's disease and its cognitive phenotypes via automated semantic analyses of action stories

Action-concept outcomes are useful targets to identify Parkinson's disease (PD) patients and differentiate between those with and without mild cognitive impairment (PD-MCI, PD-nMCI). Yet, most approaches employ burdensome examiner-dependent tasks, limiting their utility. We introduce a framework capturing action-concept markers automatically in natural speech. Patients from both subgroups and controls retold an action-laden and a non-action-laden text (AT, nAT). In each retelling, we weighed action and non-action concepts through our automated Proximity-to-Reference-Semantic-Field (P-RSF) metric, for analysis via ANCOVAs (controlling for cognitive dysfunction) and support vector machines. Patients were differentiated from controls based on AT (but not nAT) P-RSF scores. The same occurred in PD-nMCI patients. Conversely, PD-MCI patients exhibited reduced P-RSF scores for both texts. Direct discrimination between patient subgroups was not systematic, but it yielded best outcomes via AT scores. Our approach outperformed classifiers based on corpus-derived embeddings. This framework opens scalable avenues to support PD diagnosis and phenotyping.

Computerized analysis of speech and voice for Parkinson's disease: A systematic review

BACKGROUND AND OBJECTIVE

Speech impairment is an early symptom of Parkinson's disease (PD). This study has summarized the literature related to speech and voice in detecting PD and assessing its severity.

METHODS

A systematic review of the literature from 2010 to 2021 to investigate analysis methods and signal features. The keywords "Automatic analysis" in conjunction with "PD speech" or "PD voice" were used, and the PubMed and ScienceDirect databases were searched. A total of 838 papers were found on the first run, of which 189 were selected. One hundred and forty-seven were found to be suitable for the review. The different datasets, recording protocols, signal analysis methods and features that were reported are listed. Values of the features that separate PD patients from healthy controls were tabulated. Finally, the barriers that limit the wide use of computerized speech analysis are discussed.

RESULTS

Speech and voice may be valuable markers for PD. However, large differences between the datasets make it difficult to compare different studies. In addition, speech analytic methods that are not informed by physiological understanding may alienate clinicians.

CONCLUSIONS

The potential usefulness of speech and voice for the detection and assessment of PD is confirmed by evidence from the classification and correlation results.

Task-based profiles of language impairment and their relationship to cognitive dysfunction in Parkinson's disease

Objective

Parkinson’s Disease (PD) is associated with both motor and non-motor problems, such as cognitive impairment. Particular focus in this area has been on the relationship between language impairment and decline in other cognitive functions, with the literature currently inconclusive on how the nature and degree of language impairment relate to cognition or other measures of disease severity. In addition, little information is available on how language problems identified in experimental task set-ups relate to competency in self-generated language paradigms such as picture description, monologues or conversations. This study aimed to inform clinical management of language impairment in PD by exploring (1) language performance across a range of experimental as well as self-generated language tasks, (2) how the relationship between these two aspects might be affected by the nature of the cognitive and language assessment; and (3) to what degree performance can be predicted across the language tasks.

Methods

22 non-demented people with PD (PwPD) and 22 healthy control participants performed a range of cognitive and language tasks. Cognitive tasks included a screening assessment in addition to tests for set shifting, short term memory, attention, as well as letter and category fluency. Language was investigated in highly controlled grammar tasks as well as a Sentence Generation and a Narrative.

Results

The study highlighted impaired ability in set-shifting and letter fluency in the executive function tasks, and a higher rate of grammatical and lexical errors across all language tasks in the PD group. The performance in the grammar task was linked to set shifting ability, but error rates in Sentence Generation and Narrative were independent of this. There was no relevant relationship between performances across the three language tasks.

Conclusions

Our results suggest that there is a link between executive function and language performance, but that this is task dependent in non-demented PwPD. This has implications for the management of language impairment in PD, both for assessment and for designing effective interventions.

Automated text-level semantic markers of Alzheimer's disease

INTRODUCTION

Automated speech analysis has emerged as a scalable, cost-effective tool to identify persons with Alzheimer's disease dementia (ADD). Yet, most research is undermined by low interpretability and specificity.

METHODS

Combining statistical and machine learning analyses of natural speech data, we aimed to discriminate ADD patients from healthy controls (HCs) based on automated measures of domains typically affected in ADD: semantic granularity (coarseness of concepts) and ongoing semantic variability (conceptual closeness of successive words). To test for specificity, we replicated the analyses on Parkinson's disease (PD) patients.

RESULTS

Relative to controls, ADD (but not PD) patients exhibited significant differences in both measures. Also, these features robustly discriminated between ADD patients and HC, while yielding near-chance classification between PD patients and HCs.

DISCUSSION

Automated discourse-level semantic analyses can reveal objective, interpretable, and specific markers of ADD, bridging well-established neuropsychological targets with digital assessment tools.

Language in Behavioral Variant Frontotemporal Dementia: Another Stone to Be Turned in Latin America

Beyond canonical deficits in social cognition and interpersonal conduct, behavioral variant frontotemporal dementia (bvFTD) involves language difficulties in a substantial proportion of cases. However, since most evidence comes from high-income countries, the scope and relevance of language deficits in Latin American bvFTD samples remain poorly understood. As a first step toward reversing this scenario, we review studies reporting language measures in Latin American bvFTD cohorts relative to other groups. We identified 24 papers meeting systematic criteria, mainly targeting phonemic and semantic fluency, naming, semantic processing, and comprehension skills. The evidence shows widespread impairments in these domains, often related to overall cognitive disturbances. Some of these deficits may be as severe as in other diseases where they are more widely acknowledged, such as Alzheimer's disease. Considering the prevalence and informativeness of language deficits in bvFTD patients from other world regions, the need arises for more systematic research in Latin America, ideally spanning multiple domains, in diverse languages and dialects, with validated batteries. We outline key challenges and pathways of progress in this direction, laying the ground for a new regional research agenda on the disorder.

Rekindling Action Language: A Neuromodulatory Study on Parkinson's Disease Patients

Impairments of action semantics (a cognitive domain that critically engages motor brain networks) are pervasive in early Parkinson's disease (PD). However, no study has examined whether action semantic skills in persons with this disease can be influenced by non-invasive neuromodulation. Here, we recruited 22 PD patients and performed a five-day randomized, blinded, sham-controlled study to assess whether anodal transcranial direct current stimulation (atDCS) over the primary motor cortex, combined with cognitive training, can boost action-concept processing. On day 1, participants completed a picture-word association (PWA) task involving action-verb and object-noun conditions. They were then randomly assigned to either an atDCS (n = 11, 2 mA for 20 m) or a sham tDCS (n = 11, 2 mA for 30 s) group and performed an online PWA practice over three days. On day 5, they repeated the initial protocol. Relative to sham tDCS, the atDCS group exhibited faster reaction times for action (as opposed to object) concepts in the post-stimulation test. This result was exclusive to the atDCS group and held irrespective of the subjects' cognitive, executive, and motor skills, further attesting to its specificity. Our findings suggest that action-concept deficits in PD are distinctively grounded in motor networks and might be countered by direct neuromodulation of such circuits. Moreover, they provide new evidence for neurosemantic models and inform a thriving agenda in the embodied cognition framework.

Corticostriatal Regulation of Language Functions

The role of corticostriatal circuits in language functions is unclear. In this review, we consider evidence from language learning, syntax, and controlled language production and comprehension tasks that implicate various corticostriatal circuits. Converging evidence from neuroimaging in healthy individuals, studies in populations with subcortical dysfunction, pharmacological studies, and brain stimulation suggests a domain-general regulatory role of corticostriatal systems in language operations. The role of corticostriatal systems in language operations identified in this review is likely to reflect a broader function of the striatum in responding to uncertainty and conflict which demands selection, sequencing, and cognitive control. We argue that this role is dynamic and varies depending on the degree and form of cognitive control required, which in turn will recruit particular corticostriatal circuits and components organised in a cognitive hierarchy.

Language as a biomarker for psychosis: A natural language processing approach

Human ratings of conceptual disorganization, poverty of content, referential cohesion and illogical thinking have been shown to predict psychosis onset in prospective clinical high risk (CHR) cohort studies. The potential value of linguistic biomarkers has been significantly magnified, however, by recent advances in natural language processing (NLP) and machine learning (ML). Such methodologies allow for the rapid and objective measurement of language features, many of which are not easily recognized by human raters. Here we review the key findings on language production disturbance in psychosis. We also describe recent advances in the computational methods used to analyze language data, including methods for the automatic measurement of discourse coherence, syntactic complexity, poverty of content, referential coherence, and metaphorical language. Linguistic biomarkers of psychosis risk are now undergoing cross-validation, with attention to harmonization of methods. Future directions in extended CHR networks include studies of sources of variance, and combination with other promising biomarkers of psychosis risk, such as cognitive and sensory processing impairments likely to be related to language. Implications for the broader study of social communication, including reciprocal prosody, face expression and gesture, are discussed.

Classifying Parkinson's Disease Patients With Syntactic and Socio-emotional Verbal Measures

Frontostriatal disorders, such as Parkinson's disease (PD), are characterized by progressive disruption of cortico-subcortical dopaminergic loops involved in diverse higher-order domains, including language. Indeed, syntactic and emotional language tasks have emerged as potential biomarkers of frontostriatal disturbances. However, relevant studies and models have typically considered these linguistic dimensions in isolation, overlooking the potential advantages of targeting multidimensional markers. Here, we examined whether patient classification can be improved through the joint assessment of both dimensions using sentential stimuli. We evaluated 31 early PD patients and 24 healthy controls via two syntactic measures (functional-role assignment, parsing of long-distance dependencies) and a verbal task tapping social emotions (envy, Schadenfreude) and compared their classification accuracy when analyzed in isolation and in combination. Complementarily, we replicated our approach to discriminate between patients on and off medication. Results showed that specific measures of each dimension were selectively impaired in PD. In particular, joint analysis of outcomes in functional-role assignment and Schadenfreude improved the classification accuracy of patients and controls, irrespective of their overall cognitive and affective state. These results suggest that multidimensional linguistic assessments may better capture the complexity and multi-functional impact of frontostriatal disruptions, highlighting their potential contributions in the ongoing quest for sensitive markers of PD.

Electrifying discourse: Anodal tDCS of the primary motor cortex selectively reduces action appraisal in naturalistic narratives

Non-invasive stimulation of the primary motor cortex (M1) modulates processing of decontextualized action words and sentences (i.e., verbal units denoting bodily motion). This suggests that language comprehension hinges on brain circuits mediating the bodily experiences evoked by verbal material. Yet, despite its relevance to constrain mechanistic language models, such a finding fails to reveal whether and how relevant circuits operate in the face of full-blown, everyday texts. Using a novel naturalistic discourse paradigm, we examined whether direct modulation of M1 excitability influences the grasping of narrated actions. Following random group assignment, participants received anodal transcranial direct current stimulation over the left M1, or sham stimulation of the same area, or anodal stimulation of the left ventrolateral prefrontal cortex. Immediately afterwards, they listened to action-laden and neutral stories and answered questions on information realized by verbs (denoting action and non-action processes) and circumstances (conveying locative or temporal details). Anodal stimulation of the left M1 selectively decreased outcomes on action-relative to non-action information -a pattern that discriminated between stimulated and sham participants with 74% accuracy. This result was particular to M1 and held irrespective of the subjects' working memory and vocabulary skills, further attesting to its specificity. Our findings suggest that offline modulation of motor-network excitability might lead to transient unavailability of putative resources needed to evoke actions in naturalistic texts, opening promising avenues for the language embodiment framework.

Evaluation of Speech-Based Digital Biomarkers: Review and Recommendations

Speech represents a promising novel biomarker by providing a window into brain health, as shown by its disruption in various neurological and psychiatric diseases. As with many novel digital biomarkers, however, rigorous evaluation is currently lacking and is required for these measures to be used effectively and safely. This paper outlines and provides examples from the literature of evaluation steps for speech-based digital biomarkers, based on the recent V3 framework (Goldsack et al., 2020). The V3 framework describes 3 components of evaluation for digital biomarkers: verification, analytical validation, and clinical validation. Verification includes assessing the quality of speech recordings and comparing the effects of hardware and recording conditions on the integrity of the recordings. Analytical validation includes checking the accuracy and reliability of data processing and computed measures, including understanding test-retest reliability, demographic variability, and comparing measures to reference standards. Clinical validity involves verifying the correspondence of a measure to clinical outcomes which can include diagnosis, disease progression, or response to treatment. For each of these sections, we provide recommendations for the types of evaluation necessary for speech-based biomarkers and review published examples. The examples in this paper focus on speech-based biomarkers, but they can be used as a template for digital biomarker development more generally.

Precision Medicine, AI, and the Future of Personalized Health Care

The convergence of artificial intelligence (AI) and precision medicine promises to revolutionize health care. Precision medicine methods identify phenotypes of patients with less‐common responses to treatment or unique healthcare needs. AI leverages sophisticated computation and inference to generate insights, enables the system to reason and learn, and empowers clinician decision making through augmented intelligence. Recent literature suggests that translational research exploring this convergence will help solve the most difficult challenges facing precision medicine, especially those in which nongenomic and genomic determinants, combined with information from patient symptoms, clinical history, and lifestyles, will facilitate personalized diagnosis and prognostication.

Strategic Spatial Anchoring as Cognitive Compensation During Word Categorization in Parkinson's Disease: Evidence from Eye Movements

The association between a word and typical location (e.g., cloud-up) appears to modulate healthy individuals' response times and visual attention. This study examined whether similar effects can be observed in a clinical population characterized by difficulties in both spatial representation and lexical processing. In an eye-tracking experiment, participants categorized spoken words as either up-associated or down-associated. Parkinson's disease patients exhibited a tendency to maintain their visual attention in the upper half of the screen, however, this tendency was significantly lower when participants categorized concepts as down-associated. Instead, the control group showed no preference for either the upper or lower half of the screen. We argue that Parkinson's disease patients present an over-reliance on space during word categorization as a form of cognitive compensation. Such compensation reveals that this clinical population may use spatial anchoring when categorizing words with a spatial association, even in the absence of explicit spatial cues.

From discourse to pathology: Automatic identification of Parkinson's disease patients via morphological measures across three languages

Embodied cognition research on Parkinson's disease (PD) points to disruptions of frontostriatal language functions as sensitive targets for clinical assessment. However, no existing approach has been tested for crosslinguistic validity, let alone by combining naturalistic tasks with machine-learning tools. To address these issues, we conducted the first classifier-based examination of morphological processing (a core frontostriatal function) in spontaneous monologues from PD patients across three typologically different languages. The study comprised 330 participants, encompassing speakers of Spanish (61 patients, 57 matched controls), German (88 patients, 88 matched controls), and Czech (20 patients, 16 matched controls). All subjects described the activities they perform during a regular day, and their monologues were automatically coded via morphological tagging, a computerized method that labels each word with a part-of-speech tag (e.g., noun, verb) and specific morphological tags (e.g., person, gender, number, tense). The ensuing data were subjected to machine-learning analyses to assess whether differential morphological patterns could classify between patients and controls and reflect the former's degree of motor impairment. Results showed robust classification rates, with over 80% of patients being discriminated from controls in each language separately. Moreover, the most discriminative morphological features were associated with the patients' motor compromise (as indicated by Pearson r correlations between predicted and collected motor impairment scores that ranged from moderate to moderate-to-strong across languages). Taken together, our results suggest that morphological patterning, an embodied frontostriatal domain, may be distinctively affected in PD across languages and even under ecological testing conditions.

Using Language Processing and Speech Analysis for the Identification of Psychosis and Other Disorders

Increasingly, data-driven methods have been implemented to understand psychopathology. Language is the main source of information in psychiatry and represents "big data" at the level of the individual. Language and behavior are amenable to computational natural language processing (NLP) analytics, which may help operationalize the mental status examination. In this review, we highlight the application of NLP to schizophrenia and its risk states as an exemplar of its use, operationalizing tangential and concrete speech as reductions in semantic coherence and syntactic complexity, respectively. Other clinical applications are reviewed, including forecasting suicide risk and detecting intoxication. Challenges and future directions are discussed, including biomarker development, harmonization, and application of NLP more broadly to behavior, including intonation/prosody, facial expression and gesture, and the integration of these in dyads and during discourse. Similar NLP analytics can also be applied beyond humans to behavioral motifs across species, important for modeling psychopathology in animal models. Finally, clinical neuroscience can inform the development of artificial intelligence.

Speech-based characterization of dopamine replacement therapy in people with Parkinson's disease

People with Parkinson's (PWP) disease are under constant tension with respect to their dopamine replacement therapy (DRT) regimen. Waiting too long between doses results in more prominent symptoms, loss of motor function, and greater risk of falling per step. Shortened pill cycles can lead to accelerated habituation and faster development of disabling dyskinesias. The Unified Parkinson's Disease Rating Scale (MDS-UPDRS) is the gold standard for monitoring Parkinson's disease progression but requires a neurologist to administer and therefore is not an ideal instrument to continuously evaluate short-term disease fluctuations. We investigated the feasibility of using speech to detect changes in medication states, based on expectations of subtle changes in voice and content related to dopaminergic levels. We calculated acoustic and prosodic features for three speech tasks (picture description, reverse counting, and diadochokinetic rate) for 25 PWP, each evaluated "ON" and "OFF" DRT. Additionally, we generated semantic features for the picture description task. Classification of ON/OFF medication states using features generated from picture description, reverse counting and diadochokinetic rate tasks resulted in cross-validated accuracy rates of 0.89, 0.84, and 0.60, respectively. The most discriminating task was picture description which provided evidence that participants are more likely to use action words in ON than in OFF state. We also found that speech tempo was modified by DRT. Our results suggest that automatic speech assessment can capture changes associated with the DRT cycle. Given the ease of acquiring speech data, this method shows promise to remotely monitor DRT effects.

From action to abstraction: The sensorimotor grounding of metaphor in Parkinson's disease

Embodied cognition theories propose that the semantic representations engaged in during language comprehension are partly supported by perceptual and motor systems, via simulation. Activation in modality-specific regions of cortex is associated with the comprehension of literal language that describes the analogous modalities, but studies addressing the grounding of non-literal or figurative language, such as metaphors, have yielded mixed results. Differences in the psycholinguistic characteristics of sentence stimuli across studies have likely contributed to this lack of consensus. Furthermore, previous studies have been largely correlational, whilst patient studies are a critical way of determining if intact sensorimotor function is necessary to understand language drawing on sensorimotor information. We designed a battery of metaphorical and literal sentence stimuli using action and sound words, with an unprecedented level of control over critical psycholinguistic variables, to test hypotheses about the grounding of metaphorical language. In this Registered Report, we assessed the comprehension of these sentences in 41 patients with Parkinson's disease, who were predicted to be disproportionately affected by the action sentences relative to the sound sentences, and compared their performance to that of 39 healthy age-matched controls who were predicted to show no difference in performance due to sensory modality. Using preregistered Bayesian model comparison methods, we found that PD patients' comprehension of literal action sentences was not impaired, while there was some evidence for a slowing of responses to action metaphors. Follow up exploratory analyses suggest that this response time modality effect was driven by one type of metaphor (predicate) and was absent in another (nominal), despite the fact that the action semantics were similar in both syntactic forms. These results suggest that the conditions under which PD patients demonstrate hypothesized embodiment effects are limited. We offer a critical assessment of the PD action language literature and discuss implications for the embodiment debate. In addition, we suggest how future studies could leverage Bayesian statistical methods to provide more convincing evidence for or against embodied cognition effects.

A dissociation between syntactic and lexical processing in Parkinson's disease

Parkinson's disease (PD), which involves the degeneration of dopaminergic neurons in the basal ganglia, has long been associated with motor deficits. Increasing evidence suggests that language can also be impaired, including aspects of syntactic and lexical processing. However, the exact pattern of these impairments remains somewhat unclear, for several reasons. Few studies have examined and compared syntactic and lexical processing within subjects, so their relative deficits remain to be elucidated. Studies have focused on earlier stages of PD, so syntactic and lexical processing in later stages are less well understood. Research has largely probed English and a handful of other European languages, and it is unclear whether findings generalize more broadly. Finally, few studies have examined links between syntactic/lexical impairments and their neurocognitive substrates, such as measures of basal ganglia degeneration or dopaminergic processes. We addressed these gaps by investigating multiple aspects of Farsi syntactic and lexical processing in 40 Farsi native-speaking moderate-to-severe non-demented PD patients, and 40 healthy controls. Analyses revealed equivalent impairments of syntactic comprehension and syntactic judgment, across different syntactic structures. Lexical processing was impaired only for motor function-related objects (e.g., naming 'hammer', but not 'mountain'), in line with findings of PD deficits at naming action verbs as compared to objects, without the verb/noun confound. In direct comparisons between lexical and syntactic tasks, patients were better at naming words like 'mountain' (but not words like 'hammer') than at syntactic comprehension and syntactic judgment. Performance at syntactic comprehension correlated with the last levodopa equivalent dose. No other correlations were found between syntactic/lexical processing measures and either levodopa equivalent dose or hypokinesia, which reflects degeneration of basal ganglia motor-related circuits. All critical significant main effects, interactions, and correlations yielded large effect sizes. The findings elucidate the nature of syntactic and lexical processing impairments in PD.

Embodied Semantics in a Second Language: Critical Review and Clinical Implications

The role of the sensorimotor system in second language (L2) semantic processing as well as its clinical implications for bilingual patients has hitherto been neglected. We offer an overview of the issues at stake in this under-investigated field, presenting the theoretical and clinical relevance of studying L2 embodiment and reviewing the few studies on this topic. We highlight that (a) the sensorimotor network is involved in L2 processing, and that (b) in most studies, L2 is differently embodied than L1, reflected in a lower degree or in a different pattern of L2 embodiment. Importantly, we outline critical issues to be addressed in order to guide future research. We also delineate the subsequent steps needed to confirm or dismiss the value of language therapeutic approaches based on embodiment theories as a complement of speech and language therapies in adult bilinguals.

Differential 28-Days Cyclic Modulation of Affective Intensity in Female and Male Participants via Social Media

The menstrual cycle affects many aspects of female physiology, from the immune system to behavioral and emotional regulation. It is unclear however if these physiological changes are reflected in everyday, naturalistic language production, and moreover whether these putative effects can be consistently quantified. Using a novel approach based on social networks, we characterized linguistic expression differences in female and male volunteers over the course of several months, while having no physiological or reported information of the female participants' menstrual cycles. We used a simple algorithm to quantify the linguistic affect intensity of 418 (184 females and 234 males) subjects using their social networks production and found a 7-day modulatory cycle of affect intensity that corresponds to labor-week fluctuations, with no significant difference by biological sex, and a 28-day cycle over which females are significantly different than males. Our results are consistent with the hypothesis that the menstrual cycle modulates affective features of naturalistic linguistic production.

Negation markers inhibit motor routines during typing of manual action verbs

We explored whether negation markers recruit inhibitory mechanisms during keyboard-based action-verb typing. In each trial, participants read two sentences: the first featured a context (There is a contract) and the second ended with a relevant verb which had to be immediately typed. Crucially, the verb could describe manual actions, non-manual actions or non-motor processes, with either affirmative (You do sign it) or negative (You don't sign it) polarity. We assessed the impact of verb type and polarity on two typing dimensions: motor programming (lapse between target onset and first keystroke) and motor execution (lapse between first and last keystroke). Negation yielded no effect on motor planning, but it selectively delayed typing execution for manual-action verbs, irrespective of the subjects' typing skills. This suggests that processing negations during comprehension of manual-action sentences recruits inhibitory mechanisms acting on same-effector movements. Our novel finding extends embodied models of language and effector-specific motor-language integration.

Action Semantics at the Bottom of the Brain: Insights From Dysplastic Cerebellar Gangliocytoma

Recent embodied cognition research shows that access to action verbs in shallow-processing tasks becomes selectively compromised upon atrophy of the cerebellum, a critical motor region. Here we assessed whether cerebellar damage also disturbs explicit semantic processing of action pictures and its integration with ongoing motor responses. We evaluated a cognitively preserved 33-year-old man with severe dysplastic cerebellar gangliocytoma (Lhermitte-Duclos disease), encompassing most of the right cerebellum and the posterior part of the left cerebellum. The patient and eight healthy controls completed two semantic association tasks (involving pictures of objects and actions, respectively) that required motor responses. Accuracy results via Crawford’s modified t-tests revealed that the patient was selectively impaired in action association. Moreover, reaction-time analysis through Crawford’s Revised Standardized Difference Test showed that, while processing of action concepts involved slower manual responses in controls, no such effect was observed in the patient, suggesting that motor-semantic integration dynamics may be compromised following cerebellar damage. Notably, a Bayesian Test for a Deficit allowing for Covariates revealed that these patterns remained after covarying for executive performance, indicating that they were not secondary to extra-linguistic impairments. Taken together, our results extend incipient findings on the embodied functions of the cerebellum, offering unprecedented evidence of its crucial role in processing non-verbal action meanings and integrating them with concomitant movements. These findings illuminate the relatively unexplored semantic functions of this region while calling for extensions of motor cognition models.

A core avenue for transcultural research on dementia: on the cross-linguistic generalization of language-related effects in Alzheimer's disease and Parkinson's disease

OBJECTIVE

Language is a key source of cross-cultural variability, which may have both subtle and major effects on neurocognition. However, this issue has been largely overlooked in two flourishing lines of research assessing the relationship between language-related neural systems and dementia. This paper assesses the limitations of the evidence on (i) the neuroprotective effects of bilingualism in Alzheimer's disease and (ii) specific language deficits as markers of Parkinson's disease.

DESIGN

First, we outline the rationale behind each line of research. Second, we review available evidence and discuss the potential impact of cross-linguistic factors. Third, we outline ideas to foster progress in both fields and, with it, in cross-cultural neuroscience at large.

RESULTS

On the one hand, studies on bilingualism suggest that sustained use of more than one language may protect against Alzheimer's disease symptoms. On the other hand, insights from the embodied cognition framework point to syntactic and action-verb deficits as early (and even preclinical) markers of Parkinson's disease. However, both fields share a key limitation that lies at the heart of cultural neuroscience: the issue of cross-linguistic generalizability.

CONCLUSION

Relevant evidence for both research trends comes from only a handful of (mostly Indo-European) languages, which are far from capturing the full scope of structural and typological diversity of the linguistic landscape worldwide. This raises questions on the external validity of reported findings. Greater collaboration between linguistic typology and cognitive neuroscience seems crucial as a first step to assess the impact of transcultural differences on language-related effects across neurodegenerative diseases. Copyright © 2017 John Wiley & Sons, Ltd.

Digital technologies as biomarkers, clinical outcomes assessment, and recruitment tools in Alzheimer's disease clinical trials

Digital technology is transforming the development of drugs for Alzheimer's disease and was the topic of the Alzheimer's Association's Research Roundtable on its May 23–24, 2017 meeting. Research indicates that wearable devices and unobtrusive passive sensors that enable the collection of frequent or continuous, objective, and multidimensional data during daily activities may capture subtle changes in cognition and functional capacity long before the onset of dementia. The potential to exploit these technologies to improve clinical trials as both recruitment and retention tools as well as for potential end points was discussed. The implications for the collection and use of large amounts of data, lessons learned from other related disease areas, ethical concerns raised by these new technologies, and regulatory issues were also covered in the meeting. Finally, the challenges and opportunities of these new technologies for future use were discussed.

Prediction of psychosis across protocols and risk cohorts using automated language analysis

Language and speech are the primary source of data for psychiatrists to diagnose and treat mental disorders. In psychosis, the very structure of language can be disturbed, including semantic coherence (e.g., derailment and tangentiality) and syntactic complexity (e.g., concreteness). Subtle disturbances in language are evident in schizophrenia even prior to first psychosis onset, during prodromal stages. Using computer-based natural language processing analyses, we previously showed that, among English-speaking clinical (e.g., ultra) high-risk youths, baseline reduction in semantic coherence (the flow of meaning in speech) and in syntactic complexity could predict subsequent psychosis onset with high accuracy. Herein, we aimed to cross-validate these automated linguistic analytic methods in a second larger risk cohort, also English-speaking, and to discriminate speech in psychosis from normal speech. We identified an automated machine-learning speech classifier - comprising decreased semantic coherence, greater variance in that coherence, and reduced usage of possessive pronouns - that had an 83% accuracy in predicting psychosis onset (intra-protocol), a cross-validated accuracy of 79% of psychosis onset prediction in the original risk cohort (cross-protocol), and a 72% accuracy in discriminating the speech of recent-onset psychosis patients from that of healthy individuals. The classifier was highly correlated with previously identified manual linguistic predictors. Our findings support the utility and validity of automated natural language processing methods to characterize disturbances in semantics and syntax across stages of psychotic disorder. The next steps will be to apply these methods in larger risk cohorts to further test reproducibility, also in languages other than English, and identify sources of variability. This technology has the potential to improve prediction of psychosis outcome among at-risk youths and identify linguistic targets for remediation and preventive intervention. More broadly, automated linguistic analysis can be a powerful tool for diagnosis and treatment across neuropsychiatry.

A moving story: Whole-body motor training selectively improves the appraisal of action meanings in naturalistic narratives

This study examined whether systematic whole-body stimulation and increased attention to visuospatial motion patterns can enhance the appraisal of action meanings evoked by naturalistic texts. Participants listened to action and neutral (non-action) narratives before and after videogame-based bodily training, and responded to questions on information realized by verbs (denoting abstract and action processes) and circumstances (conveying locative or temporal details, for example). Strategically, we worked with dyslexic children, whose potential comprehension deficits could give room to post-training improvements. Results showed a selective boost in understanding of action information, even when controlling for baseline performance. Also, this effect proved uninfluenced by short-term memory skills, and it was absent when training relied on non-action videogames requiring minimal bodily engagement. Of note, the movements described in the texts did not match those performed by participants, suggesting that well-established effector- and direction-specific language embodiment effects may be accompanied by more coarse-grained sensorimotor resonance, driven by activation of motor and visuospatial sensory systems. In sum, the stimulation of movement-related mechanisms seems to selectively boost the appraisal of actions evoked by naturalistic texts. By demonstrating such links between two real-life activities, our study offers an empirical tie between embodied and situated accounts of cognition.

Impaired Comprehension of Speed Verbs in Parkinson's Disease

OBJECTIVES

A wealth of studies provide evidence for action simulation during language comprehension. Recent research suggests such action simulations might be sensitive to fine-grained information, such as speed. Here, we present a crucial test for action simulation of speed in language by assessing speed comprehension in patients with Parkinson's disease (PD). Based on the patients' motor deficits, we hypothesized that the speed of motion described in language would modulate their performance in semantic tasks. Specifically, they would have more difficulty processing language about relatively fast speed than language about slow speed.

METHODS

We conducted a semantic similarity judgment task on fast and slow action verbs in patients with PD and age-matched healthy controls. Participants had to decide which of two verbs most closely matched a target word.

RESULTS

Compared to controls, PD patients were slower making judgments about fast action verbs, but not for judgments about slow action verbs, suggesting impairment in processing language about fast action. Moreover, this impairment was specific to verbs describing fast action performed with the hand.

CONCLUSIONS

Problems moving quickly lead to difficulties comprehending language about moving quickly. This study provides evidence that speed is an important part of action representations. (JINS, 2017, 23, 412-420).

Unspeakable motion: Selective action-verb impairments in Parkinson's disease patients without mild cognitive impairment

Parkinson's disease (PD) patients show marked impairments in processing action verbs, and to a lesser extent, concrete (specially, manipulable) nouns. However, it is still unclear to what extent deficits in each of these categories are influenced by more general cognitive dysfunctions, and whether they are modulated by the words' implied motility. To examine these issues, we evaluated 49 non-demented PD patients and 49 healthy volunteers in an oral production task. The patients were divided into two groups depending on the presence or absence of mild cognitive impairment (PD-MCI and PD-nMCI, respectively). Participants named pictures of actions varying in motion content (low and high) and of objects varying in manipulability (low and high). The PD-MCI group showed deficits across all four categories. However, PD-nMCI patients exhibited a selective difficulty for high-motion action verbs. This finding corroborates and refines previous results suggesting that disturbances of action-related lexico-semantic information in PD constitute a sui generis alteration manifested early in the course of the disease's physiopathology. Moreover, it suggests that the grounding of action verbs on motor circuits could depend on fine-grained intracategorical semantic distinctions.