Mapping spoken language and cognitive deficits in post-stroke aphasia

Protocol for detection and monitoring of post-stroke cognitive impairment through AI-powered speech analysis: a mixed methods pilot study

Introduction

Post-stroke cognitive impairment (PSCI) affects up to 75% of stroke survivors but remains challenging to detect with traditional neuropsychological assessments. Recent advances in artificial intelligence and natural language processing have opened new avenues for cognitive screening through speech analysis, yet their application to PSCI remains largely unexplored. This study aims to characterize speech markers of PSCI in the first-year post-stroke and evaluate their utility for predicting cognitive outcomes in a Singapore cohort.

Methods

This prospective mixed-methods study will recruit 30 stroke survivors from the Alexandra Hospital and National University Hospital in Singapore. Participants will be assessed at four timepoints: baseline (within 6 weeks of stroke onset), 3-, 6-, and 12-months post-stroke. At each visit, participants will complete the Montreal Cognitive Assessment (MoCA) and a standardized speech protocol comprising picture description and semi-structured conversation tasks. Speech recordings will be automatically transcribed using automated speech recognition (ASR) systems based on pretrained acoustic models, and comprehensive linguistic and acoustic features will be extracted. Machine learning models will be developed to predict MoCA-defined cognitive impairment. Statistical analysis will include correlation analysis between speech features and MoCA scores, as well as machine learning classification and regression models to predict cognitive impairment. Linear mixed-effects models will characterize trajectories of MoCA scores and speech features over time. Qualitative analysis will follow an inductive thematic approach to explore acceptability and usability of speech-based screening.

Discussion

This study represents a critical step toward developing speech-based digital biomarkers for PSCI detection that are sensitive, culturally appropriate, and clinically feasible. If validated, this approach could transform current models of PSCI care by enabling remote, frequent, and naturalistic monitoring of cognitive health, potentially improving outcomes through earlier intervention.

Neural mechanisms driving speech and language recovery following childhood stroke: a scoping review

PURPOSE

This scoping review aimed to inform future research priorities by collating evidence on neural correlates of speech and language recovery following childhood stroke.

METHODS

Neuroimaging, motor speech, or language outcomes following childhood stroke (28 days to 18 years age) in the subacute to chronic community stages (care occurring after acute medical management, including inpatient and outpatient rehabilitation, and community-based programs) were identified and extracted from Medline, Embase, PsycInfo, and Clinical databases.

RESULTS

Of the 3990 studies screened, 11 met the inclusion criteria. Of the included articles, no papers formally assessed speech outcomes, 11 articles reported language outcomes through standardized testing, 11 utilized structural imaging (CT, MRI), and four reported functional neuroimaging outcomes (fMRI).

INTERPRETATION

This review revealed a rudimentary accounting of speech and language profiles in children post-stroke; limited by the use of varied and incomplete speech and language assessment batteries, inconsistent reporting of lesion locations associated with speech and language outcomes, a dearth of functional neuroimaging studies, and lack of information about speech and language function throughout the rehabilitation period, a time when the brain is most plastic and receptive to therapy. Future research should provide complete and accurate accounts of speech and language function and their neural correlates throughout rehabilitation and recovery to inform care, education, and employment planning.

Comparative Efficacy of Cognitive Training for Post-Stroke Aphasia: A Systematic Review and Network Meta-Analysis

BACKGROUND

Although cognitive training has shown potential for treating post-stroke aphasia (PSA), its efficacy varies across studies, and the optimal training approaches remain unclear.

OBJECTIVE

To evaluate and compare the effects of distinct cognitive training interventions, either combined with or independent of speech and language therapy (SLT), on language function in individuals with PSA.

METHODS

A systematic search encompassing PubMed, Embase, Cochrane Library, China National Knowledge Infrastructure, Wanfang, VIP, and Chinese Biomedical Databases was conducted for randomized controlled trials (RCTs). A network meta-analysis evaluated interventions, including computer-assisted cognitive training (CCT), conventional cognitive training (CT), virtual reality (VR)-based cognitive training (vrCT), telerehabilitation computer-assisted cognitive training (tCCT), working memory (WM) training, and attention training (AT).

RESULTS

Eleven RCTs comprising 501 participants were included. Individuals with PSA who underwent combined WM training with SLT led to significantly enhanced Western Aphasia Battery (WAB) Aphasia Quotient (AQ), as well as in spontaneous speech, auditory comprehension, repetition, and naming, compared to those receiving SLT alone. This combination was more effective than both CCT with SLT and tCCT with SLT in improving WAB AQ. Similarly, it outperformed both CCT with SLT and vrCT with SLT in enhancing WAB spontaneous speech. Additionally, both AT and CT combined with SLT were more effective than SLT alone in enhancing WAB spontaneous speech. Specifically, AT combined with SLT proved more effective than vrCT with SLT in this area. Moreover, vrCT combined with SLT significantly improved auditory comprehension compared with SLT alone.

CONCLUSIONS

Combining WM training and SLT and integrating vrCT with SLT both significantly enhance language function in individuals with PSA, compared with SLT alone. Our findings advocate for the use of these cognitive training approaches as promising strategies for language rehabilitation in this population. PROSPERO registration number: CRD42023462361.

Quantifier processing and semantic flexibility in patients with aphasia

Processing of quantifiers such as "many" and "few" relies on number knowledge, linguistic abilities, and working memory. Negative quantifiers (e.g., "few," "less than half") induce higher processing costs than their positive counterparts. Furthermore, the meaning of some quantifiers is flexible and thus adaptable. Importantly, in neurotypical individuals, changing the meaning of one quantifier also leads to a generalized change in meaning for its polar opposite (e.g., the change of the meaning of "many" leads to the change of that of "few"). Here, we extended this research to patients with fluent and non-fluent aphasia after stroke. In two experiments, participants heard sentences of the type "Many/few of the circles are yellow/blue," each followed by a picture with different quantities of blue and yellow circles. The participants judged whether the sentence adequately described the picture. Each experiment consisted of three blocks: a baseline block to assess the participants' criteria for both quantifiers, a training block to shift the criteria for "many," and a test block, identical to the baseline to capture any changes in quantifier semantics. In Experiment 1, the change of the meaning of "many" was induced by using adaptation to small numbers (20-50%) of circles of the named color. In Experiment 2, explicit feedback was given in the training block after each response to rate proportions of 40% (or higher) as "many," whereas 40% is normally rather rated as "few." The objective was to determine whether people with fluent or non-fluent aphasia were able to process quantifiers appropriately and whether generalized semantic flexibility was present after brain damage. Sixteen out of 21 patients were able to perform the task. People with fluent aphasia showed the expected polarity effect in the reaction times and shifted their criteria for "many" with generalization to the untrained quantifier "few." This effect, however, was only obtained after explicit feedback (Experiment 2) but not by mere adaptation (Experiment 1). In contrast, people with non-fluent aphasia did not change the quantifier semantics in either experiment. This study contributes to gaining new insights into quantifier processing and semantic flexibility in people with aphasia and general underlying processing mechanisms.

Survey on diagnosis of post-brain injury "higher brain dysfunction" in patients with cognitive impairment. Family/caregiver response

In Japan, the diagnostic criteria for the higher brain dysfunction (HBD) emerged in 2005 in response to social needs for support for the patients and their families. The issue of cognitive dysfunction after brain trauma is not unique to Japan. The purpose of this study was to reveal the current status of family members of HBD patients from their perspective, focusing on the changes before and after the establishment of diagnostic criteria in Japan. We conducted a questionnaire survey for family members supporting the HBD patients. The questionnaire included the causative condition, explanation on HBD by health professionals, and problems/difficulties they encountered. This research involved family members of 278 HBD cases (males = 211, age 49 years). The major underlying cause was head injury (n = 139). Compared to patients diagnosed pre-2005, a significantly larger proportion of family members after 2005 received information on the condition during the acute phase (within one month) (p < 0.001), including that from physicians (p < 0.001). Nearly half of the families cited a lack of awareness of HBD among the professionals as a problem. In Japan, awareness of HBD in the society is gradually increasing especially after the current diagnostic criteria were implemented, and there has been a steady increase over time in early diagnosis. Yet, there still remain those not appropriately diagnosed. To salvage those patients and the families left behind, we are suggesting several recommendations to further augment clinical practice and the healthcare systems in Japan.

Neuropsychological and Anatomical-Functional Effects of Transcranial Magnetic Stimulation in Post-Stroke Patients with Cognitive Impairment and Aphasia: A Systematic Review

Transcranial magnetic stimulation (TMS) has been found to be promising in the neurorehabilitation of post-stroke patients. Aphasia and cognitive impairment (CI) are prevalent post-stroke; however, there is still a lack of consensus about the characteristics of interventions based on TMS and its neuropsychological and anatomical-functional benefits. Therefore, studies that contribute to creating TMS protocols for these neurological conditions are necessary. To analyze the evidence of the neuropsychological and anatomical-functional TMS effects in post-stroke patients with CI and aphasia and determine the characteristics of the most used TMS in research practice. The present study followed the PRISMA guidelines and included articles from PubMed, Scopus, Web of Science, ScienceDirect, and EMBASE databases, published between January 2010 and March 2023. In the 15 articles reviewed, it was found that attention, memory, executive function, language comprehension, naming, and verbal fluency (semantic and phonological) are the neuropsychological domains that improved post-TMS. Moreover, TMS in aphasia and post-stroke CI contribute to greater frontal activation (in the inferior frontal gyrus, pars triangularis, and opercularis). Temporoparietal effects were also found. The observed effects occur when TMS is implemented in repetitive modality, at a frequency of 1 Hz, in sessions of 30 min, and that last more than 2 weeks in duration. The use of TMS contributes to the neurorehabilitation process in post-stroke patients with CI and aphasia. However, it is still necessary to standardize future intervention protocols based on accurate TMS characteristics.

Longitudinal neuropsychological performance of post-stroke adults with and without rehabilitation

This study compared the neuropsychological performance of two post-stroke groups, one undergoing rehabilitation and the other not receiving any intervention, on the acute and chronic stroke phases, and explored sociodemographic and neurological variables associated with changes in performance over time. Sixty-three adults underwent neuropsychological assessment with the Cognitive Screening Instrument (TRIACOG) less than thirty days after having a stroke and were reassessed three to six months after stroke. Thirty-eight participants did not undertake rehabilitation and twenty-five did physiotherapy and/or speech therapy between the two time points. The frequency of cognitive deficits (between groups) and the range of cognitive assessment scores over time (between and within groups) were analyzed. There was a significant decrease in the frequency of neuropsychological deficits and improvement on neuropsychological assessment scores over time only in the group undergoing rehabilitation. Severity of the neurological condition, years of education and being in rehabilitation explained the longitudinal changes in several cognitive domains measured by TRIACOG. Engaging in rehabilitation within three to six months post-stroke is crucial for enhancing the recovery of neuropsychological deficits. Cognitive screening instruments like TRIACOG can be used by health professionals to identify stroke-related neuropsychological changes and plan interventions.