Machine learning in the clinical and language characterisation of primary progressive aphasia variants

The neurobiology of sentence production: A narrative review and meta-analysis

Although there is a sizeable body of literature on sentence comprehension and processing both in healthy and disordered language users, the literature on sentence production remains much more sparse. Linguistic and computational descriptions of expressive syntactic deficits in aphasia are especially rare. In addition, the neuroimaging and (psycho) linguistic literatures operate largely separately. In this paper, I will first lay out the theoretical lay of the land with regard to psycholinguistic models of sentence production. I will then provide a brief narrative overview and large-scale meta-analysis of the neuroimaging literature as it pertains to syntactic computation, followed by an attempt to integrate the psycholinguistic models with the findings from functional and clinical neuroimaging. Finally, I provide a brief overview of the literature surrounding expressive syntactic deficits and propose a path forward to close some of the existing gaps.

The use of low-density EEG for the classification of PPA and MCI

Objective

Dissociating Primary Progressive Aphasia (PPA) from Mild Cognitive Impairment (MCI) is an important, yet challenging task. Given the need for low-cost and time-efficient classification, we used low-density electroencephalography (EEG) recordings to automatically classify PPA, MCI and healthy control (HC) individuals. To the best of our knowledge, this is the first attempt to classify individuals from these three populations at the same time.

Methods

We collected three-minute EEG recordings with an 8-channel system from eight MCI, fourteen PPA and eight HC individuals. Utilizing the Relative Wavelet Entropy method, we derived (i) functional connectivity, (ii) graph theory metrics and extracted (iii) various energy rhythms. Features from all three sources were used for classification. The k-Nearest Neighbor and Support Vector Machines classifiers were used.

Results

A 100% individual classification accuracy was achieved in the HC-MCI, HC-PPA, and MCI-PPA comparisons, and a 77.78% accuracy in the HC-MCI-PPA comparison.

Conclusion

We showed for the first time that successful automatic classification between HC, MCI and PPA is possible with short, low-density EEG recordings. Despite methodological limitations of the current study, these results have important implications for clinical practice since they show that fast, low-cost and accurate disease diagnosis of these disorders is possible. Future studies need to establish the generalizability of the current findings with larger sample sizes and the efficient use of this methodology in a clinical setting.

Data-driven prediction of regional brain metabolism using neuropsychological assessment in Alzheimer's disease and behavioral variant Frontotemporal dementia

BACKGROUND

This study aimed to evaluate the capacity of neuropsychological assessment to predict the regional brain metabolism in a cohort of patients with amnestic Alzheimer's disease (AD) and behavioral variant frontotemporal dementia (bvFTD) using Machine Learning algorithms.

METHODS

We included 360 subjects, consisting of 186 patients with AD, 87 with bvFTD, and 87 cognitively healthy controls. All participants underwent a neuropsychological assessment using the Addenbrooke's Cognitive Examination and the Neuronorma battery, in addition to [18F]-fluorodeoxyglucose positron emission tomography (FDG-PET) imaging. We trained Machine Learning algorithms, including artificial neural networks (ANN) and models that incorporate genetic algorithms (GAs), to predict the presence of regional hypometabolism in FDG-PET imaging based on cognitive testing results.

RESULTS

The proposed models demonstrated the ability to predict hypometabolism trends with approximately 70% accuracy in key regions associated with AD and bvFTD. In addition, we showed that incorporating neuropsychological tests provided relevant information for predicting brain hypometabolism. The temporal lobe was the best-predicted region, followed by the parietal, frontal, and some areas in the occipital lobe. Diagnosis played a significant role in the estimation of hypometabolism, and several neuropsychological tests were identified as the most important predictors for different brain regions. In our experiments, classical Machine Learning models, such as support vector machines enhanced by a preliminary feature selection step using GAs outperformed ANNs.

CONCLUSIONS

A successful prediction of regional brain metabolism of patients with AD and bvFTD was achieved based on the results of neuropsychological examination and Machine Learning algorithms. These findings support the neurobiological validity of neuropsychological examination and the feasibility of a topographical diagnosis in patients with neurodegenerative disorders.

Functional correlates of executive dysfunction in primary progressive aphasia: a systematic review

Introduction

Recent research has recognized executive dysfunction as another component affected in Primary Progressive Aphasia (PPA). This systematic review aimed to examine what information distinctive neurophysiological markers can provide in the evaluation of executive function (EF) deficits in PPA, and to what effect executive function deficits can be assessed through the characteristics of functional markers.

Methods

We conducted a systematic literature search following the PRISMA guidelines across studies that employed neuropsychological assessments and neurophysiological imaging techniques (EEG, MEG; PET, SPECT, fMRI, fNIRS) to investigate executive dysfunction correlates in PPA.

Results

Findings from nine articles including a total number of 111 individuals with PPA met our inclusion criteria and were synthesized. Although research on the neural correlates of EF deficits is scarce, MEG studies revealed widespread oscillatory slowing, with increased delta and decreased alpha power, where alterations in alpha, theta, and beta activities were significant predictors of executive function deficits. PET findings demonstrated significant correlations between executive dysfunction and hypometabolism in frontal brain regions. fMRI results indicated elevated homotopic connectivity in PPA patients, with a broader and more anterior distribution of abnormal hippocampal connections of which were associated with reduced executive performance.

Conclusion

Our study provides indirect support for the assumption regarding the significance of the frontal regions and inferior frontal junction in executive control and demonstrates that neurophysiological tools can be a useful aid to further investigate clinical-neurophysiological correlations in PPA.

AI-assisted assessment and treatment of aphasia: a review

Aphasia is a language disorder caused by brain injury that often results in difficulties with speech production and comprehension, significantly impacting the affected individuals' lives. Recently, artificial intelligence (AI) has been advancing in medical research. Utilizing machine learning and related technologies, AI develops sophisticated algorithms and predictive models, and can employ tools such as speech recognition and natural language processing to autonomously identify and analyze language deficits in individuals with aphasia. These advancements provide new insights and methods for assessing and treating aphasia. This article explores current AI-supported assessment and treatment approaches for aphasia and highlights key application areas. It aims to uncover how AI can enhance the process of assessment, tailor therapeutic interventions, and track the progress and outcomes of rehabilitation efforts. The article also addresses the current limitations of AI's application in aphasia and discusses prospects for future research.

Advances in semantic dementia: Neuropsychology, pathology & neuroimaging

Semantic dementia is a kind of neurodegenerative disorder, characterized by prominent semantic impairments and anterior temporal lobe atrophy. Since 2010, more studies have devoted to this rare disorder, revealing that it is more complex than we think. Clinical advances include more specific findings of semantic impairments and other higher order cognitive deficits. Neuroimaging techniques can help revealing the different brain networks affected (both structurally and functionally) in this condition. Pathological and genetic studies have also found more complex situations of semantic dementia, which might explain the huge variance existing in semantic dementia. Moreover, the current diagnosis criteria mainly focus on semantic dementia's classical prototype. We further delineated the features of three subtypes of semantic dementia based on atrophy lateralization with three severity stages. In a broader background, as a part of the continuum of neurodegenerative disorders, semantic dementia is commonly compared with other resembling conditions. Therefore, we summarized the differential diagnosis between semantic dementia and them. Finally, we introduced the challenges and achievements of its diagnosis, treatment, care and cross cultural comparison. By providing a comprehensive picture of semantic dementia on different aspects of advances, we hope to deepen the understanding of semantic dementia and promote more inspirations on both clinical and theoretical studies about it.

Clinical dimensions along the non-fluent variant primary progressive aphasia spectrum

It is debated whether primary progressive apraxia of speech (PPAOS) and progressive agrammatic aphasia (PAA) belong to the same clinical spectrum, traditionally termed non-fluent/agrammatic variant primary progressive aphasia (nfvPPA), or exist as two completely distinct syndromic entities with specific pathologic/prognostic correlates. We analysed speech, language and disease severity features in a comprehensive cohort of patients with progressive motor speech impairment and/or agrammatism to ascertain evidence of naturally occurring, clinically meaningful non-overlapping syndromic entities (e.g. PPAOS and PAA) in our data. We also assessed if data-driven latent clinical dimensions with aetiologic/prognostic value could be identified. We included 98 participants, 43 of whom had an autopsy-confirmed neuropathological diagnosis. Speech pathologists assessed motor speech features indicative of dysarthria and apraxia of speech (AOS). Quantitative expressive/receptive agrammatism measures were obtained and compared with healthy controls. Baseline and longitudinal disease severity was evaluated using the Clinical Dementia Rating Sum of Boxes (CDR-SB). We investigated the data's clustering tendency and cluster stability to form robust symptom clusters and employed principal component analysis to extract data-driven latent clinical dimensions (LCD). The longitudinal CDR-SB change was estimated using linear mixed-effects models. Of the participants included in this study, 93 conformed to previously reported clinical profiles (75 with AOS and agrammatism, 12 PPAOS and six PAA). The remaining five participants were characterized by non-fluent speech, executive dysfunction and dysarthria without apraxia of speech or frank agrammatism. No baseline clinical features differentiated between frontotemporal lobar degeneration neuropathological subgroups. The Hopkins statistic demonstrated a low cluster tendency in the entire sample (0.45 with values near 0.5 indicating random data). Cluster stability analyses showed that only two robust subgroups (differing in agrammatism, executive dysfunction and overall disease severity) could be identified. Three data-driven components accounted for 71% of the variance [(i) severity-agrammatism; (ii) prominent AOS; and (iii) prominent dysarthria]. None of these data-driven LCDs allowed an accurate prediction of neuropathology. The severity-agrammatism component was an independent predictor of a faster CDR-SB increase in all the participants. Higher dysarthria severity, reduced words per minute and expressive and receptive agrammatism severity at baseline independently predicted accelerated disease progression. Our findings indicate that PPAOS and PAA, rather than exist as completely distinct syndromic entities, constitute a clinical continuum. In our cohort, splitting the nfvPPA spectrum into separate clinical phenotypes did not improve clinical-pathological correlations, stressing the need for new biological markers and consensus regarding updated terminology and clinical classification.

From concept to practice: a scoping review of the application of AI to aphasia diagnosis and management

PURPOSE

Aphasia is an acquired communication disability resulting from impairments in language processing following brain injury, most commonly stroke. People with aphasia experience difficulties in all modalities of language that impact their quality of life. Therefore, researchers have investigated the use of Artificial Intelligence (AI) to deliver innovative solutions in Aphasia management and rehabilitation.

MATERIALS AND METHODS

We conducted a scoping review of the use of AI in aphasia research and rehabilitation to explore the evolution of AI applications to aphasia, the progression of technologies and applications. Furthermore, we aimed to identify gaps in the use of AI in Aphasia to highlight the potential areas where AI might add value. We analysed 77 studies to determine the research objectives, the history of AI techniques in Aphasia and their progression over time.

RESULTS

Most of the studies focus on automated assessment using AI, with recent studies focusing on AI for therapy and personalised assistive systems. Starting from prototypes and simulations, the use of AI has progressed to include supervised machine learning, unsupervised machine learning, natural language processing, fuzzy rules, and genetic programming.

CONCLUSION

Considerable scope remains to align AI technology with aphasia rehabilitation to empower patient-centred, customised rehabilitation and enhanced self-management.

Heterogeneity and overlap in the continuum of linguistic profile of logopenic and semantic variants of primary progressive aphasia: a Profile Analysis based on Multidimensional Scaling study

BACKGROUND

Primary progressive aphasia (PPA) diagnostic criteria underestimate the complex presentation of semantic (sv) and logopenic (lv) variants, in which symptoms partially overlap, and mixed clinical presentation (mixed-PPA) and heterogenous profile (lvPPA +) are frequent. Conceptualization of similarities and differences of these clinical conditions is still scarce.

METHODS

Lexical, semantic, phonological, and working memory errors from nine language tasks of sixty-seven PPA were analyzed using Profile Analysis based on Multidimensional Scaling, which allowed us to create a distributed representation of patients' linguistic performance in a shared space. Patients had been studied with [18F] FDG-PET. Correlations were performed between metabolic and behavioral data.

RESULTS

Patients' profiles were distributed across a continuum. All PPA, but two, presented a lexical retrieval impairment, in terms of reduced production of verbs and nouns. svPPA patients occupied a fairly clumped space along the continuum, showing a preponderant semantic deficit, which correlated to fusiform gyrus hypometabolism, while only few presented working memory deficits. Adjacently, lvPPA + presented a semantic impairment combined with phonological deficits, which correlated with metabolism in the anterior fusiform gyrus and posterior middle temporal gyrus. Starting from the shared phonological deficit side, a large portion of the space was occupied by all lvPPA, showing a combination of phonological, lexical, and working memory deficits, with the latter correlating with posterior temporo-parietal hypometabolism. Mixed PPA did not show unique profile, distributing across the space.

DISCUSSION

Different clinical PPA entities exist but overlaps are frequent. Identifying shared and unique clinical markers is critical for research and clinical practice. Further research is needed to identify the role of genetic and pathological factors in such distribution, including also higher sample size of less represented groups.

Assessing processing speed and its neural correlates in the three variants of primary progressive aphasia with a non-verbal tablet-based task

Prior research has revealed distinctive patterns of impaired language abilities across the three variants of Primary Progressive Aphasia (PPA): nonfluent/agrammatic (nfvPPA), logopenic (lvPPA) and semantic (svPPA). However, little is known about whether, and to what extent, non-verbal cognitive abilities, such as processing speed, are impacted in PPA patients. This is because neuropsychological tests typically contain linguistic stimuli and require spoken output, being therefore sensitive to verbal deficits in aphasic patients. The aim of this study is to investigate potential differences in processing speed between PPA patients and healthy controls, and among the three PPA variants, using a brief non-verbal tablet-based task (Match) modeled after the WAIS-III digit symbol coding test, and to determine its neural correlates. Here, we compared performance on the Match task between PPA patients (n = 61) and healthy controls (n = 59) and across the three PPA variants. We correlated performance on Match with voxelwise gray and white matter volumes. We found that lvPPA and nfvPPA patients performed significantly worse on Match than healthy controls and svPPA patients. Worse performance on Match across PPA patients was associated with reduced gray matter volume in specific parts of the left middle frontal gyrus, superior parietal lobule, and precuneus, and reduced white matter volume in the left parietal lobe. To conclude, our behavioral findings reveal that processing speed is differentially impacted across the three PPA variants and provide support for the potential clinical utility of a tabled-based task (Match) to assess non-verbal cognition. In addition, our neuroimaging findings confirm the importance of a set of fronto-parietal regions that previous research has associated with processing speed and executive control. Finally, our behavioral and neuroimaging findings combined indicate that differences in processing speed are largely explained by the unequal distribution of atrophy in these fronto-parietal regions across the three PPA variants.

Primary progressive aphasia: six questions in search of an answer

Here, we review recent progress in the diagnosis and management of primary progressive aphasia-the language-led dementias. We pose six key unanswered questions that challenge current assumptions and highlight the unresolved difficulties that surround these diseases. How many syndromes of primary progressive aphasia are there-and is syndromic diagnosis even useful? Are these truly 'language-led' dementias? How can we diagnose (and track) primary progressive aphasia better? Can brain pathology be predicted in these diseases? What is their core pathophysiology? In addition, how can primary progressive aphasia best be treated? We propose that pathophysiological mechanisms linking proteinopathies to phenotypes may help resolve the clinical complexity of primary progressive aphasia, and may suggest novel diagnostic tools and markers and guide the deployment of effective therapies.

The neural substrates of transdiagnostic cognitive-linguistic heterogeneity in primary progressive aphasia

BACKGROUND

Clinical variants of primary progressive aphasia (PPA) are diagnosed based on characteristic patterns of language deficits, supported by corresponding neural changes on brain imaging. However, there is (i) considerable phenotypic variability within and between each diagnostic category with partially overlapping profiles of language performance between variants and (ii) accompanying non-linguistic cognitive impairments that may be independent of aphasia magnitude and disease severity. The neurobiological basis of this cognitive-linguistic heterogeneity remains unclear. Understanding the relationship between these variables would improve PPA clinical/research characterisation and strengthen clinical trial and symptomatic treatment design. We address these knowledge gaps using a data-driven transdiagnostic approach to chart cognitive-linguistic differences and their associations with grey/white matter degeneration across multiple PPA variants.

METHODS

Forty-seven patients (13 semantic, 15 non-fluent, and 19 logopenic variant PPA) underwent assessment of general cognition, errors on language performance, and structural and diffusion magnetic resonance imaging to index whole-brain grey and white matter changes. Behavioural data were entered into varimax-rotated principal component analyses to derive orthogonal dimensions explaining the majority of cognitive variance. To uncover neural correlates of cognitive heterogeneity, derived components were used as covariates in neuroimaging analyses of grey matter (voxel-based morphometry) and white matter (network-based statistics of structural connectomes).

RESULTS

Four behavioural components emerged: general cognition, semantic memory, working memory, and motor speech/phonology. Performance patterns on the latter three principal components were in keeping with each variant's characteristic profile, but with a spectrum rather than categorical distribution across the cohort. General cognitive changes were most marked in logopenic variant PPA. Regardless of clinical diagnosis, general cognitive impairment was associated with inferior/posterior parietal grey/white matter involvement, semantic memory deficits with bilateral anterior temporal grey/white matter changes, working memory impairment with temporoparietal and frontostriatal grey/white matter involvement, and motor speech/phonology deficits with inferior/middle frontal grey matter alterations.

CONCLUSIONS

Cognitive-linguistic heterogeneity in PPA closely relates to individual-level variations on multiple behavioural dimensions and grey/white matter degeneration of regions within and beyond the language network. We further show that employment of transdiagnostic approaches may help to understand clinical symptom boundaries and reveal clinical and neural profiles that are shared across categorically defined variants of PPA.

Characterizing phonemic fluency by transfer learning with deep language models

Though phonemic fluency tasks are traditionally indexed by the number of correct responses, the underlying disorder may shape the specific choice of words-both correct and erroneous. We report the first comprehensive qualitative analysis of incorrect and correct words generated on the phonemic ('S') fluency test, in a large sample of patients (n = 239) with focal, unilateral frontal or posterior lesions and healthy controls (n = 136). We conducted detailed qualitative analyses of the single words generated in the phonemic fluency task using categorical descriptions for different types of errors, low-frequency words and clustering/switching. We further analysed patients' and healthy controls' entire sequences of words by employing stochastic block modelling of Generative Pretrained Transformer 3-based deep language representations. We conducted predictive modelling to investigate whether deep language representations of word sequences improved the accuracy of detecting the presence of frontal lesions using the phonemic fluency test. Our qualitative analyses of the single words generated revealed several novel findings. For the different types of errors analysed, we found a non-lateralized frontal effect for profanities, left frontal effects for proper nouns and permutations and a left posterior effect for perseverations. For correct words, we found a left frontal effect for low-frequency words. Our novel large language model-based approach found five distinct communities whose varied word selection patterns reflected characteristic demographic and clinical features. Predictive modelling showed that a model based on Generative Pretrained Transformer 3-derived word sequence representations predicted the presence of frontal lesions with greater fidelity than models of native features. Our study reveals a characteristic pattern of phonemic fluency responses produced by patients with frontal lesions. These findings demonstrate the significant inferential and diagnostic value of characterizing qualitative features of phonemic fluency performance with large language models and stochastic block modelling.

Speech Motor Profiles in Primary Progressive Aphasia

PURPOSE

Previous research on motor speech disorders (MSDs) in primary progressive aphasia (PPA) has largely focused on patients with the nonfluent/agrammatic variant of PPA (nfvPPA), with few systematic descriptions of MSDs in variants other than nfvPPA. There has also been an emphasis on studying apraxia of speech, whereas less is known about dysarthria or other forms of MSDs. This study aimed to examine the qualitative and quantitative characteristics of MSDs in a prospective sample of individuals with PPA independent of subtype.

METHOD

We included 38 participants with a root diagnosis of PPA according to current consensus criteria, including one case with primary progressive apraxia of speech. Speech tasks comprised various speech modalities and levels of complexity. Expert raters used a novel protocol for auditory speech analyses covering all major dimensions of speech.

RESULTS

Of the participants, 47.4% presented with some form of MSD. Individual speech motor profiles varied widely with respect to the different speech dimensions. Besides apraxia of speech, we observed different dysarthria syndromes, special forms of MSDs (e.g., neurogenic stuttering), and mixed forms. Degrees of severity ranged from mild to severe. We also observed MSDs in patients whose speech and language profiles were incompatible with nfvPPA.

CONCLUSIONS

The results confirm that MSDs are common in PPA and can manifest in different syndromes. The findings emphasize that future studies of MSDs in PPA should be extended to all clinical variants and should take into account the qualitative characteristics of motor speech dysfunction across speech dimensions.

SUPPLEMENTAL MATERIAL

https://doi.org/10.23641/asha.22555534.

Evaluating Fluency in Aphasia: Fluency Scales, Trichotomous Judgements, or Machine Learning

Background

Speech-language pathologists (SLPs) and other clinicians often use aphasia batteries, such as the Western Aphasia Battery-Revised (WAB-R), to evaluate both severity and classification of aphasia. However, the fluency scale on the WAB-R is not entirely objective and has been found to have less than ideal inter-rater reliability, due to variability in weighing the importance of one dimension (e.g. articulatory effort or grammaticality) over another. This limitation has implications for aphasia classification. The subjectivity might be mitigated through the implementation of machine learning to identify fluent and non-fluent speech.

Aims

We hypothesized that two models consisting of convolutional and recurrent neural networks can be used to identify fluent and non-fluent aphasia as judged by SLPs, with greater reliability than use of the WAB-R fluency scale.

Methods & Procedures

The training and testing dataset for the networks was collected from the public domain, and the validation dataset was collected from participants in post-stroke aphasia studies. We used Kappa scores to evaluate inter-rater reliability among SLPs, and between the networks and SLPs.

Outcome and Results

Using public domain samples, the model for detecting non-fluent aphasia achieved high accuracy on the training dataset after 10 epochs (i.e., when algorithm scans the entire dataset) and 81% testing accuracy using public domain samples. The model for detecting fluent speech had high training accuracy and 83% testing. Across samples, using the WAB-R fluency scale, there was poor to perfect agreement among SLPs on the precise WAB-R fluency score, but substantial agreement on non-fluent (score 0-4) versus fluent (score of 5-9). The agreement between the model and the SLPs was moderate for identifying non-fluent speech and substantial fpr identifying fluent speech. When SLPs were asked to identify each sample as fluent, non-fluent, or mixed (without using the fluency scale), the agreement between SLPs was almost perfect (Kappa 0.94). The agreement between the SLPs' trichotomous judgement and the models was fair for detecting non-fluent speech and substantial for detecting fluent speech.

Conclusions

Results indicate that neither the WAB-R fluency scale nor the machine learning algorithms were as useful (reliable and valid) as a simple trichotomous judgement of fluent, non-fluent, or mixed by SLPs. These results, together with data from the literature, indicate that it is time to re-consider use of the WAB-R fluency scale for classification of aphasia. It is also premature, at present, to rely on machine learning to rate spoken language fluency.

Characterization of the logopenic variant of Primary Progressive Aphasia: A systematic review and meta-analysis

The linguistic and anatomical variability of the logopenic variant of Primary Progressive Aphasia (lv-PPA) as defined by current diagnostic criteria has been the topic of an intense debate. The present review and meta-analysis aims at characterizing the profile of lv-PPA, by a comprehensive analysis of the available literature on the neuropsychological, neuroimaging, electrophysiological, pathological, and genetic features of lv-PPA. We conducted a systematic bibliographic search, leading to the inclusion of 207 papers. Of them, 12 were used for the Anatomical Likelihood Estimation meta-analysis on grey matter revealed by magnetic resonance imaging data. The results suggest that the current guidelines outline a relatively consistent syndrome, characterized by a core set of linguistic and, to a lesser extent, non-linguistic deficits, mirroring the involvement of left temporal and parietal regions typically affected by Alzheimer Disease pathology. Variations of the lv-PPA profile are discussed in terms of heterogeneity of the neuropsychological instruments and the diagnostic criteria adopted.

A Telemedicine Platform for Aphasia: Protocol for a Development and Usability Study

BACKGROUND

Aphasia is a central disorder of comprehension and expression of language that cannot be attributed to a peripheral sensory deficit or a peripheral motor disorder. The diagnosis and treatment of aphasia are complex. Interventions that facilitate this process can lead to an increase in the number of assisted patients and greater precision in the therapeutic choice by the health professional.

OBJECTIVE

This paper describes a protocol for a study that aims to implement a computer-based solution (ie, a telemedicine platform) that uses deep learning to classify vocal data from participants with aphasia and to develop serious games to treat aphasia. Additionally, this study aims to evaluate the usability and user experience of the proposed solution.

METHODS

Our interactive and smart platform will be developed to provide an alternative option for professionals and their patients with aphasia. We will design 2 serious games for aphasia rehabilitation and a deep learning-driven computational solution to aid diagnosis. A pilot evaluation of usability and user experience will reveal user satisfaction with platform features.

RESULTS

Data collection began in June 2022 and is currently ongoing. Results of system development as well as usability should be published by mid-2023.

CONCLUSIONS

This research will contribute to the treatment and diagnosis of aphasia by developing a telemedicine platform based on a co-design process. Therefore, this research will provide an alternative method for health care to patients with aphasia. Additionally, it will guide further studies with the same purpose.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/40603.

Logogenic Primary Progressive Aphasia or Alzheimer Disease: Contribution of Acoustic Markers in Early Differential Diagnosis

The logopenic variant of Primary Progressive Aphasia (lvPPA), a syndromic disorder centered on language impairment, often presents variable underlying neurodegenerative pathologies such as Alzheimer Disease (AD). Actual language assessment tests and lumbar puncture, focused on AD diagnosis, cannot precisely distinguish the symptoms, or predict their progression at onset time. We analyzed acoustic markers, aiming to discriminate lvPPA and AD as well as the influence of AD biomarkers on acoustic profiles at the beginning of the disease. We recruited people with AD (n = 8) and with lvPPA (n = 8), with cerebrospinal fluid biomarker profiles determined by lumbar puncture. The participants performed a sentence repetition task that allows assessing potential lvPPA phonological loop deficits. We found that temporal and prosodic markers significantly differentiate the lvPPA and AD group at an early stage of the disease. Biomarker and acoustic profile comparisons discriminated the two lvPPA subgroups according to their biomarkers. For lvPPA with AD biomarkers, acoustic profile equivalent to an atypical AD form with a specific alteration of the phonological loop is shown. However, lvPPA without AD biomarkers has an acoustic profile approximating the one for DLFT. Therefore, these results allow us to classify lvPPA differentially from AD based on acoustic markers from a sentence repetition task. Furthermore, our results suggest that acoustic analysis would constitute a clinically efficient alternative to refused lumbar punctures. It offers the possibility to facilitate early, specific, and accessible neurodegenerative diagnosis and may ease early care with speech therapy, preventing the progression of symptoms.

Machine-learning based approach to predict anti-CGRP response in patients with migraine: multicenter Spanish study

BACKGROUND

To date, several variables have been associated with anti-CGRP receptor or ligand-antibody response with disparate results. Our objective is to determine whether machine learning (ML)-based models can predict 6, 9 and 12 months response to anti-CGRP receptor or ligand therapies among migraine patients.

METHODS

We performed a multicenter analysis of a prospectively collected data cohort of patients with migraine receiving anti-CGRP therapies. Demographic and clinical variables were collected. Response rate defined in the 30% to 50% range -or at least 30%-, in the 50% to 75% range -or at least 50%-, and response rate over 75% reduction in the number of headache days per month at 6, 9 and 12 months. A sequential forward feature selector was used for variable selection and ML-based predictive models response to anti-CGRP therapies at 6, 9 and 12 months, with models' accuracy not less than 70%, were generated.

RESULTS

A total of 712 patients were included, 93% women, aged 48 years (SD=11.7). Eighty-three percent had chronic migraine. ML models using headache days/month, migraine days/month and HIT-6 variables yielded predictions with a F1 score range of 0.70-0.97 and AUC (area under the receiver operating curve) score range of 0.87-0.98. SHAP (SHapley Additive exPlanations) summary plots and dependence plots were generated to evaluate the relevance of the factors associated with the prediction of the above-mentioned response rates.

CONCLUSIONS

According to our study, ML models can predict anti-CGRP response at 6, 9 and 12 months. This study provides a predictive tool to be used in a real-world setting.

Genetic Algorithms for Optimized Diagnosis of Alzheimer's Disease and Frontotemporal Dementia Using Fluorodeoxyglucose Positron Emission Tomography Imaging

Genetic algorithms have a proven capability to explore a large space of solutions, and deal with very large numbers of input features. We hypothesized that the application of these algorithms to 18F-Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) may help in diagnosis of Alzheimer's disease (AD) and Frontotemporal Dementia (FTD) by selecting the most meaningful features and automating diagnosis. We aimed to develop algorithms for the three main issues in the diagnosis: discrimination between patients with AD or FTD and healthy controls (HC), differential diagnosis between behavioral FTD (bvFTD) and AD, and differential diagnosis between primary progressive aphasia (PPA) variants. Genetic algorithms, customized with K-Nearest Neighbor and BayesNet Naives as the fitness function, were developed and compared with Principal Component Analysis (PCA). K-fold cross validation within the same sample and external validation with ADNI-3 samples were performed. External validation was performed for the algorithms distinguishing AD and HC. Our study supports the use of FDG-PET imaging, which allowed a very high accuracy rate for the diagnosis of AD, FTD, and related disorders. Genetic algorithms identified the most meaningful features with the minimum set of features, which may be relevant for automated assessment of brain FDG-PET images. Overall, our study contributes to the development of an automated, and optimized diagnosis of neurodegenerative disorders using brain metabolism.

Identification of the main components of spontaneous speech in primary progressive aphasia and their neural underpinnings using multimodal MRI and FDG-PET imaging

BACKGROUND

Primary progressive aphasia (PPA) is a clinical syndrome characterized by gradual loss of language skills. This study aimed to evaluate the diagnostic capacity of a connected speech task for the diagnosis of PPA and its variants, to determine the main components of spontaneous speech, and to examine their neural correlates.

METHODS

A total of 118 participants (31 patients with nfvPPA, 11 with svPPA, 45 with lvPPA, and 31 healthy controls) were evaluated with the Cookie Theft picture description task and a comprehensive language assessment protocol. Patients also underwent ¹⁸F-fluorodeoxyglucose positron emission tomography and magnetic resonance imaging studies. Principal component analysis and machine learning were used to evaluate the main components of connected speech and the accuracy of connected speech parameters for diagnosing PPA. Voxel-based analyses were conducted to evaluate the correlation between spontaneous speech components and brain metabolism, brain volumes, and white matter microstructure.

RESULTS

Discrimination between patients with PPA and controls was 91.67%, with 77.78% discrimination between PPA variants. Parameters related to speech rate and lexical variables were the most discriminative for classification. Three main components were identified: lexical features, fluency, and syntax. The lexical component was associated with ventrolateral frontal regions, while the fluency component was associated with the medial superior prefrontal cortex. Number of pauses was more related with the left parietotemporal region, while pauses duration with the bilateral frontal lobe. The lexical component was correlated with several tracts in the language network (left frontal aslant tract, left superior longitudinal fasciculus I, II, and III, left arcuate fasciculus, and left uncinate fasciculus), and fluency was linked to the frontal aslant tract.

CONCLUSION

Spontaneous speech assessment is a useful, brief approach for the diagnosis of PPA and its variants. Neuroimaging correlates suggested a subspecialization within the left frontal lobe, with ventrolateral regions being more associated with lexical production and the medial superior prefrontal cortex with speech rate.

Application of Machine Learning to Electroencephalography for the Diagnosis of Primary Progressive Aphasia: A Pilot Study

Background. Primary progressive aphasia (PPA) is a neurodegenerative syndrome in which diagnosis is usually challenging. Biomarkers are needed for diagnosis and monitoring. In this study, we aimed to evaluate Electroencephalography (EEG) as a biomarker for the diagnosis of PPA. Methods. We conducted a cross-sectional study with 40 PPA patients categorized as non-fluent, semantic, and logopenic variants, and 20 controls. Resting-state EEG with 32 channels was acquired and preprocessed using several procedures (quantitative EEG, wavelet transformation, autoencoders, and graph theory analysis). Seven machine learning algorithms were evaluated (Decision Tree, Elastic Net, Support Vector Machines, Random Forest, K-Nearest Neighbors, Gaussian Naive Bayes, and Multinomial Naive Bayes). Results. Diagnostic capacity to distinguish between PPA and controls was high (accuracy 75%, F1-score 83% for kNN algorithm). The most important features in the classification were derived from network analysis based on graph theory. Conversely, discrimination between PPA variants was lower (Accuracy 58% and F1-score 60% for kNN). Conclusions. The application of ML to resting-state EEG may have a role in the diagnosis of PPA, especially in the differentiation from controls. Future studies with high-density EEG should explore the capacity to distinguish between PPA variants.

Whole-Exome Sequencing and C9orf72 Analysis in Primary Progressive Aphasia

Primary progressive aphasia (PPA) is mainly considered a sporadic disease and few studies have systematically analyzed its genetic basis. We here report the analyses of C9orf72 genotyping and whole-exome sequencing data in a consecutive and well-characterized cohort of 50 patients with PPA. We identified three pathogenic GRN variants, one of them unreported, and two cases with C9orf72 expansions. In addition, one likely pathogenic variant was found in the SQSTM1 gene. Overall, we found 12%of patients carrying pathogenic or likely pathogenic variants. These results support the genetic role in the pathophysiology of a proportion of patients with PPA.

Personalized Repetitive Transcranial Magnetic Stimulation for Primary Progressive Aphasia

BACKGROUND

Primary progressive aphasia (PPA) is a neurodegenerative syndrome for which no effective treatment is available.

OBJECTIVE

We aimed to assess the effect of repetitive transcranial magnetic stimulation (rTMS), using personalized targeting.

METHODS

We conducted a randomized, double-blind, pilot study of patients with PPA receiving rTMS, with a subgroup of patients receiving active- versus control-site rTMS in a cross-over design. Target for active TMS varied among the cases and was determined during a pre-treatment phase from a list of potential regions. The primary outcome was changes in spontaneous speech (word count). Secondary outcomes included changes in other language tasks, global cognition, global impression of change, neuropsychiatric symptoms, and brain metabolism using FDG-PET.

RESULTS

Twenty patients with PPA were enrolled (14 with nonfluent and 6 with semantic variant PPA). For statistical analyses, data for the two variants were combined. Compared to the control group (n = 7), the group receiving active-site rTMS (n = 20) showed improvements in spontaneous speech, other language tasks, patient and caregiver global impression of change, apathy, and depression. This group also showed improvement or stabilization of results obtained in the baseline examination. Increased metabolism was observed in several brain regions after the therapy, particularly in the left frontal and parieto-temporal lobes and in the precuneus and posterior cingulate bilaterally.

CONCLUSION

We found an improvement in language, patient and caregiver perception of change, apathy, and depression using high frequency rTMS. The increase of regional brain metabolism suggests enhancement of synaptic activity with the treatment.

TRIAL REGISTRATION

NCT03580954 (https://clinicaltrials.gov/ct2/show/NCT03580954).

Spanish Version of the Mini-Linguistic State Examination for the Diagnosis of Primary Progressive Aphasia

BACKGROUND

Primary progressive aphasia (PPA) is a neurodegenerative syndrome with three main clinical variants: non-fluent, semantic, and logopenic. Clinical diagnosis and accurate classification are challenging and often time-consuming. The Mini-Linguistic State Examination (MLSE) has been recently developed as a short language test to specifically assess language in neurodegenerative disorders.

OBJECTIVE

Our aim was to adapt and validate the Spanish version of MLSE for PPA diagnosis.

METHODS

Cross-sectional study involving 70 patients with PPA and 42 healthy controls evaluated with the MLSE. Patients were independently diagnosed and classified according to comprehensive cognitive evaluation and advanced neuroimaging.

RESULTS

Internal consistency was 0.758. The influence of age and education was very low. The area under the curve for discriminating PPA patients and healthy controls was 0.99. Effect sizes were moderate-large for the discrimination between PPA and healthy controls. Motor speech, phonology, and semantic subscores discriminated between the three clinical variants. A random forest classification model obtained an F1-score of 81%for the three PPA variants.

CONCLUSION

Our study provides a brief and useful language test for PPA diagnosis, with excellent properties for both clinical routine assessment and research purposes.

Performance Evaluation of Machine Learning Frameworks for Aphasia Assessment

Speech assessment is an essential part of the rehabilitation procedure for patients with aphasia (PWA). It is a comprehensive and time-consuming process that aims to discriminate between healthy individuals and aphasic patients, determine the type of aphasia syndrome, and determine the patients' impairment severity levels (these are referred to here as aphasia assessment tasks). Hence, the automation of aphasia assessment tasks is essential. In this study, the performance of three automatic speech assessment models based on the speech dataset-type was investigated. Three types of datasets were used: healthy subjects' dataset, aphasic patients' dataset, and a combination of healthy and aphasic datasets. Two machine learning (ML)-based frameworks, classical machine learning (CML) and deep neural network (DNN), were considered in the design of the proposed speech assessment models. In this paper, the DNN-based framework was based on a convolutional neural network (CNN). Direct or indirect transformation of these models to achieve the aphasia assessment tasks was investigated. Comparative performance results for each of the speech assessment models showed that quadrature-based high-resolution time-frequency images with a CNN framework outperformed all the CML frameworks over the three dataset-types. The CNN-based framework reported an accuracy of 99.23 ± 0.003% with the healthy individuals' dataset and 67.78 ± 0.047% with the aphasic patients' dataset. Moreover, direct or transformed relationships between the proposed speech assessment models and the aphasia assessment tasks are attainable, given a suitable dataset-type, a reasonably sized dataset, and appropriate decision logic in the ML framework.

Neuroimaging in Frontotemporal Dementia: Heterogeneity and Relationships with Underlying Neuropathology

Frontotemporal dementia encompasses a group of clinical syndromes defined pathologically by degeneration of the frontal and temporal lobes. Historically, these syndromes have been challenging to diagnose, with an average of about three years between the time of symptom onset and the initial evaluation and diagnosis. Research in the field of neuroimaging has revealed numerous biomarkers of the various frontotemporal dementia syndromes, which has provided clinicians with a method of narrowing the differential diagnosis and improving diagnostic accuracy. As such, neuroimaging is considered a core investigative tool in the evaluation of neurodegenerative disorders. Furthermore, patterns of neurodegeneration correlate with the underlying neuropathological substrates of the frontotemporal dementia syndromes, which can aid clinicians in determining the underlying etiology and improve prognostication. This review explores the advancements in neuroimaging and discusses the phenotypic and pathologic features of behavioral variant frontotemporal dementia, semantic variant primary progressive aphasia, and nonfluent variant primary progressive aphasia, as seen on structural magnetic resonance imaging and positron emission tomography.

Disentangling Heterogeneity in Alzheimer's Disease and Related Dementias Using Data-Driven Methods

Brain aging is a complex process that includes atrophy, vascular injury, and a variety of age-associated neurodegenerative pathologies, together determining an individual's course of cognitive decline. While Alzheimer's disease and related dementias contribute to the heterogeneity of brain aging, these conditions themselves are also heterogeneous in their clinical presentation, progression, and pattern of neural injury. We reviewed studies that leveraged data-driven approaches to examining heterogeneity in Alzheimer's disease and related dementias, with a principal focus on neuroimaging studies exploring subtypes of regional neurodegeneration patterns. Over the past decade, the steadily increasing wealth of clinical, neuroimaging, and molecular biomarker information collected within large-scale observational cohort studies has allowed for a richer understanding of the variability of disease expression within the aging and Alzheimer's disease and related dementias continuum. Moreover, the availability of these large-scale datasets has supported the development and increasing application of clustering techniques for studying disease heterogeneity in a data-driven manner. In particular, data-driven studies have led to new discoveries of previously unappreciated disease subtypes characterized by distinct neuroimaging patterns of regional neurodegeneration, which are paralleled by heterogeneous profiles of pathological, clinical, and molecular biomarker characteristics. Incorporating these findings into novel frameworks for more differentiated disease stratification holds great promise for improving individualized diagnosis and prognosis of expected clinical progression, and provides opportunities for development of precision medicine approaches for therapeutic intervention. We conclude with an account of the principal challenges associated with data-driven heterogeneity analyses and outline avenues for future developments in the field.