Lexical and Acoustic Speech Features Relating to Alzheimer Disease Pathology

Automated Speech Analysis to Differentiate Frontal and Right Anterior Temporal Lobe Atrophy in Frontotemporal Dementia

BACKGROUND AND OBJECTIVES

Frontotemporal dementia (FTD) includes behavioral-variant FTD (bvFTD) with predominant frontal atrophy and semantic behavioral-variant FTD (sbvFTD) with predominant right anterior temporal lobe (rATL) atrophy. These variants present diagnostic challenges because of overlapping symptoms and neuroanatomy. Accurate differentiation is crucial for clinical trial inclusion targeting TDP-43 proteinopathies. This study investigated whether automated speech analysis can distinguish between FTD-related rATL and frontal atrophy, potentially offering a noninvasive diagnostic tool.

METHODS

This cross-sectional study used data from the University of California, San Francisco Memory and Aging Center. Using stepwise logistic regression and receiver-operating characteristic curve analysis, we analyzed 16 linguistic and acoustic features that were extracted automatically from audio-recorded picture description tasks. Voxel-based morphometry was used to investigate brain-behavior relationships.

RESULTS

We evaluated 62 participants: 16 with FTD-related predominant frontal atrophy, 24 with predominant rATL atrophy, and 22 healthy controls (mean age 68.3 years, SD = 9.2; 53.2% female). Logistic regression identified 3 features (content units, lexical frequency, and familiarity) differentiating the overall FTD group from controls (area under the curve [AUC] = 0.973), adjusted for age. Within the FTD group, 5 features (adpositions/total words ratio, arousal, syllable pause duration, restarts, and words containing "thing") differentiated frontal from rATL atrophy (AUC = 0.943). Neuroimaging analyses showed that semantic features (lexical frequency, content units, and "thing" words) were linked to bilateral inferior temporal lobe structures, speech and lexical features (syllable pause duration, and adpositions/total words ratio) to bilateral inferior frontal gyri, and socioemotional features (arousal) to areas known to mediate social cognition including the right insula and bilateral anterior temporal structures. As a composite score, this set of 5 features was uniquely associated with rATL atrophy.

DISCUSSION

Automated speech analysis demonstrated high accuracy in differentiating FTD subtypes and provided insights into the neural basis of language impairments. Automated speech analysis could enhance early diagnosis and monitoring of FTD, offering a scalable, noninvasive alternative to traditional methods, particularly in resource-limited settings. Future research should focus on further clinical validation with other neuroimaging or fluid biomarkers and longitudinal cognitive data, as well as external validation in larger and more diverse populations.

Alzheimer disease seen through the lens of sex and gender

Alzheimer disease (AD) is a life-limiting neurodegenerative disorder that disproportionately affects women. Indeed, sex and gender are emerging as crucial modifiers of diagnostic and therapeutic pathways in AD. This Review provides an overview of the interactions of sex and gender with important developments in AD and offers insights into priorities for future research to facilitate the development and implementation of personalized approaches in the shifting paradigm of AD care. In particular, this Review focuses on the influence of sex and gender on important advances in the treatment and diagnosis of AD, including disease-modifying therapies, fluid-based biomarkers, cognitive assessment tools and multidomain lifestyle interventional studies.

DEMENTIA: A Hybrid Attention-Based Multimodal and Multi-Task Learning Framework With Expert Knowledge for Alzheimer's Disease Assessment From Speech

The prevalence of Alzheimer's disease (AD) is rising annually, imposing a severe burden on patients and society. Therefore, assisted AD assessment is crucial. The decline in language function and the cognitive impairment it reflects are key external manifestations of AD. Many studies have utilized speech analysis to achieve convenient, non-invasive, and low-cost AD detection. Although state-of-the-art researches achieve high-precision AD detection using multimodal information, these studies often ignore interactions between different modalities and lack explanations for complex models. To address this, we propose a multi-task learning (MTL) AD assessment model that combines hybrid attention with multimodal representations. The model fuses audio, text, and expert knowledge to fully capture intra- and inter-modal interactions, achieving simultaneous AD detection and cognitive state prediction, along with comprehensive explainability analyses of the model and various modalities. Results show that the proposed method is sufficiently sensitive in assessing AD, achieving 89.58% accuracy and 91.67% recall for the classification task and a root mean square error of 4.31 for the regression task with good generalization performance. Multimodal representations with expert knowledge and MTL contribute to AD assessment performance. Explainability analyses indicate that, compared to healthy controls, AD patients exhibit slower speech rates, reduced syntactic complexity, and a greater tendency to use pause fillers and pronouns. Therefore, Our study validates the effectiveness of the proposed method, addressing trust issues in clinical practice for assisted decision-making and further advancing the development of speech as a promising biomarker for early AD screening and cognitive decline monitoring.

Lexical markers of disordered speech in primary progressive aphasia and 'Parkinson-plus' disorders

Connected speech samples elicited by a picture description task are widely used in the assessment of aphasias, but it is not clear what their interpretation should focus on. Although such samples are easy to collect, analyses of them tend to be time-consuming, inconsistently conducted and impractical for non-specialist settings. Here, we analysed connected speech samples from patients with the three variants of primary progressive aphasia (semantic, svPPA N = 9; logopenic, lvPPA N = 9; and non-fluent, nfvPPA N = 9), progressive supranuclear palsy (PSP Richardson's syndrome N = 10), corticobasal syndrome (CBS N = 13) and age-matched healthy controls (N = 24). There were three principal aims: (i) to determine the differences in quantitative language output and psycholinguistic properties of words produced by patients and controls, (ii) to identify the neural correlates of connected speech measures and (iii) to develop a simple clinical measurement tool. Using data-driven methods, we optimized a 15-word checklist for use with the Boston Diagnostic Aphasia Examination 'cookie theft' and Mini Linguistic State Examination 'beach scene' pictures and tested the predictive validity of outputs from least absolute shrinkage and selection operator (LASSO) models using an independent clinical sample from a second site. The total language output was significantly reduced in patients with nfvPPA, PSP and CBS relative to those with svPPA and controls. The speech of patients with lvPPA and svPPA contained a disproportionately greater number of words of both high frequency and high semantic diversity. Results from our exploratory voxel-based morphometry analyses across the whole group revealed correlations between grey matter volume in (i) bilateral frontal lobes with overall language output, (ii) the left frontal and superior temporal regions with speech complexity, (iii) bilateral frontotemporal regions with phonology and (iv) bilateral cingulate and subcortical regions with age of acquisition. With the 15-word checklists, the LASSO models showed excellent accuracy for within-sample k-fold classification (over 93%) and out-of-sample validation (over 90%) between patients and controls. Between the motor disorders (nfvPPA, PSP and CBS) and lexico-semantic groups (svPPA and lvPPA), the LASSO models showed excellent accuracy for within-sample k-fold classification (88-92%) and moderately good (59-74%) differentiation for out-of-sample validation. In conclusion, we propose that a simple 15-word checklist provides a suitable screening test to identify people with progressive aphasia, while further specialist assessment is needed to differentiate accurately some groups (e.g. svPPA versus lvPPA and PSP versus nfvPPA).

A systematic review of the quantitative markers of speech and language of the frontotemporal degeneration spectrum and their potential for cross-linguistic implementation

Frontotemporal dementia (FTD) is a neurodegenerative disease spectrum with an urgent need for reliable biomarkers for early diagnosis and monitoring. Speech and language changes occur in the early stages of FTD and offer a potential non-invasive, early, and accessible diagnostic tool. The use of speech and language markers in this disease spectrum is limited by the fact that most studies investigate English-speaking patients. This systematic review examines the literature on psychoacoustic and linguistic features of speech that occur across the FTD spectrum across as many different languages as possible. 76 papers were identified that investigate psychoacoustic and linguistic markers in discursive speech. 75 % of these papers studied English-speaking patients. The most generalizable features found across different languages, are speech rate, articulation rate, pause frequency, total pause duration, noun-verb ratio, and total number of nouns. While there are clear interlinguistic differences across patient groups, the results show promise for implementation of cross-linguistic markers of speech and language across the FTD spectrum particularly for psychoacoustic features.

Automatic classification of AD pathology in FTD phenotypes using natural speech

INTRODUCTION

Screening for Alzheimer's disease neuropathologic change (ADNC) in individuals with atypical presentations is challenging but essential for clinical management. We trained automatic speech-based classifiers to distinguish frontotemporal dementia (FTD) patients with ADNC from those with frontotemporal lobar degeneration (FTLD).

METHODS

We trained automatic classifiers with 99 speech features from 1 minute speech samples of 179 participants (ADNC = 36, FTLD = 60, healthy controls [HC] = 89). Patients' pathology was assigned based on autopsy or cerebrospinal fluid analytes. Structural network-based magnetic resonance imaging analyses identified anatomical correlates of distinct speech features.

RESULTS

Our classifier showed 0.88 ± $ \pm $ 0.03 area under the curve (AUC) for ADNC versus FTLD and 0.93 ± $ \pm $ 0.04 AUC for patients versus HC. Noun frequency and pause rate correlated with gray matter volume loss in the limbic and salience networks, respectively.

DISCUSSION

Brief naturalistic speech samples can be used for screening FTD patients for underlying ADNC in vivo. This work supports the future development of digital assessment tools for FTD.

HIGHLIGHTS

We trained machine learning classifiers for frontotemporal dementia patients using natural speech. We grouped participants by neuropathological diagnosis (autopsy) or cerebrospinal fluid biomarkers. Classifiers well distinguished underlying pathology (Alzheimer's disease vs. frontotemporal lobar degeneration) in patients. We identified important features through an explainable artificial intelligence approach. This work lays the groundwork for a speech-based neuropathology screening tool.

A Decision-Making Algorithm for Remote Digital Assessments of Alzheimer's Disease

INTRODUCTION

Remote digital assessments (RDAs) such as voice recording, video and motor sensors, olfactory, hearing, and vision screenings are now starting to be employed to complement classical biomarker and clinical evidence to identify patients in the early AD stages. Choosing which RDA can be proposed to individual patients is not trivial and often time-consuming. This position paper presents a decision-making algorithm for using RDA during teleconsultations in memory clinic settings.

METHOD

The algorithm was developed by an expert panel following the Delphi methodology.

RESULTS

The decision-making algorithm is structured as a series of yes-no questions. The resulting questionnaire is freely available online.

DISCUSSION

We suggest that the use of screening questionnaires in the context of memory clinics may help accelerating the adoption of RDA in everyday clinical practice.

Speech patterns during memory recall relates to early tau burden across adulthood

INTRODUCTION

Early cognitive decline may manifest in subtle differences in speech.

METHODS

We examined 238 cognitively unimpaired adults from the Framingham Heart Study (32-75 years) who completed amyloid and tau PET imaging. Speech patterns during delayed recall of a story memory task were quantified via five speech markers, and their associations with global amyloid status and regional tau signal were examined.

RESULTS

Total utterance time, number of between-utterance pauses, speech rate, and percentage of unique words significantly correlated with delayed recall score although the shared variance was low (2%-15%). Delayed recall score was not significantly different between β-amyoid-positive (Aβ+) and -negative (Aβ-) groups and was not associated with regional tau signal. However, longer and more between-utterance pauses, and slower speech rate were associated with increased tau signal across medial temporal and early neocortical regions.

DISCUSSION

Subtle speech changes during memory recall may reflect cognitive impairment associated with early Alzheimer's disease pathology.

HIGHLIGHTS

Speech during delayed memory recall relates to tau PET signal across adulthood. Delayed memory recall score was not associated with tau PET signal. Speech shows greater sensitivity to detecting subtle cognitive changes associated with early tau accumulation. Our cohort spans adulthood, while most PET imaging studies focus on older adults.

Discriminating nonfluent/agrammatic and logopenic PPA variants with automatically extracted morphosyntactic measures from connected speech

Morphosyntactic assessments are important for characterizing individuals with nonfluent/agrammatic variant primary progressive aphasia (nfvPPA). Yet, standard tests are subject to examiner bias and often fail to differentiate between nfvPPA and logopenic variant PPA (lvPPA). Moreover, relevant neural signatures remain underexplored. Here, we leverage natural language processing tools to automatically capture morphosyntactic disturbances and their neuroanatomical correlates in 35 individuals with nfvPPA relative to 10 healthy controls (HC) and 26 individuals with lvPPA. Participants described a picture, and ensuing transcripts were analyzed via part-of-speech tagging to extract sentence-related features (e.g., subordinating and coordinating conjunctions), verbal-related features (e.g., tense markers), and nominal-related features (e.g., subjective and possessive pronouns). Gradient boosting machines were used to classify between groups using all features. We identified the most discriminant morphosyntactic marker via a feature importance algorithm and examined its neural correlates via voxel-based morphometry. Individuals with nfvPPA produced fewer morphosyntactic elements than the other two groups. Such features robustly discriminated them from both individuals with lvPPA and HCs with an AUC of .95 and .82, respectively. The most discriminatory feature corresponded to subordinating conjunctions was correlated with cortical atrophy within the left posterior inferior frontal gyrus across groups (pFWE < .05). Automated morphosyntactic analysis can efficiently differentiate nfvPPA from lvPPA. Also, the most sensitive morphosyntactic markers correlate with a core atrophy region of nfvPPA. Our approach, thus, can contribute to a key challenge in PPA diagnosis.

Reversal of the concreteness effect can be detected in the natural speech of older adults with amnestic, but not non-amnestic, mild cognitive impairment

INTRODUCTION

Patients with Alzheimer's disease present with difficulty in lexical retrieval and reversal of the concreteness effect in nouns. Little is known about the phenomena before the onset of symptoms. We anticipate early linguistic signs in the speech of people who suffer from amnestic mild cognitive impairment (MCI). Here, we report the results of a corpus-linguistic approach to the early detection of cognitive impairment.

METHODS

One hundred forty-eight English-speaking Singaporeans provided natural speech data, on topics of their choice; 74 were diagnosed with single-domain MCI (38 amnestic, 36 non-amnestic), 74 cognitively healthy. The recordings yield 267,310 words, which are tagged for parts of speech. We calculate the per-minute word counts and concreteness scores of all tagged words, nouns, and verbs in the dataset.

RESULTS

Compared to controls, subjects with amnestic MCI produce fewer but more abstract nouns. Verbs are not affected.

DISCUSSION

Slower retrieval of nouns and the reversal of the concreteness effect in nouns are manifested in natural speech and can be detected early through corpus-based analysis.

Highlights

Reversal of the concreteness effect is manifested in patients with Alzheimer's disease (AD) and semantic dementia.The paper reports a corpus-based analysis of natural speech by people with amnestic and non-amnestic mild cognitive impairment (MCI) and cognitively healthy controls.People with amnestic MCI produce fewer and more abstract nouns than people with non-amnestic MCI and healthy controls. Verbs appear to be unaffected.The imageability problem can be detected in natural everyday speech by people with amnestic MCI, which carries a higher risk of conversion to AD.

Linguistic changes in neurodegenerative diseases relate to clinical symptoms

Background

The detection and characterization of speech changes may help in the identification and monitoring of neurodegenerative diseases. However, there is limited research validating the relationship between speech changes and clinical symptoms across a wide range of neurodegenerative diseases.

Method

We analyzed speech recordings from 109 patients who were diagnosed with various neurodegenerative diseases, including Alzheimer's disease, Frontotemporal Dementia, and Vascular Cognitive Impairment, in a cognitive neurology memory clinic. Speech recordings of an open-ended picture description task were processed using the Winterlight speech analysis platform which generates >500 speech features, including the acoustics of speech and linguistic properties of spoken language. We investigated the relationship between the speech features and clinical assessments including the Mini Mental State Examination (MMSE), Mattis Dementia Rating Scale (DRS), Western Aphasia Battery (WAB), and Boston Naming Task (BNT) in a heterogeneous patient population.

Result

Linguistic features including lexical and syntactic features were significantly correlated with clinical assessments in patients, across diagnoses. Lower MMSE and DRS scores were associated with the use of shorter words and fewer prepositional phrases. Increased impairment on WAB and BNT was correlated with the use of fewer nouns but more pronouns. Patients also differed from healthy adults as their speech duration was significantly shorter with more pauses.

Conclusion

Linguistic changes such as the use of simpler vocabularies and syntax were detectable in patients with different neurodegenerative diseases and correlated with cognitive decline. Speech has the potential to be a sensitive measure for detecting cognitive impairments across various neurodegenerative diseases.

Exploring Spoken Discourse and Its Neural Correlates in Women With Alzheimer's Disease With Low Levels of Education and Socioeconomic Status

PURPOSE

Early impairments in spoken discourse abilities have been identified in Alzheimer's disease (AD). However, the impact of AD on spoken discourse and the associated neuroanatomical correlates have mainly been studied in populations with higher levels of education, although preliminary evidence seems to indicate that socioeconomic status (SES) and level of education have an impact on spoken discourse. The purpose of this study was to analyze microstructural variables in spoken discourse in people with AD with low-to-middle SES and low level of education and to study their association with gray matter (GM) density.

METHOD

Nine women with AD and 10 matched (age, SES, and education) women without brain injury (WWBI) underwent a neuropsychological assessment, which included two spoken discourse tasks, and structural magnetic resonance imaging. Microstructural variables were extracted from the discourse samples using NILC-Metrix software. Brain density, measured by voxel-based morphometry, was compared between groups and then correlated with the differentiating microstructural variables.

RESULTS

The AD group produced a lower diversity of verbal time moods and fewer words and sentences than WWBI but a greater diversity of pronouns, prepositions, and lexical richness. At the neural level, the AD group presented a lower GM density bilaterally in the hippocampus, the inferior temporal gyrus, and the anterior cingulate gyrus. Number of words and sentences produced were associated with GM density in the left parahippocampal gyrus, whereas the diversity of verbal moods was associated with the basal ganglia and the anterior cingulate gyrus bilaterally.

CONCLUSIONS

The present findings are mainly consistent with previous studies conducted in groups with higher levels of SES and education, but they suggest that atrophy in the left inferior temporal gyrus could be critical in AD in populations with lower levels of SES and education. This research provides evidence on the importance of pursuing further studies including people with various SES and education levels.

WHAT IS ALREADY KNOWN ON THIS SUBJECT

Spoken discourse has been shown to be affected in Alzheimer disease, but most studies have been conducted on individuals with middle-to-high SES and high educational levels.

WHAT THIS STUDY ADDS

The study reports on microstructural measures of spoken discourse in groups of women in the early stage of AD and healthy women, with low-to-middle SES and lower levels of education.

CLINICAL IMPLICATIONS OF THIS STUDY

This study highlights the importance of taking into consideration the SES and education level in spoken discourse analysis and in investigating the neural correlates of AD.

SUPPLEMENTAL MATERIAL

https://doi.org/10.23641/asha.24905046.

Automating the analysis of eye movement for different neurodegenerative disorders

The clinical observation and assessment of extra-ocular movements is common practice in assessing neurodegenerative disorders but remains observer-dependent. In the present study, we propose an algorithm that can automatically identify saccades, fixation, smooth pursuit, and blinks using a non-invasive eye tracker. Subsequently, response-to-stimuli-derived interpretable features were elicited that objectively and quantitatively assess patient behaviors. The cohort analysis encompasses persons with mild cognitive impairment (MCI), Alzheimer's disease (AD), Parkinson's disease (PD), Parkinson's disease mimics (PDM), and controls (CTRL). Overall, results suggested that the AD/MCI and PD groups had significantly different saccade and pursuit characteristics compared to CTRL when the target moved faster or covered a larger visual angle during smooth pursuit. These two groups also displayed more omitted antisaccades and longer average antisaccade latency than CTRL. When reading a text passage silently, people with AD/MCI had more fixations. During visual exploration, people with PD demonstrated a more variable saccade duration than other groups. In the prosaccade task, the PD group showed a significantly smaller average hypometria gain and accuracy, with the most statistical significance and highest AUC scores of features studied. The minimum saccade gain was a PD-specific feature different from CTRL and PDM. These features, as oculographic biomarkers, can be potentially leveraged in distinguishing different types of NDs, yielding more objective and precise protocols to diagnose and monitor disease progression.

The production of adjectives in narratives by individuals with primary progressive aphasia

Adjectives (e.g., hungry) are an important part of language, but have been little studied in individuals with impaired language. Adjectives are used in two different ways in English: attributively, to modify a noun (the hungry dog); or predicatively, after a verb (the dog is hungry). Attributive adjectives have a more complex grammatical structure than predicative adjectives, and may therefore be particularly prone to disruption in individuals with grammatical impairments. We investigated adjective production in three subtypes of primary progressive aphasia (PPA: agrammatic, semantic, logopenic), as well as in agrammatic stroke aphasia and a group of healthy control participants. Participants produced narratives based on picture books, and we coded every adjective they produced for its syntactic structure. Compared to healthy controls, the two agrammatic groups, but not the other two patient groups, produced significantly fewer attributive adjectives per sentence. All four patient groups were similar to controls for their rate of predicative adjective production. In addition, we found a significant correlation in the agrammatic PPA participants between their rate of producing attributive adjective and impaired production of sentences with complex syntactic structure (subject cleft sentences like It was the boy that chased the girl); no such correlation was found for predicative adjectives. Irrespective of structure, we examined the lexical characteristics of the adjectives that were produced, including length, frequency, semantic diversity and neighborhood density. Overall, the lexical characteristics of the produced adjectives were largely consistent with the language profile of each group. In sum, the results suggest that attributive adjectives present a particular challenge for individuals with agrammatic language production, and add a new dimension to the description of agrammatism. Our results further suggest that attributive adjectives may be a fruitful target for improved treatment and recovery of agrammatic language.

Changes in Digital Speech Measures in Asymptomatic Carriers of Pathogenic Variants Associated With Frontotemporal Degeneration

BACKGROUND AND OBJECTIVES

Clinical trials developing therapeutics for frontotemporal degeneration (FTD) focus on pathogenic variant carriers at preclinical stages. Objective, quantitative clinical assessment tools are needed to track stability and delayed disease onset. Natural speech can serve as an accessible, cost-effective assessment tool. We aimed to identify early changes in the natural speech of FTD pathogenic variant carriers before they become symptomatic.

METHODS

In this cohort study, speech samples of picture descriptions were collected longitudinally from healthy participants in observational studies at the University of Pennsylvania and Columbia University between 2007 and 2020. Participants were asymptomatic but at risk for familial FTD. Status as "carrier" or "noncarrier" was based on screening for known pathogenic variants in the participant's family. Thirty previously validated digital speech measures derived from automatic speech processing pipelines were selected a priori based on previous studies in patients with FTD and compared between asymptomatic carriers and noncarriers cross-sectionally and longitudinally.

RESULTS

A total of 105 participants, all asymptomatic, included 41 carriers: 12 men [30%], mean age 43 ± 13 years; education, 16 ± 2 years; MMSE 29 ± 1; and 64 noncarriers: 27 men [42%]; mean age, 48 ± 14 years; education, 15 ± 3 years; MMSE 29 ± 1. We identified 4 speech measures that differed between carriers and noncarriers at baseline: mean speech segment duration (mean difference -0.28 seconds, 95% CI -0.55 to -0.02, p = 0.04); word frequency (mean difference 0.07, 95% CI 0.008-0.14, p = 0.03); word ambiguity (mean difference 0.02, 95% CI 0.0008-0.05, p = 0.04); and interjection count per 100 words (mean difference 0.33, 95% CI 0.07-0.59, p = 0.01). Three speech measures deteriorated over time in carriers only: particle count per 100 words per month (β = -0.02, 95% CI -0.03 to -0.004, p = 0.009); total narrative production time in seconds per month (β = -0.24, 95% CI -0.37 to -0.12, p < 0.001); and total number of words per month (β = -0.48, 95% CI -0.78 to -0.19, p = 0.002) including in 3 carriers who later converted to symptomatic disease.

DISCUSSION

Using automatic processing pipelines, we identified early changes in the natural speech of FTD pathogenic variant carriers in the presymptomatic stage. These findings highlight the potential utility of natural speech as a digital clinical outcome assessment tool in FTD, where objective and quantifiable measures for abnormal behavior and language are lacking.

Acoustic Speech Analysis in Alzheimer's Disease: A Systematic Review and Meta-Analysis

BACKGROUND

The potential of biomarkers in the detection of Alzheimer's disease (AD) is prominent. Acoustics may be useful in this context but the evaluation and weighting for specific acoustic parameters on continuous speech is missing. This meta-analysis aimed to explore the significance of acoustic parameters from acoustic speech analysis on continuous speech, as a diagnostic tool for clinical AD.

METHODS

Applying PRISMA protocol, a comprehensive search was done in MEDLINE, Scopus, Web of Science, and CENTRAL, from 1960 to January 2024. Cross-sectional studies comparing the acoustic speech analysis between AD patients and healthy controls (HC), were taken into account. The bias risk of the included studies were examined via JBI checklist. Using Review Manager v.5.4.1, the mean differences of acoustic speech parameters among AD and HC were weighted, and the pooled analysis and the heterogeneity statistics were conducted.

RESULTS

In total, 1112 records (without duplicates) were obtained, and 11 papers with 7 acoustic parameters were included for this study, and 8 from 11 studies were identified with a low level of bias. Five from 7 acoustic parameters revealed significant differences among the two groups (p-values ≤ 0.01), in which for all rate-related and interruption-related acoustic parameters were the most prominent and less in temporal-related acoustic parameters.

CONCLUSIONS

Although a small number of acoustic parameters on continuous speech could be evaluated in the detection of clinical AD, the greatest potential of acoustic biomarkers for AD appeared to exist in two of three categories. Further contributions of high-quality studies are needed to support evidence for acoustics as biomarkers for AD.

Development of a Speech-based Composite Score for Remotely Quantifying Language Changes in Frontotemporal Dementia

BACKGROUND

Changes to speech and language are common symptoms across different subtypes of frontotemporal dementia (FTD). These changes affect the ability to communicate, impacting everyday functions. Accurately assessing these changes may help clinicians to track disease progression and detect response to treatment.

OBJECTIVE

To determine which aspects of speech show significant change over time and to develop a novel composite score for tracking speech and language decline in individuals with FTD.

METHOD

We recruited individuals with FTD to complete remote digital speech assessments based on a picture description task. Speech samples were analyzed to derive acoustic and linguistic measures of speech and language, which were tested for longitudinal change over the course of the study and were used to compute a novel composite score.

RESULTS

Thirty-six (16 F, 20 M; M age = 61.3 years) individuals were enrolled in the study, with 27 completing a follow-up assessment 12 months later. We identified eight variables reflecting different aspects of language that showed longitudinal decline in the FTD clinical syndrome subtypes and developed a novel composite score based on these variables. The resulting composite score demonstrated a significant effect of change over time, high test-retest reliability, and a correlation with standard scores on various other speech tasks.

CONCLUSION

Remote digital speech assessments have the potential to characterize speech and language abilities in individuals with FTD, reducing the burden of clinical assessments while providing a novel measure of speech and language abilities that is sensitive to disease and relevant to everyday function.

How Many Alzheimer-Perusini's Atypical Forms Do We Still Have to Discover?

Alzheimer-Perusini's (AD) disease represents the most spread dementia around the world and constitutes a serious problem for public health. It was first described by the two physicians from whom it took its name. Nowadays, we have extensively expanded our knowledge about this disease. Starting from a merely clinical and histopathologic description, we have now reached better molecular comprehension. For instance, we passed from an old conceptualization of the disease based on plaques and tangles to a more modern vision of mixed proteinopathy in a one-to-one relationship with an alteration of specific glial and neuronal phenotypes. However, no disease-modifying therapies are yet available. It is likely that the only way to find a few "magic bullets" is to deepen this aspect more and more until we are able to draw up specific molecular profiles for single AD cases. This review reports the most recent classifications of AD atypical variants in order to summarize all the clinical evidence using several discrimina (for example, post mortem neurofibrillary tangle density, cerebral atrophy, or FDG-PET studies). The better defined four atypical forms are posterior cortical atrophy (PCA), logopenic variant of primary progressive aphasia (LvPPA), behavioral/dysexecutive variant and AD with corticobasal degeneration (CBS). Moreover, we discuss the usefulness of such classifications before outlining the molecular-genetic aspects focusing on microglial activity or, more generally, immune system control of neuroinflammation and neurodegeneration.

Explainable Alzheimer's Disease Detection Using Linguistic Features from Automatic Speech Recognition

INTRODUCTION

Alzheimer's disease (AD) is the most prevalent type of dementia and can cause abnormal cognitive function and progressive loss of essential life skills. Early screening is thus necessary for the prevention and intervention of AD. Speech dysfunction is an early onset symptom of AD patients. Recent studies have demonstrated the promise of automated acoustic assessment using acoustic or linguistic features extracted from speech. However, most previous studies have relied on manual transcription of text to extract linguistic features, which weakens the efficiency of automated assessment. The present study thus investigates the effectiveness of automatic speech recognition (ASR) in building an end-to-end automated speech analysis model for AD detection.

METHODS

We implemented three publicly available ASR engines and compared the classification performance using the ADReSS-IS2020 dataset. Besides, the SHapley Additive exPlanations algorithm was then used to identify critical features that contributed most to model performance.

RESULTS

Three automatic transcription tools obtained mean word error rate texts of 32%, 43%, and 40%, respectively. These automated texts achieved similar or even better results than manual texts in model performance for detecting dementia, achieving classification accuracies of 89.58%, 83.33%, and 81.25%, respectively.

CONCLUSION

Our best model, using ensemble learning, is comparable to the state-of-the-art manual transcription-based methods, suggesting the possibility of an end-to-end medical assistance system for AD detection with ASR engines. Moreover, the critical linguistic features might provide insight into further studies on the mechanism of AD.

The efficacy of memory load on speech-based detection of Alzheimer's disease

Introduction

The study aims to test whether an increase in memory load could improve the efficacy in detection of Alzheimer's disease and prediction of the Mini-Mental State Examination (MMSE) score.

Methods

Speech from 45 mild-to-moderate Alzheimer's disease patients and 44 healthy older adults were collected using three speech tasks with varying memory loads. We investigated and compared speech characteristics of Alzheimer's disease across speech tasks to examine the effect of memory load on speech characteristics. Finally, we built Alzheimer's disease classification models and MMSE prediction models to assess the diagnostic value of speech tasks.

Results

The speech characteristics of Alzheimer's disease in pitch, loudness, and speech rate were observed and the high-memory-load task intensified such characteristics. The high-memory-load task outperformed in AD classification with an accuracy of 81.4% and MMSE prediction with a mean absolute error of 4.62.

Discussion

The high-memory-load recall task is an effective method for speech-based Alzheimer's disease detection.

Leveraging speech and artificial intelligence to screen for early Alzheimer's disease and amyloid beta positivity

Early detection of Alzheimer's disease is required to identify patients suitable for disease-modifying medications and to improve access to non-pharmacological preventative interventions. Prior research shows detectable changes in speech in Alzheimer's dementia and its clinical precursors. The current study assesses whether a fully automated speech-based artificial intelligence system can detect cognitive impairment and amyloid beta positivity, which characterize early stages of Alzheimer's disease. Two hundred participants (age 54-85, mean 70.6; 114 female, 86 male) from sister studies in the UK (NCT04828122) and the USA (NCT04928976), completed the same assessments and were combined in the current analyses. Participants were recruited from prior clinical trials where amyloid beta status (97 amyloid positive, 103 amyloid negative, as established via PET or CSF test) and clinical diagnostic status was known (94 cognitively unimpaired, 106 with mild cognitive impairment or mild Alzheimer's disease). The automatic story recall task was administered during supervised in-person or telemedicine assessments, where participants were asked to recall stories immediately and after a brief delay. An artificial intelligence text-pair evaluation model produced vector-based outputs from the original story text and recorded and transcribed participant recalls, quantifying differences between them. Vector-based representations were fed into logistic regression models, trained with tournament leave-pair-out cross-validation analysis to predict amyloid beta status (primary endpoint), mild cognitive impairment and amyloid beta status in diagnostic subgroups (secondary endpoints). Predictions were assessed by the area under the receiver operating characteristic curve for the test result in comparison with reference standards (diagnostic and amyloid status). Simulation analysis evaluated two potential benefits of speech-based screening: (i) mild cognitive impairment screening in primary care compared with the Mini-Mental State Exam, and (ii) pre-screening prior to PET scanning when identifying an amyloid positive sample. Speech-based screening predicted amyloid beta positivity (area under the curve = 0.77) and mild cognitive impairment or mild Alzheimer's disease (area under the curve = 0.83) in the full sample, and predicted amyloid beta in subsamples (mild cognitive impairment or mild Alzheimer's disease: area under the curve = 0.82; cognitively unimpaired: area under the curve = 0.71). Simulation analyses indicated that in primary care, speech-based screening could modestly improve detection of mild cognitive impairment (+8.5%), while reducing false positives (-59.1%). Furthermore, speech-based amyloid pre-screening was estimated to reduce the number of PET scans required by 35.3% and 35.5% in individuals with mild cognitive impairment and cognitively unimpaired individuals, respectively. Speech-based assessment offers accessible and scalable screening for mild cognitive impairment and amyloid beta positivity.