Impaired perceptual discrimination of complex objects in older adults at risk for dementia

Tau pathology accumulates in the perirhinal cortex (PRC) of the medial temporal lobe (MTL) during the earliest stages of the Alzheimer's disease (AD), appearing decades before clinical diagnosis. Here, we leveraged perceptual discrimination tasks that target PRC function to detect subtle cognitive impairment even in nominally healthy older adults. Older adults who did not have a clinical diagnosis or subjective memory complaints were categorized into "at-risk" (score <26; n = 15) and "healthy" (score ≥26; n = 23) groups based on their performance on the Montreal Cognitive Assessment. The task included two conditions known to recruit the PRC: faces and complex objects (greebles). A scene condition, known to recruit the hippocampus, and a size control condition that does not rely on the MTL were also included. Individuals in the at-risk group were less accurate than those in the healthy group for discriminating greebles. Performance on either the face or size control condition did not predict group status above and beyond that of the greeble condition. Visual discrimination tasks that are sensitive to PRC function may detect early cognitive decline associated with 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.

Detecting bulbar amyotrophic lateral sclerosis (ALS) using automatic acoustic analysis

Automatic speech assessments have the potential to dramatically improve ALS clinical practice and facilitate patient stratification for ALS clinical trials. Acoustic speech analysis has demonstrated the ability to capture a variety of relevant speech motor impairments, but implementation has been hindered by both the nature of lab-based assessments (requiring travel and time for patients) and also by the opacity of some acoustic feature analysis methods. These challenges and others have obscured the ability to distinguish different ALS disease stages/severities. Validation of automated acoustic analysis tools could enable detection of early signs of ALS, and these tools could be deployed to screen and monitor patients without requiring clinic visits. Here, we sought to determine whether acoustic features gathered using an automated assessment app could detect ALS as well as different levels of speech impairment severity resulting from ALS. Speech samples (readings of a standardized, 99-word passage) from 119 ALS patients with varying degrees of disease severity as well as 22 neurologically healthy participants were analyzed, and 53 acoustic features were extracted. Patients were stratified into early and late stages of disease (ALS-early/ALS-E and ALS-late/ALS-L) based on the ALS Functional Ratings Scale-Revised bulbar score (FRS-bulb) (median [interquartile range] of FRS-bulbar scores: 11[3]). The data were analyzed using a sparse Bayesian logistic regression classifier. It was determined that the current relatively small set of acoustic features could distinguish between ALS and controls well (area under receiver-operating characteristic curve/AUROC = 0.85), that the ALS-E patients could be separated well from control participants (AUROC = 0.78), and that ALS-E and ALS-L patients could be reasonably separated (AUROC = 0.70). These results highlight the potential for automated acoustic analyses to detect and stratify ALS.

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.

Detecting bulbar amyotrophic lateral sclerosis (ALS) using automatic acoustic analysis

Home-based speech assessments have the potential to dramatically improve ALS clinical practice and facilitate patient stratification for ALS clinical trials. Acoustic speech analysis has demonstrated the ability to capture a variety of relevant speech motor impairments, but implementation has been hindered by both the nature of lab-based assessments (requiring travel and time for patients) and also by the opacity of some acoustic feature analysis methods. Furthermore, these challenges and others have obscured the ability to distinguish different ALS disease stages/severities. Validation of remote-capable acoustic analysis tools could enable detection of early signs of ALS, and these tools could be deployed to screen and monitor patients without requiring clinic visits. Here, we sought to determine whether acoustic features gathered using a remote-capable assessment app could detect ALS as well as different levels of speech impairment severity resulting from ALS. Speech samples (readings of a standardized, 99-word passage) from 119 ALS patients with varying degrees of disease severity as well as 22 neurologically healthy participants were analyzed, and 53 acoustic features were extracted. Patients were stratified into early and late stages of disease (ALS-early/ALS-E and ALS-late/ALS-L) based on the ALS Functional Ratings Scale - Revised bulbar score (FRS-bulb). Data were analyzed using a sparse Bayesian logistic regression classifier. It was determined that the current relatively small set of acoustic features could distinguish between ALS and controls well (area under receiver operating characteristic curve/AUROC = 0.85), that the ALS-E patients could be separated well from control participants (AUROC = 0.78), and that ALS-E and ALS-L patients could be reasonably separated (AUROC = 0.70). These results highlight the potential for remote acoustic analyses to detect and stratify ALS.

PROSA-a multicenter prospective observational study to develop low-burden digital speech biomarkers in ALS and FTD

Objective: There is a need for novel biomarkers that can indicate disease state, project disease progression, or assess response to treatment for amyotrophic lateral sclerosis (ALS) and associated neurodegenerative diseases such as frontotemporal dementia (FTD). Digital biomarkers are especially promising as they can be collected non-invasively and at low burden for patients. Speech biomarkers have the potential to objectively measure cognitive, motor as well as respiratory symptoms at low-cost and in a remote fashion using widely available technology such as telephone calls. Methods: The PROSA study aims to develop and evaluate low-burden frequent prognostic digital speech biomarkers. The main goal is to create a single, easy-to-perform battery that serves as a valid and reliable proxy for cognitive, respiratory, and motor domains in ALS and FTD. The study will be a multicenter 12-months observational study aiming to include 75 ALS and 75 FTD patients as well as 50 healthy controls and build on three established longitudinal cohorts: DANCER, DESCRIBE-ALS and DESCRIBE-FTD. In addition to the extensive clinical phenotyping in DESCRIBE, PROSA collects a comprehensive speech protocol in fully remote and automated fashion over the telephone at four time points. This longitudinal speech data, together with gold standard measures, will allow advanced speech analysis using artificial intelligence for the development of speech-based phenotypes of ALS and FTD patients measuring cognitive, motor and respiratory symptoms. Conclusion: Speech-based phenotypes can be used to develop diagnostic and prognostic models predicting clinical change. Results are expected to have implications for future clinical trial stratification as well as supporting innovative trial designs in ALS and FTD.

Innovative Technologies in CNS Trials: Promises and Pitfalls for Recruitment, Retention, and Representativeness

Objective

Recruitment of a sufficiently large and representative patient sample and its retention during central nervous system (CNS) trials presents major challenges for study sponsors. Technological advances are reshaping clinical trial operations to meet these challenges, and the COVID-19 pandemic further accelerated this development.

Method of Research

The International Society for CNS Clinical Trials and Methodology (ISCTM; www.isctm.org) Innovative Technologies for CNS Trials Working Group surveyed the state of technological innovations for improved recruitment and retention and assessed their promises and pitfalls.

Results

Online advertisement and electronic patient registries can enhance recruitment, but challenges with sample representativeness, conversion rates from eligible prescreening to enrolled patients, data privacy and security, and patient identification remain hurdles for optimal use of these technologies. Electronic medical records (EMR) mining with artificial intelligence (AI)/machine learning (ML) methods is promising but awaits translation into trials. During the study treatment phase, technological innovations increasingly support participant retention, including adherence with the investigational treatment. Digital tools for adherence and retention support take many forms, including patient-centric communication channels between researchers and participants, real-time study reminders, and digital behavioral interventions to increase study compliance. However, such tools add technical complexities to trials, and their impact on the generalizability of results are largely unknown.

Conclusion

Overall, the group found a scarcity of systematic data directly assessing the impact of technological innovations on study recruitment and retention in CNS trials, even for strategies with already high adoption, such as online recruitment. Given the added complexity and costs associated with most technological innovations, such data is needed to fully harness technologies for CNS trials and drive further adoption.

Automated detection of progressive speech changes in early Alzheimer's disease

Speech and language changes occur in Alzheimer's disease (AD), but few studies have characterized their longitudinal course. We analyzed open-ended speech samples from a prodromal-to-mild AD cohort to develop a novel composite score to characterize progressive speech changes. Participant speech from the Clinical Dementia Rating (CDR) interview was analyzed to compute metrics reflecting speech and language characteristics. We determined the aspects of speech and language that exhibited significant longitudinal change over 18 months. Nine acoustic and linguistic measures were combined to create a novel composite score. The speech composite exhibited significant correlations with primary and secondary clinical endpoints and a similar effect size for detecting longitudinal change. Our results demonstrate the feasibility of using automated speech processing to characterize longitudinal change in early AD. Speech-based composite scores could be used to monitor change and detect response to treatment in future research.

HIGHLIGHTS

Longitudinal speech samples were analyzed to characterize speech changes in early AD.Acoustic and linguistic measures showed significant change over 18 months.A novel speech composite score was computed to characterize longitudinal change.The speech composite correlated with primary and secondary trial endpoints.Automated speech analysis could facilitate remote, high frequency monitoring in AD.

The Generalizability of Longitudinal Changes in Speech Before Alzheimer's Disease Diagnosis

BACKGROUND

Language impairment in Alzheimer's disease (AD) has been widely studied but due to limited data availability, relatively few studies have focused on the longitudinal change in language in the individuals who later develop AD. Significant differences in speech have previously been found by comparing the press conference transcripts of President Bush and President Reagan, who was later diagnosed with AD.

OBJECTIVE

In the current study, we explored whether the patterns previously established in the single AD-healthy control (HC) participant pair apply to a larger group of individuals who later receive AD diagnosis.

METHODS

We replicated previous methods on two larger corpora of longitudinal spontaneous speech samples of public figures, consisting of 10 and 9 AD-HC participant pairs. As we failed to find generalizable patterns of language change using previous methodology, we proposed alternative methods for data analysis, investigating the benefits of using different language features and their change with age, and compiling the single features into aggregate scores.

RESULTS

The single features that showed the strongest results were moving average type:token ratio (MATTR) and pronoun-related features. The aggregate scores performed better than the single features, with lexical diversity capturing a similar change in two-thirds of the participants.

CONCLUSION

Capturing universal patterns of language change prior to AD can be challenging, but the decline in lexical diversity and changes in MATTR and pronoun-related features act as promising measures that reflect the cognitive changes in many participants.

How Much Speech Data Is Needed for Tracking Language Change in Alzheimer's Disease? A Comparison of Random Length, 5-Min, and 1-Min Spontaneous Speech Samples

Introduction

Changes in speech can act as biomarkers of cognitive decline in Alzheimer's disease (AD). While shorter speech samples would promote data collection and analysis, the minimum length of informative speech samples remains debated. This study aims to provide insight into the effect of sample length in analyzing longitudinal recordings of spontaneous speech in AD by comparing the original random length, 5- and 1-minute-long samples. We hope to understand whether capping the audio improves the accuracy of the analysis, and whether an extra 4 min conveys necessary information.

Methods

110 spontaneous speech samples were collected from decades of Youtube videos of 17 public figures, 9 of whom eventually developed AD. 456 language features were extracted and their text-length-sensitivity, comparability, and ability to capture change over time were analyzed across three different sample lengths.

Results

Capped audio files had advantages over the random length ones. While most extracted features were statistically comparable or highly correlated across the datasets, potential effects of sample length should be acknowledged for some features. The 5-min dataset presented the highest reliability in tracking the evolution of the disease, suggesting that the 4 extra minutes do convey informative data.

Conclusion

Sample length seems to play an important role in extracting the language feature values from speech and tracking disease progress over time. We highlight the importance of further research into optimal sample length and standardization of methods when studying speech in AD.

Evaluating the utility of daily speech assessments for monitoring depression symptoms

Objective

Depression is a common mental health disorder and a major public health concern, significantly interfering with the lives of those affected. The complex clinical presentation of depression complicates symptom assessments. Day-to-day fluctuations of depression symptoms within an individual bring an additional barrier, since infrequent testing may not reveal symptom fluctuation. Digital measures such as speech can facilitate daily objective symptom evaluation. Here, we evaluated the effectiveness of daily speech assessment in characterizing speech fluctuations in the context of depression symptoms, which can be completed remotely, at a low cost and with relatively low administrative resources.

Methods

Community volunteers (N = 16) completed a daily speech assessment, using the Winterlight Speech App, and Patient Health Questionnaire-9 (PHQ-9) for 30 consecutive business days. We calculated 230 acoustic and 290 linguistic features from individual's speech and investigated their relationship to depression symptoms at the intra-individual level through repeated measures analyses.

Results

We observed that depression symptoms were linked to linguistic features, such as less frequent use of dominant and positive words. Greater depression symptomatology was also significantly correlated with acoustic features: reduced variability in speech intensity and increased jitter.

Conclusions

Our findings support the feasibility of using acoustic and linguistic features as a measure of depression symptoms and propose daily speech assessment as a tool for better characterization of symptom fluctuations.

Clinical Characteristics and Mortality of Old and Very Old Patients Hospitalized for Hip Fracture or Acute Medical Conditions

BACKGROUND

There is increasing interest in healthcare quality and economic implications for hip fracture patients of very old age. However, results are limited by access to comparable control groups.

OBJECTIVES

We examined healthcare quality measures including mortality and length of stay (LOS) in hospital of adults aged 60-107 years undergoing hip operations, compared to an age-matched group admitted for acute general medical conditions.

DESIGN

Monocentric cross-sectional study.

SETTING

Ashford and St Peter's Hospitals NHS Foundation Trust, Surrey, United Kingdom.

PARTICIPANTS

A total of 3972 consecutive admissions for hip operation from 1st April 2009 to 30th June 2019 (dataset-1) and 6979 for acute general medical conditions from 1st April 2019 to 29th February 2020 (dataset-2). Respective ages, mean (±standard deviation), were 83.5 years (±9.1) and 79.8 years (±9.8).

MEASUREMENTS

Mortality and LOS were assessed with each group divided into five- year age bands and those ≥95 years.

RESULTS

There were proportionally more (P <0.001) females admitted for hip operations (72.8%) than for acute general medical conditions (53.8%). Amongst patients admitted with general medical conditions, the frequency of the most serious recorded conditions - including congestive heart failure, stroke, and pneumonia - increased with age. Amongst patients undergoing hip operations, 5.7% died in hospital and 29.3% had a LOS ≥3 weeks. Corresponding values for acute general medical conditions were 10.4% and 11.8%. For those undergoing hip operations in all age categories, the risk of death was lower than for acute general medical group: sex-adjusted odds ratios ranged between 0.27 and 0.67, but the risk of LOS ≥3 weeks was greater: odds ratios ranged between 2.46 and 2.95.

CONCLUSIONS

Compared to those admitted with acute general medical conditions, patients admitted for hip operations had a lower risk of death, but a longer hospital LOS. .

Validation of automated pipeline for the assessment of a motor speech disorder in amyotrophic lateral sclerosis (ALS)

Background and objective

Amyotrophic lateral sclerosis (ALS) frequently causes speech impairments, which can be valuable early indicators of decline. Automated acoustic assessment of speech in ALS is attractive, and there is a pressing need to validate such tools in line with best practices, including analytical and clinical validation. We hypothesized that data analysis using a novel speech assessment pipeline would correspond strongly to analyses performed using lab-standard practices and that acoustic features from the novel pipeline would correspond to clinical outcomes of interest in ALS.

Methods

We analyzed data from three standard speech assessment tasks (i.e., vowel phonation, passage reading, and diadochokinesis) in 122 ALS patients. Data were analyzed automatically using a pipeline developed by Winterlight Labs, which yielded 53 acoustic features. First, for analytical validation, data were analyzed using a lab-standard analysis pipeline for comparison. This was followed by univariate analysis (Spearman correlations between individual features in Winterlight and in-lab datasets) and multivariate analysis (sparse canonical correlation analysis (SCCA)). Subsequently, clinical validation was performed. This included univariate analysis (Spearman correlation between automated acoustic features and clinical measures) and multivariate analysis (interpretable autoencoder-based dimensionality reduction).

Results

Analytical validity was demonstrated by substantial univariate correlations (Spearman's ρ > 0.70) between corresponding pairs of features from automated and lab-based datasets, as well as interpretable SCCA feature groups. Clinical validity was supported by strong univariate correlations between automated features and clinical measures (Spearman's ρ > 0.70), as well as associations between multivariate outputs and clinical measures.

Conclusion

This novel, automated speech assessment feature set demonstrates substantial promise as a valid tool for analyzing impaired speech in ALS patients and for the further development of these technologies.

Description of the Method for Evaluating Digital Endpoints in Alzheimer Disease Study: Protocol for an Exploratory, Cross-sectional Study

Background

More sensitive and less burdensome efficacy end points are urgently needed to improve the effectiveness of clinical drug development for Alzheimer disease (AD). Although conventional end points lack sensitivity, digital technologies hold promise for amplifying the detection of treatment signals and capturing cognitive anomalies at earlier disease stages. Using digital technologies and combining several test modalities allow for the collection of richer information about cognitive and functional status, which is not ascertainable via conventional paper-and-pencil tests.

Objective

This study aimed to assess the psychometric properties, operational feasibility, and patient acceptance of 10 promising technologies that are to be used as efficacy end points to measure cognition in future clinical drug trials.

Methods

The Method for Evaluating Digital Endpoints in Alzheimer Disease study is an exploratory, cross-sectional, noninterventional study that will evaluate 10 digital technologies’ ability to accurately classify participants into 4 cohorts according to the severity of cognitive impairment and dementia. Moreover, this study will assess the psychometric properties of each of the tested digital technologies, including the acceptable range to assess ceiling and floor effects, concurrent validity to correlate digital outcome measures to traditional paper-and-pencil tests in AD, reliability to compare test and retest, and responsiveness to evaluate the sensitivity to change in a mild cognitive challenge model. This study included 50 eligible male and female participants (aged between 60 and 80 years), of whom 13 (26%) were amyloid-negative, cognitively healthy participants (controls); 12 (24%) were amyloid-positive, cognitively healthy participants (presymptomatic); 13 (26%) had mild cognitive impairment (predementia); and 12 (24%) had mild AD (mild dementia). This study involved 4 in-clinic visits. During the initial visit, all participants completed all conventional paper-and-pencil assessments. During the following 3 visits, the participants underwent a series of novel digital assessments.

Results

Participant recruitment and data collection began in June 2020 and continued until June 2021. Hence, the data collection occurred during the COVID-19 pandemic (SARS-CoV-2 virus pandemic). Data were successfully collected from all digital technologies to evaluate statistical and operational performance and patient acceptance. This paper reports the baseline demographics and characteristics of the population studied as well as the study's progress during the pandemic.

Conclusions

This study was designed to generate feasibility insights and validation data to help advance novel digital technologies in clinical drug development. The learnings from this study will help guide future methods for assessing novel digital technologies and inform clinical drug trials in early AD, aiming to enhance clinical end point strategies with digital technologies.

International Registered Report Identifier (IRRID)

DERR1-10.2196/35442

Differential speech and language characteristics across neurodegenerative disorders

BACKGROUND

Speech and language changes have been reported to occur across a range of neurodegenerative disorders, including Alzheimer's Disease (AD), Frontotemporal Dementia (FTD) and Parkinson's Disease (PD). Characterizing and quantifying such changes will enable the development of novel speech-based measures to identify and monitor disease remotely and non-invasively. In order to determine if such measures are disease-specific, it is important to compare speech and language changes across different neurological conditions. In this study, we identify speech and language characteristics that are differentially affected across AD, FTD and PD populations.

METHOD

In this cross-study comparison, we pooled data from normative studies of older adults (N = 299), and studies of individuals with a clinical diagnosis of AD (N = 895), FTD (N = 43) or PD (N = 42). In all studies, speech was recorded as participants performed a picture description task, in which they were shown a line drawing of a scene and asked to describe everything they saw in the picture. Speech samples were transcribed and analyzed, producing >500 acoustic and linguistic variables describing the characteristics of the speech sound and content. Speech variables were compared across groups using ANOVAs with a factor of diagnosis group, and significant group effects (p < 0.05) were further examined with pairwise group comparisons.

RESULT

Speech variables showing common or differential effects according to diagnosis were identified in this exploratory cross-study comparison. Speech variables relating to the ease of speech production, including speech rate and number of pauses, were affected in all three diseases when compared to control participants. Select acoustic variables, including mean intensity and zero-crossing rate, showed the greatest differences in PD compared to FTD or AD. Individuals with AD and FTD produced picture descriptions with less relevant information content. Select lexical variables, including pronoun and preposition use, were selectively affected in AD but not FTD or PD.

CONCLUSION

This study indicates that speech and language characteristics, derived from a picture description task, were differentially affected in AD, FTD, and PD. We found evidence for acoustic changes in PD, consistent with motor speech impairments, and linguistic changes in AD and FTD, consistent with cognitive impairments.

Using Digital Speech Assessments to Detect Early Signs of Cognitive Impairment

Detecting early signs of cognitive decline is crucial for early detection and treatment of Alzheimer's Disease. Most of the current screening tools for Alzheimer's Disease represent a significant burden, requiring invasive procedures, or intensive and costly clinical testing. Recent findings have highlighted changes to speech and language patterns that occur in Alzheimer's Disease, and may be detectable prior to diagnosis. Automated tools to assess speech have been developed that can be used on a smartphone or tablet, from one's home, in under 10 min. In this study, we present the results of a study of older adults who completed a digital speech assessment task over a 6-month period. Participants were grouped according to those who scored above (N = 18) or below (N = 18) the recommended threshold for detecting cognitive impairment on the Montreal Cognitive Assessment (MoCA) and those with diagnoses of mild cognitive impairment (MCI) or early Alzheimer's Disease (AD) (N = 14). Older adults who scored above the MoCA threshold had better performance on speech composites reflecting language coherence, information richness, syntactic complexity, and word finding abilities. Those with MCI and AD showed more rapid decline in the coherence of language from baseline to 6-month follow-up, suggesting that this score may be useful both for detecting cognitive decline and monitoring change over time. This study demonstrates that automated speech assessments have potential as sensitive tools to detect early signs of cognitive impairment and monitor progression over time.

Natural Language Processing as an Emerging Tool to Detect Late-Life Depression

Late-life depression (LLD) is a major public health concern. Despite the availability of effective treatments for depression, barriers to screening and diagnosis still exist. The use of current standardized depression assessments can lead to underdiagnosis or misdiagnosis due to subjective symptom reporting and the distinct cognitive, psychomotor, and somatic features of LLD. To overcome these limitations, there has been a growing interest in the development of objective measures of depression using artificial intelligence (AI) technologies such as natural language processing (NLP). NLP approaches focus on the analysis of acoustic and linguistic aspects of human language derived from text and speech and can be integrated with machine learning approaches to classify depression and its severity. In this review, we will provide rationale for the use of NLP methods to study depression using speech, summarize previous research using NLP in LLD, compare findings to younger adults with depression and older adults with other clinical conditions, and discuss future directions including the use of complementary AI strategies to fully capture the spectrum of LLD.

Correlating natural language processing and automated speech analysis with clinician assessment to quantify speech-language changes in mild cognitive impairment and Alzheimer's dementia

BACKGROUND

Language impairment is an important marker of neurodegenerative disorders. Despite this, there is no universal system of terminology used to describe these impairments and large inter-rater variability can exist between clinicians assessing language. The use of natural language processing (NLP) and automated speech analysis (ASA) is emerging as a novel and potentially more objective method to assess language in individuals with mild cognitive impairment (MCI) and Alzheimer's dementia (AD). No studies have analyzed how variables extracted through NLP and ASA might also be correlated to language impairments identified by a clinician.

METHODS

Audio recordings (n=30) from participants with AD, MCI, and controls were rated by clinicians for word-finding difficulty, incoherence, perseveration, and errors in speech. Speech recordings were also transcribed, and linguistic and acoustic variables were extracted through NLP and ASA. Correlations between clinician-rated speech characteristics and the variables were compared using Spearman's correlation. Exploratory factor analysis was applied to find common factors between variables for each speech characteristic.

RESULTS

Clinician agreement was high in three of the four speech characteristics: word-finding difficulty (ICC = 0.92, p<0.001), incoherence (ICC = 0.91, p<0.001), and perseveration (ICC = 0.88, p<0.001). Word-finding difficulty and incoherence were useful constructs at distinguishing MCI and AD from controls, while perseveration and speech errors were less relevant. Word-finding difficulty as a construct was explained by three factors, including number and duration of pauses, word duration, and syntactic complexity. Incoherence was explained by two factors, including increased average word duration, use of past tense, and changes in age of acquisition, and more negative valence.

CONCLUSIONS

Variables extracted through automated acoustic and linguistic analysis of MCI and AD speech were significantly correlated with clinician ratings of speech and language characteristics. Our results suggest that correlating NLP and ASA with clinician observations is an objective and novel approach to measuring speech and language changes in neurodegenerative disorders.

Comparing Pre-trained and Feature-Based Models for Prediction of Alzheimer's Disease Based on Speech

Introduction: Research related to the automatic detection of Alzheimer's disease (AD) is important, given the high prevalence of AD and the high cost of traditional diagnostic methods. Since AD significantly affects the content and acoustics of spontaneous speech, natural language processing, and machine learning provide promising techniques for reliably detecting AD. There has been a recent proliferation of classification models for AD, but these vary in the datasets used, model types and training and testing paradigms. In this study, we compare and contrast the performance of two common approaches for automatic AD detection from speech on the same, well-matched dataset, to determine the advantages of using domain knowledge vs. pre-trained transfer models. Methods: Audio recordings and corresponding manually-transcribed speech transcripts of a picture description task administered to 156 demographically matched older adults, 78 with Alzheimer's Disease (AD) and 78 cognitively intact (healthy) were classified using machine learning and natural language processing as "AD" or "non-AD." The audio was acoustically-enhanced, and post-processed to improve quality of the speech recording as well control for variation caused by recording conditions. Two approaches were used for classification of these speech samples: (1) using domain knowledge: extracting an extensive set of clinically relevant linguistic and acoustic features derived from speech and transcripts based on prior literature, and (2) using transfer-learning and leveraging large pre-trained machine learning models: using transcript-representations that are automatically derived from state-of-the-art pre-trained language models, by fine-tuning Bidirectional Encoder Representations from Transformer (BERT)-based sequence classification models. Results: We compared the utility of speech transcript representations obtained from recent natural language processing models (i.e., BERT) to more clinically-interpretable language feature-based methods. Both the feature-based approaches and fine-tuned BERT models significantly outperformed the baseline linguistic model using a small set of linguistic features, demonstrating the importance of extensive linguistic information for detecting cognitive impairments relating to AD. We observed that fine-tuned BERT models numerically outperformed feature-based approaches on the AD detection task, but the difference was not statistically significant. Our main contribution is the observation that when tested on the same, demographically balanced dataset and tested on independent, unseen data, both domain knowledge and pretrained linguistic models have good predictive performance for detecting AD based on speech. It is notable that linguistic information alone is capable of achieving comparable, and even numerically better, performance than models including both acoustic and linguistic features here. We also try to shed light on the inner workings of the more black-box natural language processing model by performing an interpretability analysis, and find that attention weights reveal interesting patterns such as higher attribution to more important information content units in the picture description task, as well as pauses and filler words. Conclusion: This approach supports the value of well-performing machine learning and linguistically-focussed processing techniques to detect AD from speech and highlights the need to compare model performance on carefully balanced datasets, using consistent same training parameters and independent test datasets in order to determine the best performing predictive model.

Evaluation of Speech-Based Digital Biomarkers: Review and Recommendations

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

The contributions of spatial context and imagery to the recollection of single words

A number of theories of hippocampal function have placed spatial context at the center of richly recollected memories, but the subjective and objective ways that spatial context underlies the recollection of single words has been largely overlooked and underexplained. In this study, we conducted three experiments to investigate the involvement of spatial context in the recollection of single words. In all three experiments, participants encoded single words with varying features such as location and color. The subjective experience of recollection was measured using remember/know judgments and participant self-report of the types of information they recollected about the words. Objectively, recollection was measured using source memory judgments for both spatial and non-spatial features associated with the words. Our results provide evidence that spatial context frequently accompanies the recollection of single, isolated words, reviving discussions on the role of the hippocampus in spatial and detailed recollection.

Cognitive mapping style relates to posterior-anterior hippocampal volume ratio

As London taxi drivers acquire "the knowledge" and develop a detailed cognitive map of London, their posterior hippocampi (pHPC) gradually increase in volume, reflecting an increasing pHPC/aHPC volume ratio. In the mnemonic domain, greater pHPC/aHPC volume ratios in young adults have been found to relate to better recollection ability, indicating that the balance between pHPC and aHPC volumes might be reflective of cross-domain individual differences. Here, we examined participants' self-reported use of cognitive map-based navigational strategies in relation to their pHPC/aHPC hippocampal volume ratio. We find that greater reported cognitive map use was related to significantly greater posterior, relative to anterior, hippocampal volume in two separate samples of young adults. Further, greater reported cognitive map usage correlated with better performance on a self-initiated navigation task. Together, these data help to advance our understanding of differences between aHPC and pHPC and the greater role of pHPC in spatial mapping.

Scenes facilitate associative memory and integration

How do we form mental links between related items? Forming associations between representations is a key feature of episodic memory and provides the foundation for learning and guiding behavior. Theories suggest that spatial context plays a supportive role in episodic memory, providing a scaffold on which to form associations, but this has mostly been tested in the context of autobiographical memory. We examined the memory boosting effect of spatial stimuli in memory using an associative inference paradigm combined with eye-tracking. Across two experiments, we found that memory was better for associations that included scenes, even indirectly, compared to objects and faces. Eye-tracking measures indicated that these effects may be partly mediated by greater fixations to scenes compared to objects, but did not explain the differences between scenes and faces. These results suggest that scenes facilitate associative memory and integration across memories, demonstrating evidence in support of theories of scenes as a spatial scaffold for episodic memory. A shared spatial context may promote learning and could potentially be leveraged to improve learning and memory in educational settings or for memory-impaired populations.

Hippocampal and Retrosplenial Goal Distance Coding After Long-term Consolidation of a Real-World Environment

Recent research indicates the hippocampus may code the distance to the goal during navigation of newly learned environments. It is unclear however, whether this also pertains to highly familiar environments where extensive systems-level consolidation is thought to have transformed mnemonic representations. Here we recorded fMRI while University College London and Imperial College London students navigated virtual simulations of their own familiar campus (>2 years of exposure) and the other campus learned days before scanning. Posterior hippocampal activity tracked the distance to the goal in the newly learned campus, as well as in familiar environments when the future route contained many turns. By contrast retrosplenial cortex only tracked the distance to the goal in the familiar campus. All of these responses were abolished when participants were guided to their goal by external cues. These results open new avenues of research on navigation and consolidation of spatial information and underscore the notion that the hippocampus continues to play a role in navigation when detailed processing of the environment is needed for navigation.

Spontaneous memory retrieval varies based on familiarity with a spatial context

Spatial context can serve as a powerful cue for episodic memory. In daily life, we encounter locations varying in familiarity that may trigger different forms of memory retrieval. While previous research on autobiographical memory suggests that more familiar landmarks cue more detailed memories, theories such as cue overload predict that less familiar cues will more reliably trigger specific memory retrieval. It is therefore possible that more and less familiar cues will differentially elicit more generalized and specific memories, respectively. In this series of studies, we develop a novel paradigm for eliciting spontaneous memory retrieval based on real-world spatial contexts varying in familiarity. We found evidence that more familiar contexts generally lead to higher rates of spontaneous memory retrieval for semantic and generalized memories, but that episodic memories are more frequently retrieved for less familiar cues. These patterns demonstrate how related memories lead to the formation of more generalized representations over time, while memories with fewer associates remain episodic. We discuss these findings in relation to those obtained in a version of the study in which participants were instructed to retrieve thoughts. Together these findings provide novel insight into the dynamics of context familiarity and memory retrieval in a naturalistic autobiographical memory paradigm.

Category specificity in the medial temporal lobe: A systematic review

Theoretical accounts of medial temporal lobe (MTL) function ascribe different functions to subregions of the MTL including perirhinal, entorhinal, parahippocampal cortices, and the hippocampus. Some have suggested that the functional roles of these subregions vary in terms of their category specificity, showing preferential coding for certain stimulus types, but the evidence for this functional organization is mixed. In this systematic review, we evaluate existing evidence for regional specialization in the MTL for three categories of visual stimuli: faces, objects, and scenes. We review and synthesize across univariate and multivariate neuroimaging studies, as well as neuropsychological studies of cases with lesions to the MTL. Neuroimaging evidence suggests that faces activate the perirhinal cortex, entorhinal cortex, and the anterior hippocampus, while scenes engage the parahippocampal cortex and both the anterior and posterior hippocampus, depending on the contrast condition. There is some evidence for object-related activity in anterior MTL regions when compared to scenes, and in posterior MTL regions when compared to faces, suggesting that aspects of object representations may share similarities with face and scene representations. While neuroimaging evidence suggests some hippocampal specialization for faces and scenes, neuropsychological evidence shows that hippocampal damage leads to impairments in scene memory and perception, but does not entail equivalent impairments for faces in cases where the perirhinal cortex remains intact. Regional specialization based on stimulus categories has implications for understanding the mechanisms of MTL subregions, and highlights the need for the development of theoretical models of MTL function that can accommodate the differential patterns of specificity observed in the MTL.

Self-adaptive ultrasonic beam amplifiers: application to transcostal shock wave therapy

Ultrasound shock wave therapy is increasingly used for non-invasive surgery. It requires the focusing of very high pressure amplitude in precisely controlled focal spots. In transcostal therapy of the heart or the liver, the high impedance mismatch between the bones and surrounding tissues gives rise to strong aberrations and attenuation of the therapeutic wavefront, with potential risks of injury at the tissue-bone interface. An adaptive propagation of the ultrasonic beam through the intercostal spaces would be required. Several solutions have been developed so far, but they require a prior knowledge of the patient's anatomy or an invasive calibration process, not applicable in clinic. Here, we develop a non-invasive adaptive focusing method for ultrasound therapy through the ribcage using a time reversal cavity (TRC) acting as an ultrasonic beam amplifier. This method is based on ribcage imaging through the TRC and a projection orthogonally to the strongest identified reflectors. The focal pressure of our device was improved by up to 30% using such self-adaptive processing, without degrading the focal spots size and shape. This improvement allowed lesion formation in an Ultracal^® phantom through a ribcage without invasive calibration of the device. This adaptive method could be particularly interesting to improve the efficiency and the safety of pulsed cavitational therapy of the heart or the liver.

Multiple Scales of Representation along the Hippocampal Anteroposterior Axis in Humans

The ability to represent the world accurately relies on simultaneous coarse and fine-grained neural information coding, capturing both gist and detail of an experience. The longitudinal axis of the hippocampus may provide a gradient of representational granularity in spatial and episodic memory in rodents and humans [1-8]. Rodent place cells in the ventral hippocampus exhibit significantly larger place fields and greater autocorrelation than those in the dorsal hippocampus [1, 9-11], which may underlie a coarser and slower changing representation of space [10, 12]. Recent evidence suggests that properties of cellular dynamics in rodents can be captured with fMRI in humans during spatial navigation [13] and conceptual learning [14]. Similarly, mechanisms supporting granularity along the long axis may also be extrapolated to the scale of fMRI signal. Here, we provide the first evidence for separable scales of representation along the human hippocampal anteroposterior axis during navigation and rest by showing (1) greater similarity among voxel time courses and (2) higher temporal autocorrelation in anterior hippocampus (aHPC), relative to posterior hippocampus (pHPC), the human homologs of ventral and dorsal rodent hippocampus. aHPC voxels exhibited more similar activity at each time point and slower signal change over time than voxels in pHPC, consistent with place field organization in rodents. Importantly, similarity between voxels was related to navigational strategy and episodic memory. These findings provide evidence that the human hippocampus supports an anterior-to-posterior gradient of coarse-to-fine spatiotemporal representations, suggesting the existence of a cross-species mechanism, whereby lower neural similarity supports more complex coding of experience.

Spatial scaffold effects in event memory and imagination

Spatial context is a defining feature of episodic memories, which are often characterized as being events occurring in specific spatiotemporal contexts. In this review, I summarize research suggesting a common neural basis for episodic and spatial memory and relate this to the role of spatial context in episodic memory. I review evidence that spatial context serves as a scaffold for episodic memory and imagination, in terms of both behavioral and neural effects demonstrating a dependence of episodic memory on spatial representations. These effects are mediated by a posterior-medial set of neocortical regions, including the parahippocampal cortex, retrosplenial cortex, posterior cingulate cortex, precuneus, and angular gyrus, which interact with the hippocampus to represent spatial context in remembered and imagined events. I highlight questions and areas that require further research, including differentiation of hippocampal function along its long axis and subfields, and how these areas interact with the posterior-medial network. This article is categorized under: Psychology > Memory Neuroscience > Cognition.

A semi-analytical model of a time reversal cavity for high-amplitude focused ultrasound applications

Time reversal cavities (TRC) have been proposed as an efficient approach for 3D ultrasound therapy. They allow the precise spatio-temporal focusing of high-power ultrasound pulses within a large region of interest with a low number of transducers. Leaky TRCs are usually built by placing a multiple scattering medium, such as a random rod forest, in a reverberating cavity, and the final peak pressure gain of the device only depends on the temporal length of its impulse response. Such multiple scattering in a reverberating cavity is a complex phenomenon, and optimisation of the device's gain is usually a cumbersome process, mostly empirical, and requiring numerical simulations with extremely long computation times. In this paper, we present a semi-analytical model for the fast optimisation of a TRC. This model decouples ultrasound propagation in an empty cavity and multiple scattering in a multiple scattering medium. It was validated numerically and experimentally using a 2D-TRC and numerically using a 3D-TRC. Finally, the model was used to determine rapidly the optimal parameters of the 3D-TRC which had been confirmed by numerical simulations.

A 3D time reversal cavity for the focusing of high-intensity ultrasound pulses over a large volume

Shock wave ultrasound therapy techniques, increasingly used for non-invasive surgery, require extremely high pressure amplitudes in precise focal spots, and large high-power transducers arranged on a spherical shell are usually used to achieve that. This solution allows limited steering of the beam around the geometrical focus of the device at the cost of a large number of transducer elements, and the treatment of large and moving organs like the heart is challenging or impossible. This paper validates numerically and experimentally the possibility of using a time reversal cavity (TRC) for the same purpose. A 128-element, 1 MHz power transducer combined with different multiple scattering media in a TRC was used. We were able to focus high-power ultrasound pulses over a large volume in a controlled manner, with a limited number of transducer elements. We reached sufficiently high pressure amplitudes to erode an Ultracal^® target over a 10 cm² area.

The Maritime Medical Emergency Response Team: what do we really need?

Since 2006, the Defence Medical Services (DMS) pre-hospital care focus has been the Medical Emergency Response Team (MERT), which has enabled the projection of Damage Control Resuscitation (DCR) to the point of wounding as part of consultant- delivered care. Now in a period of contingency operations, the Royal Navy (RN)’s Role 2 medical capability, Role 2 Afloat (R2A) delivers DCR (including surgery) on a maritime platform. This article will focus on the development of the Maritime MERT component of R2A (termed Maritime In Transit Care (MITC) in Maritime Medical Doctrine) and will discuss the requirements based on experience of and preparation for an operation in 2016. Also discussed are the individual competencies and training required to be part of the Maritime MERT; it is hoped that this will simulate debate around this evolving team.

Establishing and maintaining a robust Role 2 Afloat organisation within the Royal Naval Medical Services

In 2009, the Royal Navy (RN) reconfigured the Role 2 maritime medical treatment capability, the Role 2 Afloat (R2A). This capability is now firmly established on a number of platforms in the fleet and was recently externally validated on RFA MOUNTS BAY prior to completion of an operational deployment supporting contingency operations in the Mediterranean. This article outlines the future challenges for R2A and offers suggestions on how to maintain a robust R2A organisation within the Royal Naval Medical Service (RNMS).

The spatial scaffold: The effects of spatial context on memory for events

Events always unfold in a spatial context, leading to the claim that it serves as a scaffold for encoding and retrieving episodic memories. The ubiquitous co-occurrence of spatial context with events may induce participants to generate a spatial context when hearing scenarios of events in which it is absent. Spatial context should also serve as an excellent cue for memory retrieval. To test these predictions, participants read event scenarios involving a highly familiar or less familiar spatial context, or person, which they were asked to imagine and remember. At recall, locations were more effective memory cues than people, and both were better when they were highly familiar. Most importantly, when no locations were specified at study, participants exhibited a spontaneous tendency to generate a spatial context for the scenarios, while rarely generating a person. Events with spatial context were remembered more vividly and described in more detail than those without. Together, the results favor the view that spatial context plays a leading role in remembering events.

More than accuracy: Nonverbal dialects modulate the time course of vocal emotion recognition across cultures

Using a gating paradigm, this study investigated the nature of the in-group advantage in vocal emotion recognition by comparing 2 distinct cultures. Pseudoutterances conveying 4 basic emotions, expressed in English and Hindi, were presented to English and Hindi listeners. In addition to hearing full utterances, each stimulus was gated from its onset to construct 5 processing intervals to pinpoint when the in-group advantage emerges, and whether this differs when listening to a foreign language (English participants judging Hindi) or a second language (Hindi participants judging English). An index of the mean emotion identification point for each group and unbiased measures of accuracy at each time point was calculated. Results showed that in each language condition, native listeners were faster and more accurate than non-native listeners to recognize emotions. The in-group advantage emerged in both conditions after processing 400 ms to 500 ms of acoustic information. In the bilingual Hindi group, greater oral proficiency in English predicted faster and more accurate recognition of English emotional expressions. Consistent with dialect theory, our findings provide new evidence that nonverbal dialects impede both the accuracy and the efficiency of vocal emotion processing in cross-cultural settings, even when individuals are highly proficient in the out-group target language.