Automatic speech analysis for the assessment of patients with predementia and Alzheimer's disease

Multimodal Technologies for Remote Assessment of Neurological and Mental Health

PURPOSE

Automated remote assessment and monitoring of patients' neurological and mental health is increasingly becoming an essential component of the digital clinic and telehealth ecosystem, especially after the COVID-19 pandemic. This review article reviews various modalities of health information that are useful for developing such remote clinical assessments in the real world at scale.

APPROACH

We first present an overview of the various modalities of health information-speech acoustics, natural language, conversational dynamics, orofacial or full body movement, eye gaze, respiration, cardiopulmonary, and neural-which can each be extracted from various signal sources-audio, video, text, or sensors. We further motivate their clinical utility with examples of how information from each modality can help us characterize how different disorders affect different aspects of patients' spoken communication. We then elucidate the advantages of combining one or more of these modalities toward a more holistic, informative, and robust assessment.

FINDINGS

We find that combining multiple modalities of health information allows for improved scientific interpretability, improved performance on downstream health applications such as early detection and progress monitoring, improved technological robustness, and improved user experience. We illustrate how these principles can be leveraged for remote clinical assessment at scale using a real-world case study of the Modality assessment platform.

CONCLUSION

This review article motivates the combination of human-centric information from multiple modalities to measure various aspects of patients' health, arguing that remote clinical assessment that integrates this complementary information can be more effective and lead to better clinical outcomes than using any one data stream in isolation.

Artificial intelligence-enhanced patient evaluation: bridging art and science

The advent of digital health and artificial intelligence (AI) has promised to revolutionize clinical care, but real-world patient evaluation has yet to witness transformative changes. As history taking and physical examination continue to rely on long-established practices, a growing pipeline of AI-enhanced digital tools may soon augment the traditional clinical encounter into a data-driven process. This article presents an evidence-backed vision of how promising AI applications may enhance traditional practices, streamlining tedious tasks while elevating diverse data sources, including AI-enabled stethoscopes, cameras, and wearable sensors, to platforms for personalized medicine and efficient care delivery. Through the lens of traditional patient evaluation, we illustrate how digital technologies may soon be interwoven into routine clinical workflows, introducing a novel paradigm of longitudinal monitoring. Finally, we provide a skeptic's view on the practical, ethical, and regulatory challenges that limit the uptake of such technologies.

Automated free speech analysis reveals distinct markers of Alzheimer's and frontotemporal dementia

Dementia can disrupt how people experience and describe events as well as their own role in them. Alzheimer's disease (AD) compromises the processing of entities expressed by nouns, while behavioral variant frontotemporal dementia (bvFTD) entails a depersonalized perspective with increased third-person references. Yet, no study has examined whether these patterns can be captured in connected speech via natural language processing tools. To tackle such gaps, we asked 96 participants (32 AD patients, 32 bvFTD patients, 32 healthy controls) to narrate a typical day of their lives and calculated the proportion of nouns, verbs, and first- or third-person markers (via part-of-speech and morphological tagging). We also extracted objective properties (frequency, phonological neighborhood, length, semantic variability) from each content word. In our main study (with 21 AD patients, 21 bvFTD patients, and 21 healthy controls), we used inferential statistics and machine learning for group-level and subject-level discrimination. The above linguistic features were correlated with patients' scores in tests of general cognitive status and executive functions. We found that, compared with HCs, (i) AD (but not bvFTD) patients produced significantly fewer nouns, (ii) bvFTD (but not AD) patients used significantly more third-person markers, and (iii) both patient groups produced more frequent words. Machine learning analyses showed that these features identified individuals with AD and bvFTD (AUC = 0.71). A generalizability test, with a model trained on the entire main study sample and tested on hold-out samples (11 AD patients, 11 bvFTD patients, 11 healthy controls), showed even better performance, with AUCs of 0.76 and 0.83 for AD and bvFTD, respectively. No linguistic feature was significantly correlated with cognitive test scores in either patient group. These results suggest that specific cognitive traits of each disorder can be captured automatically in connected speech, favoring interpretability for enhanced syndrome characterization, diagnosis, and monitoring.

Alzheimer's in the modern age: Ethical challenges in the use of digital monitoring to identify cognitive changes

Pushes toward earlier detection of Alzheimer's disease (AD)-related cognitive changes are creating interest in leveraging technologies, like cellphones, that are already widespread and well-equipped for data collection to facilitate digital monitoring for AD. Studies are ongoing to identify and validate potential "digital biomarkers" that might indicate someone has or is at risk of developing AD dementia. Digital biomarkers for AD have potential as a tool in aiding more timely diagnosis, though more robust research is needed to support their validity and utility. While there are grounds for optimism, leveraging digital monitoring and informatics for cognitive changes also poses ethical challenges, related to topics such as algorithmic bias, consent, and data privacy and security. As we confront the modern era of Alzheimer's disease, individuals, companies, regulators and policymakers alike must prepare for a future in which our day-to-day interactions with technology in our daily life may identify AD-related cognitive changes.

The Reliability and Clinical Validation of Automatically-Derived Verbal Memory Features of the Verbal Learning Test in Early Diagnostics of Cognitive Impairment

BACKGROUND

Previous research has shown that verbal memory accurately measures cognitive decline in the early phases of neurocognitive impairment. Automatic speech recognition from the verbal learning task (VLT) can potentially be used to differentiate between people with and without cognitive impairment.

OBJECTIVE

Investigate whether automatic speech recognition (ASR) of the VLT is reliable and able to differentiate between subjective cognitive decline (SCD) and mild cognitive impairment (MCI).

METHODS

The VLT was recorded and processed via a mobile application. Following, verbal memory features were automatically extracted. The diagnostic performance of the automatically derived features was investigated by training machine learning classifiers to distinguish between participants with SCD versus MCI/dementia.

RESULTS

The ICC for inter-rater reliability between the clinical and automatically derived features was 0.87 for the total immediate recall and 0.94 for the delayed recall. The full model including the total immediate recall, delayed recall, recognition count, and the novel verbal memory features had an AUC of 0.79 for distinguishing between participants with SCD versus MCI/dementia. The ten best differentiating VLT features correlated low to moderate with other cognitive tests such as logical memory tasks, semantic verbal fluency, and executive functioning.

CONCLUSIONS

The VLT with automatically derived verbal memory features showed in general high agreement with the clinical scoring and distinguished well between SCD and MCI/dementia participants. This might be of added value in screening for cognitive impairment.

Harnessing the Power of Voice: A Deep Neural Network Model for Alzheimer's Disease Detection

Background and Purpose

Voice, reflecting cerebral functions, holds potential for analyzing and understanding brain function, especially in the context of cognitive impairment (CI) and Alzheimer's disease (AD). This study used voice data to distinguish between normal cognition and CI or Alzheimer's disease dementia (ADD).

Methods

This study enrolled 3 groups of subjects: 1) 52 subjects with subjective cognitive decline; 2) 110 subjects with mild CI; and 3) 59 subjects with ADD. Voice features were extracted using Mel-frequency cepstral coefficients and Chroma.

Results

A deep neural network (DNN) model showed promising performance, with an accuracy of roughly 81% in 10 trials in predicting ADD, which increased to an average value of about 82.0%±1.6% when evaluated against unseen test dataset.

Conclusions

Although results did not demonstrate the level of accuracy necessary for a definitive clinical tool, they provided a compelling proof-of-concept for the potential use of voice data in cognitive status assessment. DNN algorithms using voice offer a promising approach to early detection of AD. They could improve the accuracy and accessibility of diagnosis, ultimately leading to better outcomes for patients.

Speech changes in old age: Methodological considerations for speech-based discrimination of healthy ageing and Alzheimer's disease

BACKGROUND

Recent evidence suggests that speech substantially changes in ageing. As a complex neurophysiological process, it can accurately reflect changes in the motor and cognitive systems underpinning human speech. Since healthy ageing is not always easily discriminable from early stages of dementia based on cognitive and behavioural hallmarks, speech is explored as a preclinical biomarker of pathological itineraries in old age. A greater and more specific impairment of neuromuscular activation, as well as  a specific cognitive and linguistic impairment in dementia, unchain discriminating changes in speech. Yet, there is no consensus on such discriminatory speech parameters, neither on how they should be elicited and assessed.

AIMS

To provide a state-of-the-art on speech parameters that allow for early discrimination between healthy and pathological ageing; the aetiology of these parameters; the effect of the type of experimental stimuli on speech elicitation and the predictive power of different speech parameters; and the most promising methods for speech analysis and their clinical implications.

METHODS & PROCEDURES

A scoping review methodology is used in accordance with the PRISMA model. Following a systematic search of PubMed, PsycINFO and CINAHL, 24 studies are included and analysed in the review.

MAIN CONTRIBUTION

The results of this review yield three key questions for the clinical assessment of speech in ageing. First, acoustic and temporal parameters are more sensitive to changes in pathological ageing and, of these two, temporal variables are more affected by cognitive impairment. Second, different types of stimuli can trigger speech parameters with different degree of accuracy for the discrimination of clinical groups. Tasks with higher cognitive load are more precise in eliciting higher levels of accuracy. Finally, automatic speech analysis for the discrimination of healthy and pathological ageing should be improved for both research and clinical practice.

CONCLUSIONS & IMPLICATIONS

Speech analysis is a promising non-invasive tool for the preclinical screening of healthy and pathological ageing. The main current challenges of speech analysis in ageing are the automatization of its clinical assessment and the consideration of the speaker's cognitive background during evaluation.

WHAT THIS PAPER ADDS

What is already known on the subject Societal aging  goes hand in hand with the rising incidence of ageing-related neurodegenerations, mainly Alzheimer's disease (AD). This is particularly noteworthy in countries with longer life expectancies. Healthy ageing and early stages of AD share a set of cognitive and behavioural characteristics. Since there is no cure for dementias, developing methods for accurate discrimination of healthy ageing and early AD is currently a priority. Speech has been described as one of the most significantly impaired features in AD. Neuropathological alterations in motor and cognitive systems would underlie specific speech impairment in dementia. Since speech can be evaluated quickly, non-invasively and inexpensively, its value for the clinical assessment of ageing itineraries may be particularly high. What this paper adds to existing knowledge Theoretical and experimental advances in the assessment of speech as a marker of AD have developed rapidly over the last decade. Yet, they are not always known to clinicians. Furthermore, there is a need to provide an updated state-of-the-art on which speech features are discriminatory to AD, how they can be assessed, what kind of results they can yield, and how such results should be interpreted. This article provides an updated overview of speech profiling, methods of speech measurement and analysis, and the clinical power of speech assessment for early discrimination of AD as the most common cause of dementia. What are the potential or actual clinical implications of this work? This article provides an overview of the predictive potential of different speech parameters in relation to AD cognitive impairment. In addition, it discusses the effect that the cognitive state, the type of elicitation task and the type of assessment method may have on the results of the speech-based analysis in ageing.

Neural Computation-Based Methods for the Early Diagnosis and Prognosis of Alzheimer's Disease Not Using Neuroimaging Biomarkers: A Systematic Review

Background

The growing number of older adults in recent decades has led to more prevalent geriatric diseases, such as strokes and dementia. Therefore, Alzheimer's disease (AD), as the most common type of dementia, has become more frequent too.

Background

Objective: The goals of this work are to present state-of-the-art studies focused on the automatic diagnosis and prognosis of AD and its early stages, mainly mild cognitive impairment, and predicting how the research on this topic may change in the future.

Methods

Articles found in the existing literature needed to fulfill several selection criteria. Among others, their classification methods were based on artificial neural networks (ANNs), including deep learning, and data not from brain signals or neuroimaging techniques were used. Considering our selection criteria, 42 articles published in the last decade were finally selected.

Results

The most medically significant results are shown. Similar quantities of articles based on shallow and deep ANNs were found. Recurrent neural networks and transformers were common with speech or in longitudinal studies. Convolutional neural networks (CNNs) were popular with gait or combined with others in modular approaches. Above one third of the cross-sectional studies utilized multimodal data. Non-public datasets were frequently used in cross-sectional studies, whereas the opposite in longitudinal ones. The most popular databases were indicated, which will be helpful for future researchers in this field.

Conclusions

The introduction of CNNs in the last decade and their superb results with neuroimaging data did not negatively affect the usage of other modalities. In fact, new ones emerged.

Voice analysis results in individuals with Alzheimer's disease: How do age and cognitive status affect voice parameters?

BACKGROUND

Reports of acoustic changes in the voice in individuals with Alzheimer's disease (AD) and the relationship of acoustic changes with age and cognitive status are still limited.

OBJECTIVE

This study aims to determine the changes in voice analysis results in AD, as well as the effects of age and cognitive status on voice parameters.

METHODS

The study included 47 (AD: 30; healthy: 17) women with a mean age of 76.13 years. The acoustic voice parameters mean fundamental frequency (F0), relative average perturbation (RAP), jitter percent (Jitt), shimmer percent (Shim), and noise-to-harmonic ratio were detected. The mini-mental state examination (MMSE) was utilized.

RESULTS

F0, Shim, Jitt, and RAP values were found to be statistically significantly higher in individuals with AD compared to healthy individuals. There was a significant negative correlation between MMSE and F0, Jitt, RAP and Shim, and the MMSE score had a significant negative effect on F0, Jitt, and RAP (p < .05).

CONCLUSION

Cognitive status was discovered to significantly impact the voice, with fundamental frequency and frequency and amplitude perturbations increasing as cognitive level decreases. In order to contribute to the therapy process for voice disorders, cognitive functions can be focused on in addition to voice therapy.

Post-Processing Automatic Transcriptions with Machine Learning for Verbal Fluency Scoring

Objective

To compare verbal fluency scores derived from manual transcriptions to those obtained using automatic speech recognition enhanced with machine learning classifiers.

Methods

Using Amazon Web Services, we automatically transcribed verbal fluency recordings from 1400 individuals who performed both animal and letter F verbal fluency tasks. We manually adjusted timings and contents of the automatic transcriptions to obtain "gold standard" transcriptions. To make automatic scoring possible, we trained machine learning classifiers to discern between valid and invalid utterances. We then calculated and compared verbal fluency scores from the manual and automatic transcriptions.

Results

For both animal and letter fluency tasks, we achieved good separation of valid versus invalid utterances. Verbal fluency scores calculated based on automatic transcriptions showed high correlation with those calculated after manual correction.

Conclusion

Many techniques for scoring verbal fluency word lists require accurate transcriptions with word timings. We show that machine learning methods can be applied to improve off-the-shelf ASR for this purpose. These automatically derived scores may be satisfactory for some applications. Low correlations among some of the scores indicate the need for improvement in automatic speech recognition before a fully automatic approach can be reliably implemented.

AI-based assessments of speech and language impairments in dementia

Recent advancements in the artificial intelligence (AI) domain have revolutionized the early detection of cognitive impairments associated with dementia. This has motivated clinicians to use AI-powered dementia detection systems, particularly systems developed based on individuals' and patients' speech and language, for a quick and accurate identification of patients with dementia. This paper reviews articles about developing assessment tools using machine learning and deep learning algorithms trained by vocal and textual datasets.

An explainable machine learning model of cognitive decline derived from speech

INTRODUCTION

Traditional Alzheimer's disease (AD) and mild cognitive impairment (MCI) screening lacks the sensitivity and timeliness required to detect subtle indicators of cognitive decline. Multimodal artificial intelligence technologies using only speech data promise improved detection of neurodegenerative disorders.

METHODS

Speech collected over the telephone from 91 older participants who were cognitively healthy (n = 29) or had diagnoses of AD (n = 30) or amnestic MCI (aMCI; n = 32) was analyzed with multimodal natural language and speech processing methods. An explainable ensemble decision tree classifier for the multiclass prediction of cognitive decline was created.

RESULTS

This approach was 75% accurate overall-an improvement over traditional speech-based screening tools and a unimodal language-based model. We include a dashboard for the examination of the results, allowing for novel ways of interpreting such data.

DISCUSSION

This work provides a foundation for a meaningful change in medicine as clinical translation, scalability, and user friendliness were core to the methodologies.

Highlights

Remote assessments and artificial intelligence (AI) models allow greater access to cognitive decline screening.Speech impairments differ significantly between mild AD, amnestic mild cognitive impairment (aMCI), and healthy controls.AI predictions of cognitive decline are more accurate than experts and standard tools.The AI model was 75% accurate in classifying mild AD, aMCI, and healthy controls.

Further evaluation of narrative description as a measure of cognitive function in Alzheimer's disease

OBJECTIVE

The narrative description (ND) test objectively measures the ability to understand and describe visual scenes. As subtle differences in speech occur early in cognitive decline, we analyzed linguistic features for their utility in detecting cognitive impairment and predicting downstream decline.

METHOD

Participants (n = 52) with normal cognition to mild dementia performed the ND test (watched twenty 30-s video clips and described the visual content). Cognitive function was followed for up to 5 years. We computed simple linguistic features such as content efficiency, speech rate, and part of speech and unique word counts. We examined (a) relationships between cognitive status and ND score and linguistic features; (b) ability to discriminate early cognitive impairment from normal cognition using ND score and linguistic features; and (c) whether ND score and linguistic features were associated with future cognitive functional decline.

RESULTS

Many of the linguistic-feature metrics were related to cognitive status. Many of the linguistic features could distinguish between the cognitively normal group and the mild cognitive impairment (MCI) and Dementia groups. The area under the curve (AUC) for ND score alone was 0.74, with a nonsignificant increase to 0.78 when adding mean word length. Among participants with subjective cognitive decline (SCD) at the first visit, a smaller number of words plus more interjections or a lower ND score at baseline were predictive of future cognitive decline.

CONCLUSIONS

While many linguistic features were associated with cognitive status, and some were able to detect early cognitive impairment or predictive of future cognitive decline, all the features we tested seem to have been captured by the ND score. Thus, adding linguistic measures to the ND test score did not add to its value in assessing current or predicting future cognitive status. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Speech patterns in responses to questions asked by an intelligent virtual agent can help to distinguish between people with early stage neurodegenerative disorders and healthy controls

Previous research has provided strong evidence that speech patterns can help to distinguish between people with early stage neurodegenerative disorders (ND) and healthy controls. This study examined speech patterns in responses to questions asked by an intelligent virtual agent (IVA): a talking head on a computer which asks pre-recorded questions. The study investigated whether measures of response length, speech rate and pausing in responses to questions asked by an IVA help to distinguish between healthy control participants and people diagnosed with Mild Cognitive Impairment (MCI) or Alzheimer's disease (AD). The study also considered whether those measures can further help to distinguish between people with MCI, people with AD, and healthy control participants (HC). There were 38 people with ND (31 people with MCI, 7 people with AD) and 26 HC. All interactions took place in English. People with MCI spoke fewer words compared to HC, and people with AD and people with MCI spoke for less time than HC. People with AD spoke at a slower rate than people with MCI and HC. There were significant differences across all three groups for the proportion of time spent pausing and the average pause duration: silent pauses make up the greatest proportion of responses from people with AD, who also have the longest average silent pause duration, followed by people with MCI then HC. Therefore, the study demonstrates the potential of an IVA as a method for collecting data showing patterns which can help to distinguish between diagnostic groups.

Harnessing acoustic speech parameters to decipher amyloid status in individuals with mild cognitive impairment

Alzheimer's disease (AD) is a neurodegenerative condition characterized by a gradual decline in cognitive functions. Currently, there are no effective treatments for AD, underscoring the importance of identifying individuals in the preclinical stages of mild cognitive impairment (MCI) to enable early interventions. Among the neuropathological events associated with the onset of the disease is the accumulation of amyloid protein in the brain, which correlates with decreased levels of Aβ42 peptide in the cerebrospinal fluid (CSF). Consequently, the development of non-invasive, low-cost, and easy-to-administer proxies for detecting Aβ42 positivity in CSF becomes particularly valuable. A promising approach to achieve this is spontaneous speech analysis, which combined with machine learning (ML) techniques, has proven highly useful in AD. In this study, we examined the relationship between amyloid status in CSF and acoustic features derived from the description of the Cookie Theft picture in MCI patients from a memory clinic. The cohort consisted of fifty-two patients with MCI (mean age 73 years, 65% female, and 57% positive amyloid status). Eighty-eight acoustic parameters were extracted from voice recordings using the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS), and several ML models were used to classify the amyloid status. Furthermore, interpretability techniques were employed to examine the influence of input variables on the determination of amyloid-positive status. The best model, based on acoustic variables, achieved an accuracy of 75% with an area under the curve (AUC) of 0.79 in the prediction of amyloid status evaluated by bootstrapping and Leave-One-Out Cross Validation (LOOCV), outperforming conventional neuropsychological tests (AUC = 0.66). Our results showed that the automated analysis of voice recordings derived from spontaneous speech tests offers valuable insights into AD biomarkers during the preclinical stages. These findings introduce novel possibilities for the use of digital biomarkers to identify subjects at high risk of developing AD.

The Use of Artificial Intelligence in the Management of Neurodegenerative Disorders; Focus on Alzheimer's Disease

Recent advances in artificial intelligence (AI) have shown great promise in the diagnosis, prediction, treatment plans, and monitoring of neurodegenerative disorders. AI algorithms can analyze huge quantities of data from numerous sources, including medical images, quantifiable proteins in urine, blood, and cerebrospinal fluid (CSF), genetic information, clinical records, electroencephalography (EEG) signals, driving behaviors, and so forth. Alzheimer's disease (AD) is one of the most common neurodegenerative disorders that progressively damage cognitive abilities and memory. This study specifically explores the possible application of AI in the diagnosis, prediction, monitoring, biomarker or drug discovery, and classification of AD.

Guess What We Can Hear-Novel Voice Biomarkers for the Remote Detection of Disease

The advancement of digital biomarkers and the provision of remote health care greatly progressed during the coronavirus disease 2019 global pandemic. Combining voice/speech data with artificial intelligence and machine-based learning offers a novel solution to the growing demand for telemedicine. Voice biomarkers, obtained from the extraction of characteristic acoustic and linguistic features, are associated with a variety of diseases and even coronavirus disease 2019. In the current review, we (1) describe the basis on which digital voice biomarkers could facilitate "telemedicine," (2) discuss potential mechanisms that may explain the association between voice biomarkers and disease, (3) offer a novel classification system to conceptualize voice biomarkers depending on different methods for recording and analyzing voice/speech samples, (4) outline evidence revealing an association between voice biomarkers and a number of disease states, and (5) describe the process of developing a voice biomarker from recording, storing voice samples, and extracting acoustic and linguistic features relevant to training and testing deep and machine-based learning algorithms to detect disease. We further explore several important future considerations in this area of research, including the necessity for clinical trials and the importance of safeguarding data and individual privacy. To this end, we searched PubMed and Google Scholar to identify studies evaluating the relationship between voice/speech features and biomarkers and various diseases. Search terms included digital biomarker, telemedicine, voice features, voice biomarker, speech features, speech biomarkers, acoustics, linguistics, cardiovascular disease, neurologic disease, psychiatric disease, and infectious disease. The search was limited to studies published in English in peer-reviewed journals between 1980 and the present. To identify potential studies not captured by our database search strategy, we also searched studies listed in the bibliography of relevant publications and reviews.

Applied Machine Learning Techniques to Diagnose Voice-Affecting Conditions and Disorders: Systematic Literature Review

BACKGROUND

Normal voice production depends on the synchronized cooperation of multiple physiological systems, which makes the voice sensitive to changes. Any systematic, neurological, and aerodigestive distortion is prone to affect voice production through reduced cognitive, pulmonary, and muscular functionality. This sensitivity inspired using voice as a biomarker to examine disorders that affect the voice. Technological improvements and emerging machine learning (ML) technologies have enabled possibilities of extracting digital vocal features from the voice for automated diagnosis and monitoring systems.

OBJECTIVE

This study aims to summarize a comprehensive view of research on voice-affecting disorders that uses ML techniques for diagnosis and monitoring through voice samples where systematic conditions, nonlaryngeal aerodigestive disorders, and neurological disorders are specifically of interest.

METHODS

This systematic literature review (SLR) investigated the state of the art of voice-based diagnostic and monitoring systems with ML technologies, targeting voice-affecting disorders without direct relation to the voice box from the point of view of applied health technology. Through a comprehensive search string, studies published from 2012 to 2022 from the databases Scopus, PubMed, and Web of Science were scanned and collected for assessment. To minimize bias, retrieval of the relevant references in other studies in the field was ensured, and 2 authors assessed the collected studies. Low-quality studies were removed through a quality assessment and relevant data were extracted through summary tables for analysis. The articles were checked for similarities between author groups to prevent cumulative redundancy bias during the screening process, where only 1 article was included from the same author group.

RESULTS

In the analysis of the 145 included studies, support vector machines were the most utilized ML technique (51/145, 35.2%), with the most studied disease being Parkinson disease (PD; reported in 87/145, 60%, studies). After 2017, 16 additional voice-affecting disorders were examined, in contrast to the 3 investigated previously. Furthermore, an upsurge in the use of artificial neural network-based architectures was observed after 2017. Almost half of the included studies were published in last 2 years (2021 and 2022). A broad interest from many countries was observed. Notably, nearly one-half (n=75) of the studies relied on 10 distinct data sets, and 11/145 (7.6%) used demographic data as an input for ML models.

CONCLUSIONS

This SLR revealed considerable interest across multiple countries in using ML techniques for diagnosing and monitoring voice-affecting disorders, with PD being the most studied disorder. However, the review identified several gaps, including limited and unbalanced data set usage in studies, and a focus on diagnostic test rather than disorder-specific monitoring. Despite the limitations of being constrained by only peer-reviewed publications written in English, the SLR provides valuable insights into the current state of research on ML-based voice-affecting disorder diagnosis and monitoring and highlighting areas to address in future research.

Discrimination of mild cognitive impairment based on involuntary changes caused in voice elements

In this study, the technique associated with the capturing involuntary changes in voice elements caused by diseases is applied to diagnose them and a voice index is proposed to discriminate mild cognitive impairments. The participants in this study included 399 elderly people aged 65 years or older living in Matsumoto City, Nagano Prefecture, Japan. The participants were categorized into healthy and mild cognitive impairment groups based on clinical evaluation. It was hypothesized that as dementia progressed, task performance would become more challenging, and the effects on vocal cords and prosody would change significantly. In the study, voice samples of the participants were recorded while they were engaged in mental calculational tasks and during the reading of the results of the calculations written on paper. The change in prosody during the calculation from that during reading was expressed based on the difference in the acoustics. Principal component analysis was used to aggregate groups of voice features with similar characteristics of feature differences into several principal components. These principal components were combined with logistic regression analysis to propose a voice index to discriminate different mild cognitive impairment types. Discrimination accuracies of 90% and 65% were obtained for discriminations using the proposed index on the training and verification data (obtained from a population different from the training data), respectively. Therefore, it is suggested that the proposed index may be utilized as a means for discriminating mild cognitive impairments.

Narrative recall in relapsing-remitting multiple sclerosis: A potentially useful speech task for detecting subtle cognitive changes

Our research studied relapsing-remitting multiple sclerosis (RRMS). In half of the RRMS cases, mild cognitive difficulties are present, but often remain undetected despite their adverse effects on individuals' daily life. Detecting subtle cognitive alterations using speech analysis have rarely been implemented in MS research. We applied automatic speech recognition technology to devise a speech task with potential diagnostic value. Therefore, we used two narrative tasks adjusted for the neural and cognitive characteristics of RRMS; namely narrative recall and personal narrative. In addition to speech analysis, we examined the information processing speed, working memory, verbal fluency, and naming skills. Twenty-one participants with RRMS and 21 gender-, age-, and education-matched healthy controls took part in the study. All the participants with RRMS achieved a normal performance on Addenbrooke's Cognitive Examination. The following parameters of speech were measured: articulation and speech rate, the proportion, duration, frequency, and average length of silent and filled pauses. We found significant differences in the temporal parameters between groups and speech tasks. ROC analysis produced high classification accuracy for the narrative recall task (0.877 and 0.866), but low accuracy for the personal narrative task (0.617 and 0.592). The information processing speed affected the speech of the RRMS group but not that of the control group. The higher cognitive load of the narrative recall task may be the cause of significant changes in the speech of the RRMS group relative to the controls. Results suggest that narrative recall task may be effective for detecting subtle cognitive changes in RRMS.

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.

Landmark-based analysis of speech differentiates conversational from clear speech in speakers with muscle tension dysphonia

This study evaluated the feasibility of differentiating conversational and clear speech produced by individuals with muscle tension dysphonia (MTD) using landmark-based analysis of speech (LMBAS). Thirty-four adult speakers with MTD recorded conversational and clear speech, with 27 of them able to produce clear speech. The recordings of these individuals were analyzed with the open-source LMBAS program, SpeechMark®, matlab Toolbox version 1.1.2. The results indicated that glottal landmarks, burst onset landmarks, and the duration between glottal landmarks differentiated conversational speech from clear speech. LMBAS shows potential as an approach for detecting the difference between conversational and clear speech in dysphonic individuals.

Varied performance of picture description task as a screening tool across MCI subtypes

A picture description task is a component of Miro Health's platform for self-administration of neurobehavioral assessments. Picture description has been used as a screening tool for identification of individuals with Alzheimer's disease and mild cognitive impairment (MCI), but currently requires in-person administration and scoring by someone with access to and familiarity with a scoring rubric. The Miro Health implementation allows broader use of this assessment through self-administration and automated processing, analysis, and scoring to deliver clinically useful quantifications of the users' speech production, vocal characteristics, and language. Picture description responses were collected from 62 healthy controls (HC), and 33 participants with MCI: 18 with amnestic MCI (aMCI) and 15 with non-amnestic MCI (naMCI). Speech and language features and contrasts between pairs of features were evaluated for differences in their distributions in the participant subgroups. Picture description features were selected and combined using penalized logistic regression to form risk scores for classification of HC versus MCI as well as HC versus specific MCI subtypes. A picture-description based risk score distinguishes MCI and HC with an area under the receiver operator curve (AUROC) of 0.74. When contrasting specific subtypes of MCI and HC, the classifiers have an AUROC of 0.88 for aMCI versus HC and and AUROC of 0.61 for naMCI versus HC. Tests of association of individual features or contrasts of pairs of features with HC versus aMCI identified 20 features with p-values below 5e-3 and False Discovery Rates (FDRs) at or below 0.113, and 61 contrasts with p-values below 5e-4 and FDRs at or below 0.132. Findings suggest that performance of picture description as a screening tool for MCI detection will vary greatly by MCI subtype or by the proportion of various subtypes in an undifferentiated MCI population.

The foundation and architecture of precision medicine in neurology and psychiatry

Neurological and psychiatric diseases have high degrees of genetic and pathophysiological heterogeneity, irrespective of clinical manifestations. Traditional medical paradigms have focused on late-stage syndromic aspects of these diseases, with little consideration of the underlying biology. Advances in disease modeling and methodological design have paved the way for the development of precision medicine (PM), an established concept in oncology with growing attention from other medical specialties. We propose a PM architecture for central nervous system diseases built on four converging pillars: multimodal biomarkers, systems medicine, digital health technologies, and data science. We discuss Alzheimer's disease (AD), an area of significant unmet medical need, as a case-in-point for the proposed framework. AD can be seen as one of the most advanced PM-oriented disease models and as a compelling catalyzer towards PM-oriented neuroscience drug development and advanced healthcare practice.

Automatic Detection of Putative Mild Cognitive Impairment from Speech Acoustic Features in Mandarin-Speaking Elders

BACKGROUND

To date, the reliable detection of mild cognitive impairment (MCI) remains a significant challenge for clinicians. Very few studies investigated the sensitivity of acoustic features in detecting Mandarin-speaking elders at risk for MCI, defined as "putative MCI" (pMCI).

OBJECTIVE

This study sought to investigate the possibility of using automatically extracted speech acoustic features to detect elderly people with pMCI and reveal the potential acoustic markers of cognitive decline at an early stage.

METHODS

Forty-one older adults with pMCI and 41 healthy elderly controls completed four reading tasks (syllable utterance, tongue twister, diadochokinesis, and short sentence reading), from which acoustic features were extracted automatically to train machine learning classifiers. Correlation analysis was employed to evaluate the relationship between classifier predictions and participants' cognitive ability measured by Mini-Mental State Examination 2.

RESULTS

Classification results revealed that some temporal features (e.g., speech rate, utterance duration, and the number of silent pauses), spectral features (e.g., variability of F1 and F2), and energy features (e.g., SD of peak intensity and SD of intensity range) were effective predictors of pMCI. The best classification result was achieved in the Random Forest classifier (accuracy = 0.81, AUC = 0.81). Correlation analysis uncovered a strong negative correlation between participants' cognitive test scores and the probability estimates of pMCI in the Random Forest classifier, and a modest negative correlation in the Support Vector Machine classifier.

CONCLUSIONS

The automatic acoustic analysis of speech could provide a promising non-invasive way to assess and monitor the early cognitive decline in Mandarin-speaking elders.

Vocal biomarker predicts fatigue in people with COVID-19: results from the prospective Predi-COVID cohort study

OBJECTIVE

To develop a vocal biomarker for fatigue monitoring in people with COVID-19.

DESIGN

Prospective cohort study.

SETTING

Predi-COVID data between May 2020 and May 2021.

PARTICIPANTS

A total of 1772 voice recordings were used to train an AI-based algorithm to predict fatigue, stratified by gender and smartphone's operating system (Android/iOS). The recordings were collected from 296 participants tracked for 2 weeks following SARS-CoV-2 infection.

PRIMARY AND SECONDARY OUTCOME MEASURES

Four machine learning algorithms (logistic regression, k-nearest neighbours, support vector machine and soft voting classifier) were used to train and derive the fatigue vocal biomarker. The models were evaluated based on the following metrics: area under the curve (AUC), accuracy, F1-score, precision and recall. The Brier score was also used to evaluate the models' calibrations.

RESULTS

The final study population included 56% of women and had a mean (±SD) age of 40 (±13) years. Women were more likely to report fatigue (p<0.001). We developed four models for Android female, Android male, iOS female and iOS male users with a weighted AUC of 86%, 82%, 79%, 85% and a mean Brier Score of 0.15, 0.12, 0.17, 0.12, respectively. The vocal biomarker derived from the prediction models successfully discriminated COVID-19 participants with and without fatigue.

CONCLUSIONS

This study demonstrates the feasibility of identifying and remotely monitoring fatigue thanks to voice. Vocal biomarkers, digitally integrated into telemedicine technologies, are expected to improve the monitoring of people with COVID-19 or Long-COVID.

TRIAL REGISTRATION NUMBER

NCT04380987.

Speech silence character as a diagnostic biomarker of early cognitive decline and its functional mechanism: a multicenter cross-sectional cohort study

BACKGROUND

Language deficits frequently occur during the prodromal stages of Alzheimer's disease (AD). However, the characteristics of linguistic impairment and its underlying mechanism(s) remain to be explored for the early diagnosis of AD.

METHODS

The percentage of silence duration (PSD) of 324 subjects was analyzed, including patients with AD, amnestic mild cognitive impairment (aMCI), and normal controls (NC) recruited from the China multi-center cohort, and the diagnostic efficiency was replicated from the Pitt center cohort. Furthermore, the specific language network involved in the fragmented speech was analyzed using task-based functional magnetic resonance.

RESULTS

In the China cohort, PSD increased significantly in aMCI and AD patients. The area under the curve of the receiver operating characteristic curves is 0.74, 0.84, and 0.80 in the classification of NC/aMCI, NC/AD, and NC/aMCI+AD. In the Pitt center cohort, PSD was verified as a reliable diagnosis biomarker to differentiate mild AD patients from NC. Next, in response to fluency tasks, clusters in the bilateral inferior frontal gyrus, precentral gyrus, left inferior temporal gyrus, and inferior parietal lobule deactivated markedly in the aMCI/AD group (cluster-level P < 0.05, family-wise error (FWE) corrected). In the patient group (AD+aMCI), higher activation level of the right pars triangularis was associated with higher PSD in in both semantic and phonemic tasks.

CONCLUSIONS

PSD is a reliable diagnostic biomarker for the early stage of AD and aMCI. At as early as aMCI phase, the brain response to fluency tasks was inhibited markedly, partly explaining why PSD was elevated simultaneously.

Technology for dementia care: benefits, opportunities and concerns

The rise in incidence and prevalence of dementia globally is driving the technological revolution to develop effective healthcare solutions for dementia patients and caretakers. These solutions promise enhanced mechanisms to manage lifestyle, monitor cognitive performance, ensure the security and safety of the elderly, and deliver rehabilitation services. In this viewpoint, we contextualize the role of technology in dementia care by elaborating on these solutions and discussing the associated benefits, opportunities, and concerns.

A comparison of techniques for deriving clustering and switching scores from verbal fluency word lists

Objective

To compare techniques for computing clustering and switching scores in terms of agreement, correlation, and empirical value as predictors of incident cognitive impairment (ICI).

Methods

We transcribed animal and letter F fluency recordings on 640 cases of ICI and matched controls from a national epidemiological study, amending each transcription with word timings. We then calculated clustering and switching scores, as well as scores indexing speed of responses, using techniques described in the literature. We evaluated agreement among the techniques with Cohen’s κ and calculated correlations among the scores. After fitting a base model with raw scores, repetitions, and intrusions, we fit a series of Bayesian logistic regression models adding either clustering and switching scores or speed scores, comparing the models in terms of several metrics. We partitioned the ICI cases into acute and progressive cases and repeated the regression analysis for each group.

Results

For animal fluency, we found that models with speed scores derived using the slope difference algorithm achieved the best values of the Watanabe–Akaike Information Criterion (WAIC), but with good net reclassification improvement (NRI) only for the progressive group (8.2%). For letter fluency, different models excelled for prediction of acute and progressive cases. For acute cases, NRI was best for speed scores derived from a network model (3.4%), while for progressive cases, the best model used clustering and switching scores derived from the same network model (5.1%). Combining variables from the best animal and letter F models led to marginal improvements in model fit and NRI only for the all-cases and acute-cases analyses.

Conclusion

Speed scores improve a base model for predicting progressive cognitive impairment from animal fluency. Letter fluency scores may provide complementary information.

Automated detection of mild cognitive impairment and dementia from voice recordings: A natural language processing approach

INTRODUCTION

Automated computational assessment of neuropsychological tests would enable widespread, cost-effective screening for dementia.

METHODS

A novel natural language processing approach is developed and validated to identify different stages of dementia based on automated transcription of digital voice recordings of subjects' neuropsychological tests conducted by the Framingham Heart Study (n = 1084). Transcribed sentences from the test were encoded into quantitative data and several models were trained and tested using these data and the participants' demographic characteristics.

RESULTS

Average area under the curve (AUC) on the held-out test data reached 92.6%, 88.0%, and 74.4% for differentiating Normal cognition from Dementia, Normal or Mild Cognitive Impairment (MCI) from Dementia, and Normal from MCI, respectively.

DISCUSSION

The proposed approach offers a fully automated identification of MCI and dementia based on a recorded neuropsychological test, providing an opportunity to develop a remote screening tool that could be adapted easily to any language.

Structural Correlates of Overt Sentence Reading in Mild Cognitive Impairment and Mild-to-Moderate Alzheimer's Disease

BACKGROUND

Overt sentence reading in mild cognitive impairment (MCI) and mild-tomoderate Alzheimer's disease (AD) has been associated with slowness of speech, characterized by a higher number of pauses, shorter speech units and slower speech rate and attributed to reduced working memory/ attention and language capacity.

OBJECTIVE

This preliminary case-control study investigates whether the temporal organization of speech is associated with the volume of brain regions involved in overt sentence reading and explores the discriminative ability of temporal speech parameters and standard volumetric MRI measures for the classification of MCI and AD.

METHODS

Individuals with MCI, mild-to-moderate AD, and healthy controls (HC) had a structural MRI scan and read aloud sentences varying in cognitive-linguistic demand (length). The association between speech features and regional brain volumes was examined by linear mixed-effect modeling. Genetic programming was used to explore the discriminative ability of temporal and MRI features.

RESULTS

Longer sentences, slower speech rate, and a higher number of pauses and shorter interpausal units were associated with reduced volumes of the reading network. Speech-based classifiers performed similarly to the MRI-based classifiers for MCI-HC (67% vs. 68%) and slightly better for AD-HC (80% vs. 64%) and AD-MCI (82% vs. 59%). Adding the speech features to the MRI features slightly improved the performance of MRI-based classification for AD-HC and MCI-HC but not HC-MCI.

CONCLUSION

The temporal organization of speech in overt sentence reading reflects underlying volume reductions. It may represent a sensitive marker for early assessment of structural changes and cognitive- linguistic deficits associated with healthy aging, MCI, and AD.

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

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

Verbal fluency response times predict incident cognitive impairment

Introduction

In recent decades, researchers have defined novel methods for scoring verbal fluency tasks. In this work, we evaluate novel scores based on speed of word responses.

Methods

We transcribed verbal fluency recordings from 641 cases of incident cognitive impairment (ICI) and matched controls, all participants in a large national epidemiological study. Timing measurements of utterances were used to calculate a speed score for each recording. Traditional raw and speed scores were entered into Cox proportional hazards (CPH) regression models predicting time to ICI.

Results

Concordance of the CPH model with speed scores was 0.599, an improvement of 3.4% over a model with only raw scores and demographics. Scores with significant effects included animals raw and speed scores, and letter F speed score.

Discussion

Novel verbal fluency scores based on response times could enable use of remotely administered fluency tasks for early detection of cognitive decline.

Highlights

 The current work evaluates prognostication with verbal fluency speed scores. These speed scores improve survival models predicting cognitive decline. Cases with progressive decline have some characteristics suggestive of Alzheimer's disease. The subset of acute decliners is probably pathologically heterogeneous.

Temporal speech parameters detect mild cognitive impairment in different languages: validation and comparison of the Speech-GAP Test® in English and Hungarian

BACKGROUND

The development of automatic speech recognition (ASR) technology allows the analysis of temporal (time-based) speech parameters characteristic of mild cognitive impairment (MCI). However, no information has been available on whether the analysis of spontaneous speech can be used with the same efficiency in different language environments.

OBJECTIVE

The main goal of this international pilot study is to address the question whether the Speech-Gap Test® (S-GAP Test®), previously tested in the Hungarian language, is appropriate for and applicable to the recognition of MCI in other languages such as English.

METHOD

After an initial screening of 88 individuals, English-speaking (n = 33) and Hungarian-speaking (n = 33) participants were classified as having MCI or as healthy controls (HC) based on Petersen's criteria. Speech of each participant was recorded via a spontaneous speech task. 15 temporal parameters were determined and calculated by means of ASR.

RESULTS

Seven temporal parameters in the English-speaking sample and 5 in the Hungarian-speaking sample showed significant differences between the MCI and the HC group. Receiver operating characteristics (ROC) analysis clearly distinguished the English-speaking MCI cases from the HC group based on speech tempo and articulation tempo with 100% sensitivity, and on three more temporal parameters with high sensitivity (85.7%). In the Hungarian-speaking sample, the ROC analysis showed similar sensitivity rates (92.3%).

CONCLUSION

The results of this study in different native-speaking populations suggest that changes in acoustic parameters detected by the S-GAP Test® might be present across different languages.

Multimodal MRI cerebral correlates of verbal fluency switching and its impairment in women with depression

BACKGROUND

The search of biomarkers in the field of depression requires easy implementable tests that are biologically rooted. Qualitative analysis of verbal fluency tests (VFT) are good candidates, but its cerebral correlates are unknown.

METHODS

We collected qualitative semantic and phonemic VFT scores along with grey and white matter anatomical MRI of depressed (n = 26) and healthy controls (HC, n = 25) women. Qualitative VFT variables are the "clustering score" (i.e. the ability to produce words within subcategories) and the "switching score" (i.e. the ability to switch between clusters). The clustering and switching scores were automatically calculated using a data-driven approach. Brain measures were cortical thickness (CT) and fractional anisotropy (FA). We tested for associations between CT, FA and qualitative VFT variables within each group.

RESULTS

Patients had reduced switching VFT scores compared to HC. Thicker cortex was associated with better switching score in semantic VFT bilaterally in the frontal (superior, rostral middle and inferior gyri), parietal (inferior parietal lobule including the supramarginal gyri), temporal (transverse and fusiform gyri) and occipital (lingual gyri) lobes in the depressed group. Positive association between FA and the switching score in semantic VFT was retrieved in depressed patients within the corpus callosum, right inferior fronto-occipital fasciculus, right superior longitudinal fasciculus extending to the anterior thalamic radiation (all p < 0.05, corrected).

CONCLUSION

Together, these results suggest that automatic qualitative VFT scores are associated with brain anatomy and reinforce its potential use as a surrogate for depression cerebral bases.

Using Automatic Speech Recognition to Assess Thai Speech Language Fluency in the Montreal Cognitive Assessment (MoCA)

The Montreal cognitive assessment (MoCA), a widely accepted screening tool for identifying patients with mild cognitive impairment (MCI), includes a language fluency test of verbal functioning; its scores are based on the number of unique correct words produced by the test taker. However, it is possible that unique words may be counted differently for various languages. This study focuses on Thai as a language that differs from English in terms of word combinations. We applied various automatic speech recognition (ASR) techniques to develop an assisted scoring system for the MoCA language fluency test with Thai language support. This was a challenge because Thai is a low-resource language for which domain-specific data are not publicly available, especially speech data from patients with MCIs. Furthermore, the great variety of pronunciation, intonation, tone, and accent of the patients, all of which might differ from healthy controls, bring more complexity to the model. We propose a hybrid time delay neural network hidden Markov model (TDNN-HMM) architecture for acoustic model training to create our ASR system that is robust to environmental noise and to the variation of voice quality impacted by MCI. The LOTUS Thai speech corpus was incorporated into the training set to improve the model’s generalization. A preprocessing algorithm was implemented to reduce the background noise and improve the overall data quality before feeding data into the TDNN-HMM system for automatic word detection and language fluency score calculation. The results show that the TDNN-HMM model in combination with data augmentation using lattice-free maximum mutual information (LF-MMI) objective function provides a word error rate (WER) of 30.77%. To our knowledge, this is the first study to develop an ASR with Thai language support to automate the scoring system of MoCA’s language fluency assessment.

Automated text-level semantic markers of Alzheimer's disease

INTRODUCTION

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

METHODS

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

RESULTS

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

DISCUSSION

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

Speech- and Language-Based Classification of Alzheimer's Disease: A Systematic Review

Background: Alzheimer’s disease (AD) has paramount importance due to its rising prevalence, the impact on the patient and society, and the related healthcare costs. However, current diagnostic techniques are not designed for frequent mass screening, delaying therapeutic intervention and worsening prognoses. To be able to detect AD at an early stage, ideally at a pre-clinical stage, speech analysis emerges as a simple low-cost non-invasive procedure. Objectives: In this work it is our objective to do a systematic review about speech-based detection and classification of Alzheimer’s Disease with the purpose of identifying the most effective algorithms and best practices. Methods: A systematic literature search was performed from Jan 2015 up to May 2020 using ScienceDirect, PubMed and DBLP. Articles were screened by title, abstract and full text as needed. A manual complementary search among the references of the included papers was also performed. Inclusion criteria and search strategies were defined a priori. Results: We were able: to identify the main resources that can support the development of decision support systems for AD, to list speech features that are correlated with the linguistic and acoustic footprint of the disease, to recognize the data models that can provide robust results and to observe the performance indicators that were reported. Discussion: A computational system with the adequate elements combination, based on the identified best-practices, can point to a whole new diagnostic approach, leading to better insights about AD symptoms and its disease patterns, creating conditions to promote a longer life span as well as an improvement in patient quality of life. The clinically relevant results that were identified can be used to establish a reference system and help to define research guidelines for future developments.

Automatic Assessment of Loneliness in Older Adults Using Speech Analysis on Responses to Daily Life Questions

Loneliness is a perceived state of social and emotional isolation that has been associated with a wide range of adverse health effects in older adults. Automatically assessing loneliness by passively monitoring daily behaviors could potentially contribute to early detection and intervention for mitigating loneliness. Speech data has been successfully used for inferring changes in emotional states and mental health conditions, but its association with loneliness in older adults remains unexplored. In this study, we developed a tablet-based application and collected speech responses of 57 older adults to daily life questions regarding, for example, one's feelings and future travel plans. From audio data of these speech responses, we automatically extracted speech features characterizing acoustic, prosodic, and linguistic aspects, and investigated their associations with self-rated scores of the UCLA Loneliness Scale. Consequently, we found that with increasing loneliness scores, speech responses tended to have less inflections, longer pauses, reduced second formant frequencies, reduced variances of the speech spectrum, more filler words, and fewer positive words. The cross-validation results showed that regression and binary-classification models using speech features could estimate loneliness scores with an R 2 of 0.57 and detect individuals with high loneliness scores with 95.6% accuracy, respectively. Our study provides the first empirical results suggesting the possibility of using speech data that can be collected in everyday life for the automatic assessments of loneliness in older adults, which could help develop monitoring technologies for early detection and intervention for mitigating loneliness.

A Comparison of Speech Features between Mild Cognitive Impairment and Healthy Aging Groups

Background and Purpose

Language dysfunction is a symptom common to patients with Alzheimer's disease (AD). Speech feature analysis may be a patient-friendly screening test for early-stage AD. We aimed to investigate the speech features of amnestic mild cognitive impairment (aMCI) compared to normal controls (NCs).

Methods

Spoken responses to test questions were recorded with a microphone placed 15 cm in front of each participant. Speech samples delivered in response to four spoken test prompts (free speech test, Mini-Mental State Examination [MMSE], picture description test, and sentence repetition test) were obtained from 98 patients with aMCI and 139 NCs. Each recording was transcribed, with speech features noted. The frequency of the ten speech features assessed was evaluated to compare speech abilities between the test groups.

Results

Among the ten speech features, the frequency of pauses (p=0.001) and mumbles (p=0.001) were significantly higher in patients with aMCI than in NCs. Moreover, MMSE score was found to negatively correlate with the frequency of pauses (r=−0.441, p<0.001) and mumbles (r=−0.341, p<0.001).

Conclusions

Frequent pauses and mumbles reflect cognitive decline in aMCI patients in episodic and semantic memory tests. Speech feature analysis may prove to be a speech-based biomarker for screening early-stage cognitive impairment.

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.

Detection of COVID-19 from voice, cough and breathing patterns: Dataset and preliminary results

COVID-19 heavily affects breathing and voice and causes symptoms that make patients' voices distinctive, creating recognizable audio signatures. Initial studies have already suggested the potential of using voice as a screening solution. In this article we present a dataset of voice, cough and breathing audio recordings collected from individuals infected by SARS-CoV-2 virus, as well as non-infected subjects via large scale crowdsourced campaign. We describe preliminary results for detection of COVID-19 from cough patterns using standard acoustic features sets, wavelet scattering features and deep audio embeddings extracted from low-level feature representations (VGGish and OpenL3). Our models achieve accuracy of 88.52%, sensitivity of 88.75% and specificity of 90.87%, confirming the applicability of audio signatures to identify COVID-19 symptoms. We furthermore provide an in-depth analysis of the most informative acoustic features and try to elucidate the mechanisms that alter the acoustic characteristics of coughs of people with COVID-19.

Detection of Mild Cognitive Impairment Through Natural Language and Touchscreen Typing Processing

Mild cognitive impairment (MCI), an identified prodromal stage of Alzheimer's Disease (AD), often evades detection in the early stages of the condition, when existing diagnostic methods are employed in the clinical setting. From an alternative perspective, smartphone interaction behavioral data, unobtrusively acquired in a non-clinical setting, can assist the screening and monitoring of MCI and its symptoms' progression. In this vein, the diagnostic ability of digital biomarkers, drawn from Fine Motor Impairment (FMI)- and Spontaneous Written Speech (SWS)-related data analysis, are examined here. In particular, keystroke dynamics derived from touchscreen typing activities, using Convolutional Neural Networks, along with linguistic features of SWS through Natural Language Processing (NLP), were used to distinguish amongst MCI patients and healthy controls (HC). Analytically, three indices of FMI (rigidity, bradykinesia and alternate finger tapping) and nine NLP features, related with lexical richness, grammatical, syntactical complexity, and word deficits, formed the feature space. The proposed approach was tested on two demographically matched groups of 11 MCI patients and 12 HC, having undergone the same neuropsychological tests, producing 4,930 typing sessions and 78 short texts, within 6 months, for analysis. A cascaded-classifier scheme was realized under three different feature combinations and validated via a Leave-One-Subject-Out cross-validation scheme. The acquired results have shown: (a) keystroke features with a k-NN classifier achieved an Area Under Curve (AUC) of 0.78 [95% confidence interval (CI):0.68-0.88; specificity/sensitivity (SP/SE): 0.64/0.92], (b) NLP features with a Logistic regression classifier achieved an AUC of 0.76 (95% CI: 0.65-0.85; SP/SE: 0.80/0.71), and (c) an ensemble model with the fusion of keystroke and NLP features resulted in AUC of 0.75 (95% CI:0.63-0.86; SP/SE 0.90/0.60). The current findings indicate the potentiality of new digital biomarkers to capture early stages of cognitive decline, providing a highly specific remote screening tool in-the-wild.

Tablet-Based Automatic Assessment for Early Detection of Alzheimer's Disease Using Speech Responses to Daily Life Questions

Health-monitoring technologies for automatically detecting the early signs of Alzheimer's disease (AD) have become increasingly important. Speech responses to neuropsychological tasks have been used for quantifying changes resulting from AD and differentiating AD and mild cognitive impairment (MCI) from cognitively normal (CN). However, whether and how other types of speech tasks with less burden on older adults could be used for detecting early signs of AD remains unexplored. In this study, we developed a tablet-based application and compared speech responses to daily life questions with those to neuropsychological tasks in terms of differentiating MCI from CN. We found that in daily life questions, around 80% of speech features showing significant differences between CN and MCI overlapped those showing significant differences in both our study and other studies using neuropsychological tasks, but the number of significantly different features as well as their effect sizes from life questions decreased compared with those from neuropsychological tasks. On the other hand, the results of classification models for detecting MCI by using the speech features showed that daily life questions could achieve high accuracy, i.e., 86.4%, comparable to neuropsychological tasks by using eight questions against all five neuropsychological tasks. Our results indicate that, while daily life questions may elicit weaker but statistically discernable differences in speech responses resulting from MCI than neuropsychological tasks, combining them could be useful for detecting MCI with comparable performance to using neuropsychological tasks, which could help develop health-monitoring technologies for early detection of AD in a less burdensome manner.

Artificial Intelligence and Its Application to Minimal Hepatic Encephalopathy Diagnosis

Hepatic encephalopathy (HE) is a brain dysfunction caused by liver insufficiency and/or portosystemic shunting. HE manifests as a spectrum of neurological or psychiatric abnormalities. Diagnosis of overt HE (OHE) is based on the typical clinical manifestation, but covert HE (CHE) has only very subtle clinical signs and minimal HE (MHE) is detected only by specialized time-consuming psychometric tests, for which there is still no universally accepted gold standard. Significant progress has been made in artificial intelligence and its application to medicine. In this review, we introduce how artificial intelligence has been used to diagnose minimal hepatic encephalopathy thus far, and we discuss its further potential in analyzing speech and handwriting data, which are probably the most accessible data for evaluating the cognitive state of the patient.