Background: Language is a valuable source of clinical information in Alzheimer’s disease, as it declines concurrently with neurodegeneration. Consequently, speech and language data have been extensively studied in connection with its diagnosis. Objective: Firstly, to summarize the existing findings on the use of artificial intelligence, speech, and language processing to predict cognitive decline in the context of Alzheimer’s disease. Secondly, to detail current research procedures, highlight their limitations, and suggest strategies to address them. Methods: Systematic review of original research between 2000 and 2019, registered in PROSPERO (reference CRD42018116606). An interdisciplinary search covered six databases on engineering (ACM and IEEE), psychology (PsycINFO), medicine (PubMed and Embase), and Web of Science. Bibliographies of relevant papers were screened until December 2019. Results: From 3,654 search results, 51 articles were selected against the eligibility criteria. Four tables summarize their findings: study details (aim, population, interventions, comparisons, methods, and outcomes), data details (size, type, modalities, annotation, balance, availability, and language of study), methodology (pre-processing, feature generation, machine learning, evaluation, and results), and clinical applicability (research implications, clinical potential, risk of bias, and strengths/limitations). Conclusion: Promising results are reported across nearly all 51 studies, but very few have been implemented in clinical research or practice. The main limitations of the field are poor standardization, limited comparability of results, and a degree of disconnect between study aims and clinical applications. Active attempts to close these gaps will support translation of future research into clinical practice.

Speech analysis could provide an indicator of Alzheimer's disease and help develop clinical tools for automatically detecting and monitoring disease progression. While previous studies have employed acoustic (speech) features for characterisation of Alzheimer's dementia, these studies focused on a few common prosodic features, often in combination with lexical and syntactic features which require transcription. We present a detailed study of the predictive value of purely acoustic features automatically extracted from spontaneous speech for Alzheimer's dementia detection, from a computational paralinguistics perspective. The effectiveness of several state-of-the-art paralinguistic feature sets for Alzheimer's detection were assessed on a balanced sample of DementiaBank's Pitt spontaneous speech dataset, with patients matched by gender and age. The feature sets assessed were the extended Geneva minimalistic acoustic parameter set (eGeMAPS), the emobase feature set, the ComParE 2013 feature set, and new Multi-Resolution Cochleagram (MRCG) features. Furthermore, we introduce a new active data representation (ADR) method for feature extraction in Alzheimer's dementia recognition. Results show that classification models based solely on acoustic speech features extracted through our ADR method can achieve accuracy levels comparable to those achieved by models that employ higher-level language features. Analysis of the results suggests that all feature sets contribute information not captured by other feature sets. We show that while the eGeMAPs feature set provides slightly better accuracy than other feature sets individually (71.34%), “hard fusion” of feature sets improves accuracy to 78.70%.

Introduction Decreasing the incidence of Alzheimer’s disease (AD) is a global public health priority. Early detection of AD is an important requisite for the implementation of prevention strategies towards this goal. While it is plausible that patients at the early stages of AD may exhibit subtle behavioural signs of neurodegeneration, neuropsychological testing seems unable to detect these signs in preclinical AD. Recent studies indicate that spontaneous speech data, which can be collected frequently and naturally, provide good predictors for AD detection in cohorts with a clinical diagnosis. The potential of models based on such data for detecting preclinical AD remains unknown. Methods and analysis The PREVENT-Elicitation of Dialogues (PREVENT-ED) study builds on the PREVENT Dementia project to investigate whether early behavioural signs of AD may be detected through dialogue interaction. Participants recruited through PREVENT, aged 40–59 at baseline, will be included in this study. We will use speech processing and machine learning methods to assess how well speech and visuospatial markers agree with neuropsychological, biomarker, clinical, lifestyle and genetic data from the PREVENT cohort. Ethics and dissemination There are no expected risks or burdens to participants. The procedures are not invasive and do not raise significant ethical issues. We only approach healthy consenting adults and all participants will be informed that this is an exploratory study and therefore has no diagnostic aim. Confidentiality aspects such as data encryption and storage comply with the General Data Protection Regulation and with the requirements from sponsoring bodies and ethical committees. This study has been granted ethical approval by the London-Surrey Research Ethics Committee (REC reference No: 18/LO/0860), and by Caldicott and Information Governance (reference No: CRD18048). PREVENT-ED results will be published in peer-reviewed journals.

Background: While interventions have been designed which use extended reality (XR) technology in promoting physical, mental and social well-being through cultural heritage experiences, well-defined methodologies for the assessment of such interventions is lacking. Objectives: We present a protocol for evaluating the usability and effectiveness of an XR system that mediates and facilitates access to intangible cultural heritage experiences. We aim to assess the effects of these experiences on user well-being and attitudes across four case studies: ageing societies, sustainable tourism, disappearing communities, and immigration and multiculturalism. Methods and analysis: Participants will be randomly assigned to control or intervention groups. The effects of the XR intervention on well-being will be assessed through statistical analysis of the participants’ salivary cortisol and cortisone levels, physiological signals, and subjective ratings, both pre- and post-intervention and between control and intervention groups. Usability will be measured through a system usability scale. Speech will be recorded for qualitative and natural language processing analysis. Machine learning models will be developed for prediction of affect and well-being on multimodal data. Discussion: This is one of the first international and multidisciplinary studies to explore the effects of XR-mediated intangible cultural heritage experiences on well-being and attitudes towards issues of societal importance. One of the main strengths of this study is the range of data modalities it collects, and the range of methods it employs to analyse these data in a complementary manner, including qualitative, statistical and advanced machine learning methods. Conclusion: This protocol offers a method and four case studies to assess the potential of immersive XR experiences and interventions of intangible cultural heritage as contributors to increased well-being and as actors of societal change. It stands as a reference model for further similar interventions in the field.

The ADReSS Challenge at INTERSPEECH 2020 defines a shared task through which different approaches to the automated recognition of Alzheimer's dementia based on spontaneous speech can be compared. ADReSS provides researchers with a benchmark speech dataset which has been acoustically pre-processed and balanced in terms of age and gender, defining two cognitive assessment tasks, namely: the Alzheimer's speech classification task and the neuropsychological score regression task. In the Alzheimer's speech classification task, ADReSS challenge participants create models for classifying speech as dementia or healthy control speech. In the the neuropsychological score regression task, participants create models to predict mini-mental state examination scores. This paper describes the ADReSS Challenge in detail and presents a baseline for both tasks, including feature extraction procedures and results for classification and regression models. ADReSS aims to provide the speech and language Alzheimer's research community with a platform for comprehensive methodological comparisons. This will hopefully contribute to addressing the lack of standardisation that currently affects the field and shed light on avenues for future research and clinical applicability.

Building on the success of the ADReSS Challenge at Interspeech 2020, which attracted the participation of 34 teams from across the world, the ADReSSo Challenge targets three difficult automatic prediction problems of societal and medical relevance, namely: detection of Alzheimer's Dementia, inference of cognitive testing scores, and prediction of cognitive decline. This paper presents these prediction tasks in detail, describes the datasets used, and reports the results of the baseline classification and regression models we developed for each task. A combination of acoustic and linguistic features extracted directly from audio recordings, without human intervention, yielded a baseline accuracy of 78.87% for the AD classification task, an MMSE prediction root mean squared (RMSE) error of 5.28, and 68.75% accuracy for the cognitive decline prediction task.