Phonation biomechanic analysis of Alzheimer׳s Disease cases

Development of digital voice biomarkers and associations with cognition, cerebrospinal biomarkers, and neural representation in early Alzheimer's disease

Introduction

Advances in natural language processing (NLP), speech recognition, and machine learning (ML) allow the exploration of linguistic and acoustic changes previously difficult to measure. We developed processes for deriving lexical-semantic and acoustic measures as Alzheimer's disease (AD) digital voice biomarkers.

Methods

We collected connected speech, neuropsychological, neuroimaging, and cerebrospinal fluid (CSF) AD biomarker data from 92 cognitively unimpaired (40 Aβ+) and 114 impaired (63 Aβ+) participants. Acoustic and lexical-semantic features were derived from audio recordings using ML approaches.

Results

Lexical-semantic (area under the curve [AUC] = 0.80) and acoustic (AUC = 0.77) scores demonstrated higher diagnostic performance for detecting MCI compared to Boston Naming Test (AUC = 0.66). Only lexical-semantic scores detected amyloid-β status (p = 0.0003). Acoustic scores associated with hippocampal volume (p = 0.017) while lexical-semantic scores associated with CSF amyloid-β (p = 0.007). Both measures were significantly associated with 2-year disease progression.

Discussion

These preliminary findings suggest that derived digital biomarkers may identify cognitive impairment in preclinical and prodromal AD, and may predict disease progression.

Highlights

This study derived lexical-semantic and acoustics features as Alzheimer's disease (AD) digital biomarkers.These features were derived from audio recordings using machine learning approaches.Voice biomarkers detected cognitive impairment and amyloid-β status in early stages of AD.Voice biomarkers may predict Alzheimer's disease progression.These markers significantly mapped to functional connectivity in AD-susceptible brain regions.

A Systematic Review of Expressive and Receptive Prosody in People With Dementia

Purpose This review was designed to provide a systematic overview of prosody in people with a primary diagnosis of dementia (PwD) and evaluate the potential use of prosodic features for diagnosis of dementia. Method A systematic search of five databases was conducted using Medical Subject Headings and keywords. Studies included in the review were evaluated for their methodological quality using the modified Joanna Briggs Institute checklist. Results A total of 14 articles were identified as being relevant for this review. Among the 14 articles, the methodological quality ranged, with eight rated as weak, four rated as moderate, and two rated as strong. Ten of the 14 articles had people with Alzheimer's disease (AD) as participants, and the remaining four had people with frontotemporal dementia as participants. Four articles focused on receptive prosody, another six focused on expressive prosody, and the remaining four articles were investigations into both. The 14 articles presented inconsistent findings, and various tasks were used to measure prosodic features in PwD in the articles. Prosody was studied as a diagnostic tool for dementia in four of the articles, all of which were based on expressive prosody in individuals with AD. Among the four articles, three proposed the use of automatic speech analysis for diagnosis of AD. Conclusions This review demonstrates that prosody in PwD is an underinvestigated area. In particular, it was concerning that most articles were of weak methodological quality. Nevertheless, it was found that prosody may be a potential diagnostic tool for assessing dementia. More studies that replicate the existing studies and those with stronger methodology are needed to confirm that receptive and/or expressive prosody can be used for dementia diagnosis.

On the analysis of speech and disfluencies for automatic detection of Mild Cognitive Impairment

Alzheimer’s disease is characterized by a progressive and irreversible cognitive deterioration. In a previous stage, the so-called Mild Cognitive Impairment or cognitive loss appears. Nevertheless, this previous stage does not seem sufficiently severe to interfere in independent abilities of daily life, so it is usually diagnosed inappropriately. Thus, its detection is a crucial challenge to be addressed by medical specialists. This paper presents a novel proposal for such early diagnosis based on automatic analysis of speech and disfluencies, and Deep Learning methodologies. The proposed tools could be useful for supporting Mild Cognitive Impairment diagnosis. The Deep Learning approach includes Convolutional Neural Networks and nonlinear multifeature modeling. Additionally, an automatic hybrid methodology is used in order to select the most relevant features by means of nonparametric Mann–Whitney U test and Support Vector Machine Attribute evaluation.