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

Abstract

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 novel speech analysis algorithm to detect cognitive impairment in a Spanish population

“…In fact, machine learning (ML) techniques have been developed utilizing various speech and linguistic biomarkers to identify individuals with MCI ( 26 ), early AD ( 27 , 28 ), dementia ( 29 ), Parkinson’s disease ( 30 ), and frontotemporal disorders ( 31 ). For instance, Hajjar and colleagues ( 27 ) found both acoustic and lexical-semantic biomarkers to be sensitive to cognitive impairment and disease progression in the early stages of AD.…”

“…In fact, machine learning (ML) techniques have been developed utilizing various speech and linguistic biomarkers to identify individuals with MCI ( 26 ), early AD ( 27 , 28 ), dementia ( 29 ), Parkinson’s disease ( 30 ), and frontotemporal disorders ( 31 ). For instance, Hajjar and colleagues ( 27 ) found both acoustic and lexical-semantic biomarkers to be sensitive to cognitive impairment and disease progression in the early stages of AD. Several additional studies have demonstrated efficacy of computer-assisted linguistic processing algorithms in detecting speech differences between normal and impaired individuals in the English language ( 32 , 33 ).…”

Longitudinal observational cohort study: Speech for Intelligent cognition change tracking and DEtection of Alzheimer’s Disease (SIDE-AD)

“…In our own systematic review on the potential of using interactive AI methods to detect AD biomarkers, we concluded that when compared with traditional neuropsychological assessment methods, speech and language technology were at least equally discriminative between different groups. 14 Interestingly, speech-based markers have been found to detect AD pathology such as amyloid‐β status, 19 but evidence also suggests that people with higher amyloid levels (both asymptomatic and those with mild cognitive impairment) exhibit a greater rate of decline in episodic memory and language, 20 suggesting the causal relation between speech and AD pathology should be explored further. Some of the most promising AD markers in speech may be lexico-semantic, 21 meaning the use of deictic words such as those referring to specific time (eg, now, tomorrow), place (eg, here, at home) or person (eg, I, the person).…”

Early ultrasonic vocalization deficits and related thyroarytenoid muscle pathology in the transgenic TgF344-AD rat model of Alzheimer’s disease

“…Importantly, vocal deficits and disordered communication also occur early during disease progression, often develop prior to the onset of classic memory and cognitive dysfunction ( Garrard et al, 2005 ; Hajjar et al, 2023 ), worsen over time, and significantly reduce health and quality of life ( Humbert et al, 2010 ; Mueller et al, 2018a ) with devastating associated economic burden ( Woodward, 2013 ). Although signs/symptoms of communication deficits have been traditionally classified as mid-to late-stage events ( Ross et al, 1990 ), recent studies suggest earlier prodromal involvement of other regions in the central and peripheral nervous systems ( Delaby et al, 2015 ; King et al, 2018 , 2019 ; Morris et al, 2019 ; Trushina, 2019 ; Cheng et al, 2020 ; Leuzy et al, 2022a ), potentially directly impacting laryngeal coordination and communication ( Mueller et al, 2018a ; Mahon and Lachman, 2022 ).…”