Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment

Digital voice recordings can offer affordable, accessible ways to evaluate behavior and function. We assessed how combining different low-level voice descriptors can evaluate cognitive status. Using voice recordings from neuropsychological exams at the Framingham Heart Study, we developed a machine...

Descripción completa

Detalles Bibliográficos
Autores principales: Karjadi, Cody, Xue, Chonghua, Cordella, Claire, Kiran, Swathi, Paschalidis, Ioannis Ch., Au, Rhoda, Kolachalama, Vijaya B.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: IOS Press 2023
Materias:
Short Communication
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10657667/
https://www.ncbi.nlm.nih.gov/pubmed/37840494
http://dx.doi.org/10.3233/JAD-230560
_version_ 1785148187052343296
author Karjadi, Cody
Xue, Chonghua
Cordella, Claire
Kiran, Swathi
Paschalidis, Ioannis Ch.
Au, Rhoda
Kolachalama, Vijaya B.
author_facet Karjadi, Cody
Xue, Chonghua
Cordella, Claire
Kiran, Swathi
Paschalidis, Ioannis Ch.
Au, Rhoda
Kolachalama, Vijaya B.
author_sort Karjadi, Cody
collection PubMed
description Digital voice recordings can offer affordable, accessible ways to evaluate behavior and function. We assessed how combining different low-level voice descriptors can evaluate cognitive status. Using voice recordings from neuropsychological exams at the Framingham Heart Study, we developed a machine learning framework fusing spectral, prosodic, and sound quality measures early in the training cycle. The model’s area under the receiver operating characteristic curve was 0.832 (±0.034) in differentiating persons with dementia from those who had normal cognition. This offers a data-driven framework for analyzing minimally processed voice recordings for cognitive assessment, highlighting the value of digital technologies in disease detection and intervention.
format Online
Article
Text
id pubmed-10657667
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher IOS Press
record_format MEDLINE/PubMed
spelling pubmed-106576672023-11-19 Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment Karjadi, Cody Xue, Chonghua Cordella, Claire Kiran, Swathi Paschalidis, Ioannis Ch. Au, Rhoda Kolachalama, Vijaya B. J Alzheimers Dis Short Communication Digital voice recordings can offer affordable, accessible ways to evaluate behavior and function. We assessed how combining different low-level voice descriptors can evaluate cognitive status. Using voice recordings from neuropsychological exams at the Framingham Heart Study, we developed a machine learning framework fusing spectral, prosodic, and sound quality measures early in the training cycle. The model’s area under the receiver operating characteristic curve was 0.832 (±0.034) in differentiating persons with dementia from those who had normal cognition. This offers a data-driven framework for analyzing minimally processed voice recordings for cognitive assessment, highlighting the value of digital technologies in disease detection and intervention. IOS Press 2023-11-07 /pmc/articles/PMC10657667/ /pubmed/37840494 http://dx.doi.org/10.3233/JAD-230560 Text en © 2023 – The authors. Published by IOS Press https://creativecommons.org/licenses/by-nc/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution Non-Commercial (CC BY-NC 4.0) License (https://creativecommons.org/licenses/by-nc/4.0/) , which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Short Communication
Karjadi, Cody
Xue, Chonghua
Cordella, Claire
Kiran, Swathi
Paschalidis, Ioannis Ch.
Au, Rhoda
Kolachalama, Vijaya B.
Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment
title Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment
title_full Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment
title_fullStr Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment
title_full_unstemmed Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment
title_short Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment
title_sort fusion of low-level descriptors of digital voice recordings for dementia assessment
topic Short Communication
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10657667/
https://www.ncbi.nlm.nih.gov/pubmed/37840494
http://dx.doi.org/10.3233/JAD-230560
work_keys_str_mv AT karjadicody fusionoflowleveldescriptorsofdigitalvoicerecordingsfordementiaassessment
AT xuechonghua fusionoflowleveldescriptorsofdigitalvoicerecordingsfordementiaassessment
AT cordellaclaire fusionoflowleveldescriptorsofdigitalvoicerecordingsfordementiaassessment
AT kiranswathi fusionoflowleveldescriptorsofdigitalvoicerecordingsfordementiaassessment
AT paschalidisioannisch fusionoflowleveldescriptorsofdigitalvoicerecordingsfordementiaassessment
AT aurhoda fusionoflowleveldescriptorsofdigitalvoicerecordingsfordementiaassessment
AT kolachalamavijayab fusionoflowleveldescriptorsofdigitalvoicerecordingsfordementiaassessment

Ejemplares similares