Lexical Speech Features of Spontaneous Speech in Older Persons With and Without Cognitive Impairment: Reliability Analysis.
Alzheimer’s disease
cognitive dysfunction
early diagnosis
psychometrics
speech
technology assessment
Journal
JMIR aging
ISSN: 2561-7605
Titre abrégé: JMIR Aging
Pays: Canada
ID NLM: 101740387
Informations de publication
Date de publication:
10 Oct 2023
10 Oct 2023
Historique:
received:
14
02
2023
revised:
19
06
2023
accepted:
20
08
2023
medline:
11
10
2023
pubmed:
11
10
2023
entrez:
11
10
2023
Statut:
epublish
Résumé
Speech analysis data are promising digital biomarkers for the early detection of Alzheimer disease. However, despite its importance, very few studies in this area have examined whether older adults produce spontaneous speech with characteristics that are sufficiently consistent to be used as proxy markers of cognitive status. This preliminary study seeks to investigate consistency across lexical characteristics of speech in older adults with and without cognitive impairment. A total of 39 older adults from a larger, ongoing study (age: mean 81.1, SD 5.9 years) were included. Participants completed neuropsychological testing and both picture description tasks and expository tasks to elicit speech. Participants with T-scores of ≤40 on ≥2 cognitive tests were categorized as having mild cognitive impairment (MCI). Speech features were computed automatically by using Python and the Natural Language Toolkit. Reliability indices based on mean correlations for picture description tasks and expository tasks were similar in persons with and without MCI (with r ranging from 0.49 to 0.65 within tasks). Intraindividual variability was generally preserved across lexical speech features. Speech rate and filler rate were the most consistent indices for the cognitively intact group, and speech rate was the most consistent for the MCI group. Our findings suggest that automatically calculated lexical properties of speech are consistent in older adults with varying levels of cognitive impairment. These findings encourage further investigation of the utility of speech analysis and other digital biomarkers for monitoring cognitive status over time.
Sections du résumé
Background
UNASSIGNED
Speech analysis data are promising digital biomarkers for the early detection of Alzheimer disease. However, despite its importance, very few studies in this area have examined whether older adults produce spontaneous speech with characteristics that are sufficiently consistent to be used as proxy markers of cognitive status.
Objective
UNASSIGNED
This preliminary study seeks to investigate consistency across lexical characteristics of speech in older adults with and without cognitive impairment.
Methods
UNASSIGNED
A total of 39 older adults from a larger, ongoing study (age: mean 81.1, SD 5.9 years) were included. Participants completed neuropsychological testing and both picture description tasks and expository tasks to elicit speech. Participants with T-scores of ≤40 on ≥2 cognitive tests were categorized as having mild cognitive impairment (MCI). Speech features were computed automatically by using Python and the Natural Language Toolkit.
Results
UNASSIGNED
Reliability indices based on mean correlations for picture description tasks and expository tasks were similar in persons with and without MCI (with r ranging from 0.49 to 0.65 within tasks). Intraindividual variability was generally preserved across lexical speech features. Speech rate and filler rate were the most consistent indices for the cognitively intact group, and speech rate was the most consistent for the MCI group.
Conclusions
UNASSIGNED
Our findings suggest that automatically calculated lexical properties of speech are consistent in older adults with varying levels of cognitive impairment. These findings encourage further investigation of the utility of speech analysis and other digital biomarkers for monitoring cognitive status over time.
Identifiants
pubmed: 37819025
pii: v6i1e46483
doi: 10.2196/46483
pmc: PMC10583496
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e46483Informations de copyright
© Phillip Hamrick, Victoria Sanborn, Rachel Ostrand, John Gunstad. Originally published in JMIR Aging (https://aging.jmir.org).
Références
Curr Alzheimer Res. 2018;15(2):130-138
pubmed: 29165085
J Med Internet Res. 2019 Aug 30;21(8):e12785
pubmed: 31471958
Alzheimers Dement (Amst). 2016 May 26;4:47-55
pubmed: 27489880
Neuropsychol Dev Cogn B Aging Neuropsychol Cogn. 2023 Jun 5;:1-12
pubmed: 37272884
Psychiatry Res. 2022 May;311:114511
pubmed: 35316691
J Int Neuropsychol Soc. 2016 Oct;22(9):937-943
pubmed: 27029348
PLoS One. 2011 Apr 19;6(4):e16973
pubmed: 21526188
JMIR Aging. 2022 Sep 21;5(3):e33460
pubmed: 36129754
Expert Rev Neurother. 2011 May;11(5):665-76
pubmed: 21539487
J Alzheimers Dis. 2020;75(1):211-221
pubmed: 32250297
J Geriatr Psychiatry Neurol. 2021 Sep;34(5):357-369
pubmed: 32723128
Psychol Rep. 2011 Oct;109(2):686-700
pubmed: 22238866
Proc Natl Acad Sci U S A. 2018 Feb 13;115(7):1487-1492
pubmed: 29378936
Appl Neuropsychol Adult. 2022 Sep-Oct;29(5):1250-1257
pubmed: 33377800
Am J Speech Lang Pathol. 2007 Nov;16(4):295-315
pubmed: 17971491
Behav Res Methods. 2016 Jun;48(2):475-86
pubmed: 25862539
J Speech Hear Res. 1993 Apr;36(2):338-50
pubmed: 8487525
J Acoust Soc Am. 2018 Sep;144(3):1331
pubmed: 30424655
Appl Corpus Linguistics. 2023 Dec;3(3):
pubmed: 37476646
Neuropsychology. 2008 Mar;22(2):188-95
pubmed: 18331161
Neuropsychol Dev Cogn B Aging Neuropsychol Cogn. 2009 May;16(3):241-59
pubmed: 18982506
J Alzheimers Dis. 2018;65(2):519-542
pubmed: 30103314
Front Psychol. 2017 Mar 06;8:269
pubmed: 28321196
Alzheimers Dement (Amst). 2018 Nov 03;10:773-781
pubmed: 30505927
JMIR Aging. 2020 Apr 8;3(1):e17136
pubmed: 32267236
Cortex. 2015 Aug;69:237-54
pubmed: 26103601
Curr Alzheimer Res. 2018;15(2):120-129
pubmed: 28847279
J Clin Psychiatry. 1987 Aug;48(8):314-8
pubmed: 3611032
Neuropsychologia. 1989;27(8):1073-9
pubmed: 2797414
Neurol Clin Pract. 2019 Apr;9(2):109-117
pubmed: 31041124