Computerized analysis of speech and language to identify psycholinguistic correlates of frontotemporal lobar degeneration

Serguei V S Pakhomov, Glenn E. Smith, Dustin Chacon, Yara Feliciano, Neill R Graff Radford, Richard John Caselli, David S Knopman

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Objective: To evaluate the use of a semiautomated computerized system for measuring speech and language characteristics in patients with frontotemporal lobar degeneration (FTLD). Background: FTLD is a heterogeneous disorder comprising at least 3 variants. Computerized assessment of spontaneous verbal descriptions by patients with FTLD offers a detailed and reproducible view of the underlying cognitive deficits. Methods: Audiorecorded speech samples of 38 patients from 3 participating medical centers were elicited using the Cookie Theft stimulus. Each patient underwent a battery of neuropsychologic tests. The audio was analyzed by the computerized system to measure 15 speech and language variables. Analysis of variance was used to identify characteristics with significant differences in means between FTLD variants. Factor analysis was used to examine the implicit relations between subsets of the variables. Results: Semiautomated measurements of pause-to-word ratio and pronoun-to-noun ratio were able to discriminate between some of the FTLD variants. Principal component analysis of all 14 variables suggested 4 subjectively defined components (length, hesitancy, empty content, grammaticality) corresponding to the phenomenology of FTLD variants. Conclusion: Semiautomated language and speech analysis is a promising novel approach to neuropsychologic assessment that offers a valuable contribution to the toolbox of researchers in dementia and other neurodegenerative disorders.

Original languageEnglish (US)
Pages (from-to)165-177
Number of pages13
JournalCognitive and Behavioral Neurology
Volume23
Issue number3
DOIs
StatePublished - Sep 2010

Fingerprint

Frontotemporal Lobar Degeneration
Psycholinguistics
Language
Theft
Neuropsychological Tests
Principal Component Analysis
Neurodegenerative Diseases
Statistical Factor Analysis
Dementia
Analysis of Variance
Research Personnel

Keywords

  • automated speech analysis
  • frontotemporal lobar degeneration
  • language
  • prosody
  • spontaneous speech

ASJC Scopus subject areas

  • Neuropsychology and Physiological Psychology
  • Psychiatry and Mental health
  • Cognitive Neuroscience

Cite this

Computerized analysis of speech and language to identify psycholinguistic correlates of frontotemporal lobar degeneration. / Pakhomov, Serguei V S; Smith, Glenn E.; Chacon, Dustin; Feliciano, Yara; Graff Radford, Neill R; Caselli, Richard John; Knopman, David S.

In: Cognitive and Behavioral Neurology, Vol. 23, No. 3, 09.2010, p. 165-177.

Research output: Contribution to journalArticle

@article{e3748683b642445397a4961f0daaf48f,
title = "Computerized analysis of speech and language to identify psycholinguistic correlates of frontotemporal lobar degeneration",
abstract = "Objective: To evaluate the use of a semiautomated computerized system for measuring speech and language characteristics in patients with frontotemporal lobar degeneration (FTLD). Background: FTLD is a heterogeneous disorder comprising at least 3 variants. Computerized assessment of spontaneous verbal descriptions by patients with FTLD offers a detailed and reproducible view of the underlying cognitive deficits. Methods: Audiorecorded speech samples of 38 patients from 3 participating medical centers were elicited using the Cookie Theft stimulus. Each patient underwent a battery of neuropsychologic tests. The audio was analyzed by the computerized system to measure 15 speech and language variables. Analysis of variance was used to identify characteristics with significant differences in means between FTLD variants. Factor analysis was used to examine the implicit relations between subsets of the variables. Results: Semiautomated measurements of pause-to-word ratio and pronoun-to-noun ratio were able to discriminate between some of the FTLD variants. Principal component analysis of all 14 variables suggested 4 subjectively defined components (length, hesitancy, empty content, grammaticality) corresponding to the phenomenology of FTLD variants. Conclusion: Semiautomated language and speech analysis is a promising novel approach to neuropsychologic assessment that offers a valuable contribution to the toolbox of researchers in dementia and other neurodegenerative disorders.",
keywords = "automated speech analysis, frontotemporal lobar degeneration, language, prosody, spontaneous speech",
author = "Pakhomov, {Serguei V S} and Smith, {Glenn E.} and Dustin Chacon and Yara Feliciano and {Graff Radford}, {Neill R} and Caselli, {Richard John} and Knopman, {David S}",
year = "2010",
month = "9",
doi = "10.1097/WNN.0b013e3181c5dde3",
language = "English (US)",
volume = "23",
pages = "165--177",
journal = "Cognitive and Behavioral Neurology",
issn = "1543-3633",
publisher = "Lippincott Williams and Wilkins",
number = "3",

}

TY - JOUR

T1 - Computerized analysis of speech and language to identify psycholinguistic correlates of frontotemporal lobar degeneration

AU - Pakhomov, Serguei V S

AU - Smith, Glenn E.

AU - Chacon, Dustin

AU - Feliciano, Yara

AU - Graff Radford, Neill R

AU - Caselli, Richard John

AU - Knopman, David S

PY - 2010/9

Y1 - 2010/9

N2 - Objective: To evaluate the use of a semiautomated computerized system for measuring speech and language characteristics in patients with frontotemporal lobar degeneration (FTLD). Background: FTLD is a heterogeneous disorder comprising at least 3 variants. Computerized assessment of spontaneous verbal descriptions by patients with FTLD offers a detailed and reproducible view of the underlying cognitive deficits. Methods: Audiorecorded speech samples of 38 patients from 3 participating medical centers were elicited using the Cookie Theft stimulus. Each patient underwent a battery of neuropsychologic tests. The audio was analyzed by the computerized system to measure 15 speech and language variables. Analysis of variance was used to identify characteristics with significant differences in means between FTLD variants. Factor analysis was used to examine the implicit relations between subsets of the variables. Results: Semiautomated measurements of pause-to-word ratio and pronoun-to-noun ratio were able to discriminate between some of the FTLD variants. Principal component analysis of all 14 variables suggested 4 subjectively defined components (length, hesitancy, empty content, grammaticality) corresponding to the phenomenology of FTLD variants. Conclusion: Semiautomated language and speech analysis is a promising novel approach to neuropsychologic assessment that offers a valuable contribution to the toolbox of researchers in dementia and other neurodegenerative disorders.

AB - Objective: To evaluate the use of a semiautomated computerized system for measuring speech and language characteristics in patients with frontotemporal lobar degeneration (FTLD). Background: FTLD is a heterogeneous disorder comprising at least 3 variants. Computerized assessment of spontaneous verbal descriptions by patients with FTLD offers a detailed and reproducible view of the underlying cognitive deficits. Methods: Audiorecorded speech samples of 38 patients from 3 participating medical centers were elicited using the Cookie Theft stimulus. Each patient underwent a battery of neuropsychologic tests. The audio was analyzed by the computerized system to measure 15 speech and language variables. Analysis of variance was used to identify characteristics with significant differences in means between FTLD variants. Factor analysis was used to examine the implicit relations between subsets of the variables. Results: Semiautomated measurements of pause-to-word ratio and pronoun-to-noun ratio were able to discriminate between some of the FTLD variants. Principal component analysis of all 14 variables suggested 4 subjectively defined components (length, hesitancy, empty content, grammaticality) corresponding to the phenomenology of FTLD variants. Conclusion: Semiautomated language and speech analysis is a promising novel approach to neuropsychologic assessment that offers a valuable contribution to the toolbox of researchers in dementia and other neurodegenerative disorders.

KW - automated speech analysis

KW - frontotemporal lobar degeneration

KW - language

KW - prosody

KW - spontaneous speech

UR - http://www.scopus.com/inward/record.url?scp=77957576161&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957576161&partnerID=8YFLogxK

U2 - 10.1097/WNN.0b013e3181c5dde3

DO - 10.1097/WNN.0b013e3181c5dde3

M3 - Article

C2 - 20829666

AN - SCOPUS:77957576161

VL - 23

SP - 165

EP - 177

JO - Cognitive and Behavioral Neurology

JF - Cognitive and Behavioral Neurology

SN - 1543-3633

IS - 3

ER -