A predictive model for diagnosing stroke-related apraxia of speech

Kirrie J. Ballard, Lamiae Azizi, Joseph R. Duffy, Malcolm R. McNeil, Mark Halaki, Nicholas O'Dwyer, Claire Layfield, Dominique I. Scholl, Adam P. Vogel, Donald A. Robin

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Diagnosis of the speech motor planning/programming disorder, apraxia of speech (AOS), has proven challenging, largely due to its common co-occurrence with the language-based impairment of aphasia. Currently, diagnosis is based on perceptually identifying and rating the severity of several speech features. It is not known whether all, or a subset of the features, are required for a positive diagnosis. The purpose of this study was to assess predictor variables for the presence of AOS after left-hemisphere stroke, with the goal of increasing diagnostic objectivity and efficiency. This population-based case-control study involved a sample of 72 cases, using the outcome measure of expert judgment on presence of AOS and including a large number of independently collected candidate predictors representing behavioral measures of linguistic, cognitive, nonspeech oral motor, and speech motor ability. We constructed a predictive model using multiple imputation to deal with missing data; the Least Absolute Shrinkage and Selection Operator (Lasso) technique for variable selection to define the most relevant predictors, and bootstrapping to check the model stability and quantify the optimism of the developed model. Two measures were sufficient to distinguish between participants with AOS plus aphasia and those with aphasia alone, (1) a measure of speech errors with words of increasing length and (2) a measure of relative vowel duration in three-syllable words with weak-strong stress pattern (e.g., banana, potato). The model has high discriminative ability to distinguish between cases with and without AOS (c-index=0.93) and good agreement between observed and predicted probabilities (calibration slope=0.94). Some caution is warranted, given the relatively small sample specific to left-hemisphere stroke, and the limitations of imputing missing data. These two speech measures are straightforward to collect and analyse, facilitating use in research and clinical settings.

LanguageEnglish
Pages129-139
Number of pages11
JournalNeuropsychologia
Volume81
DOIs
Publication statusPublished - 29 Jan 2016
Externally publishedYes

Fingerprint

Apraxias
Stroke
Aphasia
Aptitude
Speech Disorders
Musa
Linguistics
Solanum tuberosum
Calibration
Case-Control Studies
Language
Outcome Assessment (Health Care)
Efficiency

Keywords

  • Apraxia of speech
  • Aphasia
  • Diagnosis
  • Lexical stress
  • Speech motor control
  • Stroke

Cite this

Ballard, K. J., Azizi, L., Duffy, J. R., McNeil, M. R., Halaki, M., O'Dwyer, N., ... Robin, D. A. (2016). A predictive model for diagnosing stroke-related apraxia of speech. Neuropsychologia, 81, 129-139. https://doi.org/10.1016/j.neuropsychologia.2015.12.010
Ballard, Kirrie J. ; Azizi, Lamiae ; Duffy, Joseph R. ; McNeil, Malcolm R. ; Halaki, Mark ; O'Dwyer, Nicholas ; Layfield, Claire ; Scholl, Dominique I. ; Vogel, Adam P. ; Robin, Donald A. / A predictive model for diagnosing stroke-related apraxia of speech. In: Neuropsychologia. 2016 ; Vol. 81. pp. 129-139.
@article{8718f9e0eabe4e9ab87cc599580d97e9,
title = "A predictive model for diagnosing stroke-related apraxia of speech",
abstract = "Diagnosis of the speech motor planning/programming disorder, apraxia of speech (AOS), has proven challenging, largely due to its common co-occurrence with the language-based impairment of aphasia. Currently, diagnosis is based on perceptually identifying and rating the severity of several speech features. It is not known whether all, or a subset of the features, are required for a positive diagnosis. The purpose of this study was to assess predictor variables for the presence of AOS after left-hemisphere stroke, with the goal of increasing diagnostic objectivity and efficiency. This population-based case-control study involved a sample of 72 cases, using the outcome measure of expert judgment on presence of AOS and including a large number of independently collected candidate predictors representing behavioral measures of linguistic, cognitive, nonspeech oral motor, and speech motor ability. We constructed a predictive model using multiple imputation to deal with missing data; the Least Absolute Shrinkage and Selection Operator (Lasso) technique for variable selection to define the most relevant predictors, and bootstrapping to check the model stability and quantify the optimism of the developed model. Two measures were sufficient to distinguish between participants with AOS plus aphasia and those with aphasia alone, (1) a measure of speech errors with words of increasing length and (2) a measure of relative vowel duration in three-syllable words with weak-strong stress pattern (e.g., banana, potato). The model has high discriminative ability to distinguish between cases with and without AOS (c-index=0.93) and good agreement between observed and predicted probabilities (calibration slope=0.94). Some caution is warranted, given the relatively small sample specific to left-hemisphere stroke, and the limitations of imputing missing data. These two speech measures are straightforward to collect and analyse, facilitating use in research and clinical settings.",
keywords = "Apraxia of speech, Aphasia, Diagnosis, Lexical stress, Speech motor control, Stroke",
author = "Ballard, {Kirrie J.} and Lamiae Azizi and Duffy, {Joseph R.} and McNeil, {Malcolm R.} and Mark Halaki and Nicholas O'Dwyer and Claire Layfield and Scholl, {Dominique I.} and Vogel, {Adam P.} and Robin, {Donald A.}",
year = "2016",
month = "1",
day = "29",
doi = "10.1016/j.neuropsychologia.2015.12.010",
language = "English",
volume = "81",
pages = "129--139",
journal = "Neuropsychologia",
issn = "0028-3932",
publisher = "Elsevier",

}

Ballard, KJ, Azizi, L, Duffy, JR, McNeil, MR, Halaki, M, O'Dwyer, N, Layfield, C, Scholl, DI, Vogel, AP & Robin, DA 2016, 'A predictive model for diagnosing stroke-related apraxia of speech', Neuropsychologia, vol. 81, pp. 129-139. https://doi.org/10.1016/j.neuropsychologia.2015.12.010

A predictive model for diagnosing stroke-related apraxia of speech. / Ballard, Kirrie J.; Azizi, Lamiae; Duffy, Joseph R.; McNeil, Malcolm R.; Halaki, Mark; O'Dwyer, Nicholas; Layfield, Claire; Scholl, Dominique I.; Vogel, Adam P.; Robin, Donald A.

In: Neuropsychologia, Vol. 81, 29.01.2016, p. 129-139.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A predictive model for diagnosing stroke-related apraxia of speech

AU - Ballard, Kirrie J.

AU - Azizi, Lamiae

AU - Duffy, Joseph R.

AU - McNeil, Malcolm R.

AU - Halaki, Mark

AU - O'Dwyer, Nicholas

AU - Layfield, Claire

AU - Scholl, Dominique I.

AU - Vogel, Adam P.

AU - Robin, Donald A.

PY - 2016/1/29

Y1 - 2016/1/29

N2 - Diagnosis of the speech motor planning/programming disorder, apraxia of speech (AOS), has proven challenging, largely due to its common co-occurrence with the language-based impairment of aphasia. Currently, diagnosis is based on perceptually identifying and rating the severity of several speech features. It is not known whether all, or a subset of the features, are required for a positive diagnosis. The purpose of this study was to assess predictor variables for the presence of AOS after left-hemisphere stroke, with the goal of increasing diagnostic objectivity and efficiency. This population-based case-control study involved a sample of 72 cases, using the outcome measure of expert judgment on presence of AOS and including a large number of independently collected candidate predictors representing behavioral measures of linguistic, cognitive, nonspeech oral motor, and speech motor ability. We constructed a predictive model using multiple imputation to deal with missing data; the Least Absolute Shrinkage and Selection Operator (Lasso) technique for variable selection to define the most relevant predictors, and bootstrapping to check the model stability and quantify the optimism of the developed model. Two measures were sufficient to distinguish between participants with AOS plus aphasia and those with aphasia alone, (1) a measure of speech errors with words of increasing length and (2) a measure of relative vowel duration in three-syllable words with weak-strong stress pattern (e.g., banana, potato). The model has high discriminative ability to distinguish between cases with and without AOS (c-index=0.93) and good agreement between observed and predicted probabilities (calibration slope=0.94). Some caution is warranted, given the relatively small sample specific to left-hemisphere stroke, and the limitations of imputing missing data. These two speech measures are straightforward to collect and analyse, facilitating use in research and clinical settings.

AB - Diagnosis of the speech motor planning/programming disorder, apraxia of speech (AOS), has proven challenging, largely due to its common co-occurrence with the language-based impairment of aphasia. Currently, diagnosis is based on perceptually identifying and rating the severity of several speech features. It is not known whether all, or a subset of the features, are required for a positive diagnosis. The purpose of this study was to assess predictor variables for the presence of AOS after left-hemisphere stroke, with the goal of increasing diagnostic objectivity and efficiency. This population-based case-control study involved a sample of 72 cases, using the outcome measure of expert judgment on presence of AOS and including a large number of independently collected candidate predictors representing behavioral measures of linguistic, cognitive, nonspeech oral motor, and speech motor ability. We constructed a predictive model using multiple imputation to deal with missing data; the Least Absolute Shrinkage and Selection Operator (Lasso) technique for variable selection to define the most relevant predictors, and bootstrapping to check the model stability and quantify the optimism of the developed model. Two measures were sufficient to distinguish between participants with AOS plus aphasia and those with aphasia alone, (1) a measure of speech errors with words of increasing length and (2) a measure of relative vowel duration in three-syllable words with weak-strong stress pattern (e.g., banana, potato). The model has high discriminative ability to distinguish between cases with and without AOS (c-index=0.93) and good agreement between observed and predicted probabilities (calibration slope=0.94). Some caution is warranted, given the relatively small sample specific to left-hemisphere stroke, and the limitations of imputing missing data. These two speech measures are straightforward to collect and analyse, facilitating use in research and clinical settings.

KW - Apraxia of speech

KW - Aphasia

KW - Diagnosis

KW - Lexical stress

KW - Speech motor control

KW - Stroke

UR - http://www.scopus.com/inward/record.url?scp=84951025769&partnerID=8YFLogxK

U2 - 10.1016/j.neuropsychologia.2015.12.010

DO - 10.1016/j.neuropsychologia.2015.12.010

M3 - Article

VL - 81

SP - 129

EP - 139

JO - Neuropsychologia

T2 - Neuropsychologia

JF - Neuropsychologia

SN - 0028-3932

ER -

Ballard KJ, Azizi L, Duffy JR, McNeil MR, Halaki M, O'Dwyer N et al. A predictive model for diagnosing stroke-related apraxia of speech. Neuropsychologia. 2016 Jan 29;81:129-139. https://doi.org/10.1016/j.neuropsychologia.2015.12.010