Computer-automated dementia screening using a touch-tone telephone

James C. Mundt, Kae L. Ferber, Matthew Rizzo, John H. Greist

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

Background: This study investigated the sensitivity and specificity of a computer-automated telephone system to evaluate cognitive impairment in elderly callers to identify signs of early dementia. Methods: The Clinical Dementia Rating Scale was used to assess 155 subjects aged 56 to 93 years (n = 74, 27, 42, and 12, with a Clinical Dementia Rating Scale score of 0, 0.5, 1, and 2, respectively). These subjects performed a battery of tests administered by an interactive voice response system using standard Touch-Tone telephones. Seventy-four collateral informants also completed an interactive voice response version of the Symptoms of Dementia Screener. Results: Sixteen cognitively impaired subjects were unable to complete the telephone call. Performances on 6 of 8 tasks were significantly influenced by Clinical Dementia Rating Scale status. The mean (SD) call length was 12 minutes 27 seconds (2 minutes 32 seconds). A subsample (n = 116) was analyzed using machine-learning methods, producing a scoring algorithm that combined performances across 4 tasks. Results indicated a potential sensitivity of 82.0% and specificity of 85.5%. The scoring model generalized to a validation subsample (n = 39), producing 85.0% sensitivity and 78.9% specificity. The K agreement between predicted and actual group membership was 0.64 (P<.001). Of the 16 subjects unable to complete the call, 11 provided sufficient information to permit us to classify them as impaired. Standard scoring of the interactive voice response-administered Symptoms of Dementia Screener (completed by informants) produced a screening sensitivity of 63.5% and 100% specificity. A lower criterion found a 90.4% sensitivity, without lowering specificity. Conclusions: Computer-automated telephone screening for early dementia using either informant or direct assessment is feasible. Such systems could provide wide-scale, cost-effective screening, education, and referral services to patients and caregivers.

Original languageEnglish (US)
Pages (from-to)2481-2487
Number of pages7
JournalArchives of Internal Medicine
Volume161
Issue number20
DOIs
StatePublished - Nov 12 2001

Fingerprint

Touch
Telephone
Dementia
Sensitivity and Specificity
Caregivers
Referral and Consultation
Education
Costs and Cost Analysis

ASJC Scopus subject areas

  • Internal Medicine

Cite this

Computer-automated dementia screening using a touch-tone telephone. / Mundt, James C.; Ferber, Kae L.; Rizzo, Matthew; Greist, John H.

In: Archives of Internal Medicine, Vol. 161, No. 20, 12.11.2001, p. 2481-2487.

Research output: Contribution to journalArticle

Mundt, James C. ; Ferber, Kae L. ; Rizzo, Matthew ; Greist, John H. / Computer-automated dementia screening using a touch-tone telephone. In: Archives of Internal Medicine. 2001 ; Vol. 161, No. 20. pp. 2481-2487.
@article{ef4f6efa8d7344b3bdb657505a41a263,
title = "Computer-automated dementia screening using a touch-tone telephone",
abstract = "Background: This study investigated the sensitivity and specificity of a computer-automated telephone system to evaluate cognitive impairment in elderly callers to identify signs of early dementia. Methods: The Clinical Dementia Rating Scale was used to assess 155 subjects aged 56 to 93 years (n = 74, 27, 42, and 12, with a Clinical Dementia Rating Scale score of 0, 0.5, 1, and 2, respectively). These subjects performed a battery of tests administered by an interactive voice response system using standard Touch-Tone telephones. Seventy-four collateral informants also completed an interactive voice response version of the Symptoms of Dementia Screener. Results: Sixteen cognitively impaired subjects were unable to complete the telephone call. Performances on 6 of 8 tasks were significantly influenced by Clinical Dementia Rating Scale status. The mean (SD) call length was 12 minutes 27 seconds (2 minutes 32 seconds). A subsample (n = 116) was analyzed using machine-learning methods, producing a scoring algorithm that combined performances across 4 tasks. Results indicated a potential sensitivity of 82.0{\%} and specificity of 85.5{\%}. The scoring model generalized to a validation subsample (n = 39), producing 85.0{\%} sensitivity and 78.9{\%} specificity. The K agreement between predicted and actual group membership was 0.64 (P<.001). Of the 16 subjects unable to complete the call, 11 provided sufficient information to permit us to classify them as impaired. Standard scoring of the interactive voice response-administered Symptoms of Dementia Screener (completed by informants) produced a screening sensitivity of 63.5{\%} and 100{\%} specificity. A lower criterion found a 90.4{\%} sensitivity, without lowering specificity. Conclusions: Computer-automated telephone screening for early dementia using either informant or direct assessment is feasible. Such systems could provide wide-scale, cost-effective screening, education, and referral services to patients and caregivers.",
author = "Mundt, {James C.} and Ferber, {Kae L.} and Matthew Rizzo and Greist, {John H.}",
year = "2001",
month = "11",
day = "12",
doi = "10.1001/archinte.161.20.2481",
language = "English (US)",
volume = "161",
pages = "2481--2487",
journal = "JAMA Internal Medicine",
issn = "2168-6106",
publisher = "American Medical Association",
number = "20",

}

TY - JOUR

T1 - Computer-automated dementia screening using a touch-tone telephone

AU - Mundt, James C.

AU - Ferber, Kae L.

AU - Rizzo, Matthew

AU - Greist, John H.

PY - 2001/11/12

Y1 - 2001/11/12

N2 - Background: This study investigated the sensitivity and specificity of a computer-automated telephone system to evaluate cognitive impairment in elderly callers to identify signs of early dementia. Methods: The Clinical Dementia Rating Scale was used to assess 155 subjects aged 56 to 93 years (n = 74, 27, 42, and 12, with a Clinical Dementia Rating Scale score of 0, 0.5, 1, and 2, respectively). These subjects performed a battery of tests administered by an interactive voice response system using standard Touch-Tone telephones. Seventy-four collateral informants also completed an interactive voice response version of the Symptoms of Dementia Screener. Results: Sixteen cognitively impaired subjects were unable to complete the telephone call. Performances on 6 of 8 tasks were significantly influenced by Clinical Dementia Rating Scale status. The mean (SD) call length was 12 minutes 27 seconds (2 minutes 32 seconds). A subsample (n = 116) was analyzed using machine-learning methods, producing a scoring algorithm that combined performances across 4 tasks. Results indicated a potential sensitivity of 82.0% and specificity of 85.5%. The scoring model generalized to a validation subsample (n = 39), producing 85.0% sensitivity and 78.9% specificity. The K agreement between predicted and actual group membership was 0.64 (P<.001). Of the 16 subjects unable to complete the call, 11 provided sufficient information to permit us to classify them as impaired. Standard scoring of the interactive voice response-administered Symptoms of Dementia Screener (completed by informants) produced a screening sensitivity of 63.5% and 100% specificity. A lower criterion found a 90.4% sensitivity, without lowering specificity. Conclusions: Computer-automated telephone screening for early dementia using either informant or direct assessment is feasible. Such systems could provide wide-scale, cost-effective screening, education, and referral services to patients and caregivers.

AB - Background: This study investigated the sensitivity and specificity of a computer-automated telephone system to evaluate cognitive impairment in elderly callers to identify signs of early dementia. Methods: The Clinical Dementia Rating Scale was used to assess 155 subjects aged 56 to 93 years (n = 74, 27, 42, and 12, with a Clinical Dementia Rating Scale score of 0, 0.5, 1, and 2, respectively). These subjects performed a battery of tests administered by an interactive voice response system using standard Touch-Tone telephones. Seventy-four collateral informants also completed an interactive voice response version of the Symptoms of Dementia Screener. Results: Sixteen cognitively impaired subjects were unable to complete the telephone call. Performances on 6 of 8 tasks were significantly influenced by Clinical Dementia Rating Scale status. The mean (SD) call length was 12 minutes 27 seconds (2 minutes 32 seconds). A subsample (n = 116) was analyzed using machine-learning methods, producing a scoring algorithm that combined performances across 4 tasks. Results indicated a potential sensitivity of 82.0% and specificity of 85.5%. The scoring model generalized to a validation subsample (n = 39), producing 85.0% sensitivity and 78.9% specificity. The K agreement between predicted and actual group membership was 0.64 (P<.001). Of the 16 subjects unable to complete the call, 11 provided sufficient information to permit us to classify them as impaired. Standard scoring of the interactive voice response-administered Symptoms of Dementia Screener (completed by informants) produced a screening sensitivity of 63.5% and 100% specificity. A lower criterion found a 90.4% sensitivity, without lowering specificity. Conclusions: Computer-automated telephone screening for early dementia using either informant or direct assessment is feasible. Such systems could provide wide-scale, cost-effective screening, education, and referral services to patients and caregivers.

UR - http://www.scopus.com/inward/record.url?scp=0035851307&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035851307&partnerID=8YFLogxK

U2 - 10.1001/archinte.161.20.2481

DO - 10.1001/archinte.161.20.2481

M3 - Article

VL - 161

SP - 2481

EP - 2487

JO - JAMA Internal Medicine

JF - JAMA Internal Medicine

SN - 2168-6106

IS - 20

ER -