Computer-automated dementia screening using a touch-tone telephone

Citation
Jc. Mundt et al., Computer-automated dementia screening using a touch-tone telephone, ARCH IN MED, 161(20), 2001, pp. 2481-2487
Citations number
27
Categorie Soggetti
General & Internal Medicine","Medical Research General Topics
Journal title
ARCHIVES OF INTERNAL MEDICINE
ISSN journal
00039926 → ACNP
Volume
161
Issue
20
Year of publication
2001
Pages
2481 - 2487
Database
ISI
SICI code
0003-9926(20011112)161:20<2481:CDSUAT>2.0.ZU;2-0
Abstract
Background: This study investigated the sensitivity and specificity of a co mputer-automated telephone system to evaluate cognitive impairment in elder ly 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 usin g standard Touch-Tone telephones. Seventy-four collateral informants also c ompleted 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 combine d performances across 4 tasks. Results indicated a potential sensitivity of 82.0% and specificity of 85.5%. The scoring model generalized to a validat ion subsample (n=39), producing 85.0% sensitivity and 78.9% specificity. Th e kappa agreement between predicted and actual group membership was 0.64 (P <.001). Of the 16 subjects unable to complete the call, 11 provided suffici ent information to permit us to classify them as impaired, Standard scoring of the interactive voice response-administered Symptoms of Dementia Screen er (completed by informants) produced a screening sensitivity of 63.5% and 100% specificity. A lower criterion found a 90.4% sensitivity, without lowe ring specificity. Conclusions: Computer-automated telephone screening for early dementia usin g either informant or direct assessment is feasible. Such systems could pro vide wide-scale, cost-effective screening, education, and referral services to patients and caregivers.