Automated semantic relevance as an indicator of cognitive decline: Out‐of‐sample validation on a large‐scale longitudinal dataset

We developed and evaluated an automatically extracted measure of cognition (semantic relevance) using automated and manual transcripts of audio recordings from healthy and cognitively impaired participants describing the Cookie Theft picture from the Boston Diagnostic Aphasia Examination. We describ...

Full description

Saved in:
Bibliographic Details
Published inAlzheimer's & dementia : diagnosis, assessment & disease monitoring Vol. 14; no. 1; pp. e12294 - n/a
Main Authors Stegmann, Gabriela, Hahn, Shira, Bhandari, Samarth, Kawabata, Kan, Shefner, Jeremy, Duncan, Cayla Jessica, Liss, Julie, Berisha, Visar, Mueller, Kimberly
Format Journal Article
LanguageEnglish
Published United States John Wiley & Sons, Inc 2022
John Wiley and Sons Inc
Subjects
Accuracy
algorithm
Algorithms
Alzheimer's disease
Amyotrophic lateral sclerosis
automatic
Automation
cognition
Cognition & reasoning
Cognitive & Behavioral Assessment
Cognitive ability
Data collection
Datasets
Dementia
digital
Language
Linguistics
longitudinal
Secondary schools
Semantics
Speech
Voice recognition
digital
cognition
speech
automatic
language
longitudinal
algorithm
Online AccessGet full text
ISSN2352-8729
2352-8729
DOI10.1002/dad2.12294

Cover

More Information
Summary:We developed and evaluated an automatically extracted measure of cognition (semantic relevance) using automated and manual transcripts of audio recordings from healthy and cognitively impaired participants describing the Cookie Theft picture from the Boston Diagnostic Aphasia Examination. We describe the rationale and metric validation. We developed the measure on one dataset and evaluated it on a large database (>2000 samples) by comparing accuracy against a manually calculated metric and evaluating its clinical relevance. The fully automated measure was accurate (r = .84), had moderate to good reliability (intra‐class correlation = .73), correlated with Mini‐Mental State Examination and improved the fit in the context of other automatic language features (r = .65), and longitudinally declined with age and level of cognitive impairment. This study demonstrates the use of a rigorous analytical and clinical framework for validating automatic measures of speech, and applied it to a measure that is accurate and clinically relevant.
Bibliography:Julie Liss, Visar Berisha, and Kimberly Mueller share senior authorship.
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2352-8729
2352-8729
DOI:10.1002/dad2.12294