Automated remote speech‐based testing of individuals with cognitive decline: Bayesian agreement of transcription accuracy

Abstract Introduction We investigated the agreement between automated and gold‐standard manual transcriptions of telephone chatbot‐based semantic verbal fluency testing. Methods We examined 78 cases from the Screening over Speech in Unselected Populations for Clinical Trials in AD (PROSPECT‐AD) stud...

Full description

Saved in:
Bibliographic Details
Main Authors: Alexandra König, Stefanie Köhler, Johannes Tröger, Emrah Düzel, Wenzel Glanz, Michaela Butryn, Elisa Mallick, Josef Priller, Slawek Altenstein, Annika Spottke, Okka Kimmich, Björn Falkenburger, Antje Osterrath, Jens Wiltfang, Claudia Bartels, Ingo Kilimann, Christoph Laske, Matthias H. Munk, Sandra Roeske, Ingo Frommann, Daniel C. Hoffmann, Frank Jessen, Michael Wagner, Nicklas Linz, Stefan Teipel
Format: Article
Language:English
Published: Wiley 2024-10-01
Series:Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring
Subjects:
Online Access:https://doi.org/10.1002/dad2.70011
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850041038151876608
author Alexandra König
Stefanie Köhler
Johannes Tröger
Emrah Düzel
Wenzel Glanz
Michaela Butryn
Elisa Mallick
Josef Priller
Slawek Altenstein
Annika Spottke
Okka Kimmich
Björn Falkenburger
Antje Osterrath
Jens Wiltfang
Claudia Bartels
Ingo Kilimann
Christoph Laske
Matthias H. Munk
Sandra Roeske
Ingo Frommann
Daniel C. Hoffmann
Frank Jessen
Michael Wagner
Nicklas Linz
Stefan Teipel
author_facet Alexandra König
Stefanie Köhler
Johannes Tröger
Emrah Düzel
Wenzel Glanz
Michaela Butryn
Elisa Mallick
Josef Priller
Slawek Altenstein
Annika Spottke
Okka Kimmich
Björn Falkenburger
Antje Osterrath
Jens Wiltfang
Claudia Bartels
Ingo Kilimann
Christoph Laske
Matthias H. Munk
Sandra Roeske
Ingo Frommann
Daniel C. Hoffmann
Frank Jessen
Michael Wagner
Nicklas Linz
Stefan Teipel
author_sort Alexandra König
collection DOAJ
description Abstract Introduction We investigated the agreement between automated and gold‐standard manual transcriptions of telephone chatbot‐based semantic verbal fluency testing. Methods We examined 78 cases from the Screening over Speech in Unselected Populations for Clinical Trials in AD (PROSPECT‐AD) study, including cognitively normal individuals and individuals with subjective cognitive decline, mild cognitive impairment, and dementia. We used Bayesian Bland–Altman analysis of word count and the qualitative features of semantic cluster size, cluster switches, and word frequencies. Results We found high levels of agreement for word count, with a 93% probability of a newly observed difference being below the minimally important difference. The qualitative features had fair levels of agreement. Word count reached high levels of discrimination between cognitively impaired and unimpaired individuals, regardless of transcription mode. Discussion Our results support the use of automated speech recognition particularly for the assessment of quantitative speech features, even when using data from telephone calls with cognitively impaired individuals in their homes. Highlights High levels of agreement were found between automated and gold‐standard manual transcriptions of telephone chatbot‐based semantic verbal fluency testing, particularly for word count. The qualitative features had fair levels of agreement. Word count reached high levels of discrimination between cognitively impaired and unimpaired individuals, regardless of transcription mode. Automated speech recognition for the assessment of quantitative and qualitative speech features, even when using data from telephone calls with cognitively impaired individuals in their homes, seems feasible and reliable.
format Article
id doaj-art-4dbd398884b4485dba14ea3ee8c3609d
institution DOAJ
issn 2352-8729
language English
publishDate 2024-10-01
publisher Wiley
record_format Article
series Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring
spelling doaj-art-4dbd398884b4485dba14ea3ee8c3609d2025-08-20T02:55:53ZengWileyAlzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring2352-87292024-10-01164n/an/a10.1002/dad2.70011Automated remote speech‐based testing of individuals with cognitive decline: Bayesian agreement of transcription accuracyAlexandra König0Stefanie Köhler1Johannes Tröger2Emrah Düzel3Wenzel Glanz4Michaela Butryn5Elisa Mallick6Josef Priller7Slawek Altenstein8Annika Spottke9Okka Kimmich10Björn Falkenburger11Antje Osterrath12Jens Wiltfang13Claudia Bartels14Ingo Kilimann15Christoph Laske16Matthias H. Munk17Sandra Roeske18Ingo Frommann19Daniel C. Hoffmann20Frank Jessen21Michael Wagner22Nicklas Linz23Stefan Teipel24ki:elements GmbH Saarbrücken GermanyGerman Center for Neurodegenerative Diseases (DZNE), Rostock Greifswald GermanyUniversité Côte d'Azur, Centre Hospitalier et Universitaire, Clinique Gériatrique du Cerveau et du Mouvement, Centre Mémoire de Ressources et de Recherche Nice FranceGerman Center for Neurodegenerative Diseases (DZNE) Magdeburg GermanyGerman Center for Neurodegenerative Diseases (DZNE) Magdeburg GermanyGerman Center for Neurodegenerative Diseases (DZNE) Magdeburg GermanyUniversité Côte d'Azur, Centre Hospitalier et Universitaire, Clinique Gériatrique du Cerveau et du Mouvement, Centre Mémoire de Ressources et de Recherche Nice FranceGerman Center for Neurodegenerative Diseases (DZNE) Berlin GermanyGerman Center for Neurodegenerative Diseases (DZNE) Berlin GermanyGerman Center for Neurodegenerative Diseases (DZNE) Bonn GermanyGerman Center for Neurodegenerative Diseases (DZNE) Bonn GermanyGerman Center for Neurodegenerative Diseases (DZNE) Dresden GermanyGerman Center for Neurodegenerative Diseases (DZNE) Dresden GermanyGerman Center for Neurodegenerative Diseases (DZNE) Göttingen GermanyDepartment of Psychiatry and Psychotherapy University Medical Center Goettingen University of Goettingen Göttingen GermanyGerman Center for Neurodegenerative Diseases (DZNE), Rostock Greifswald GermanyGerman Center for Neurodegenerative Diseases (DZNE) Tübingen GermanyGerman Center for Neurodegenerative Diseases (DZNE) Tübingen GermanyGerman Center for Neurodegenerative Diseases (DZNE) Bonn GermanyGerman Center for Neurodegenerative Diseases (DZNE) Bonn GermanyGerman Center for Neurodegenerative Diseases (DZNE) Bonn GermanyGerman Center for Neurodegenerative Diseases (DZNE) Bonn GermanyGerman Center for Neurodegenerative Diseases (DZNE) Bonn GermanyUniversité Côte d'Azur, Centre Hospitalier et Universitaire, Clinique Gériatrique du Cerveau et du Mouvement, Centre Mémoire de Ressources et de Recherche Nice FranceGerman Center for Neurodegenerative Diseases (DZNE), Rostock Greifswald GermanyAbstract Introduction We investigated the agreement between automated and gold‐standard manual transcriptions of telephone chatbot‐based semantic verbal fluency testing. Methods We examined 78 cases from the Screening over Speech in Unselected Populations for Clinical Trials in AD (PROSPECT‐AD) study, including cognitively normal individuals and individuals with subjective cognitive decline, mild cognitive impairment, and dementia. We used Bayesian Bland–Altman analysis of word count and the qualitative features of semantic cluster size, cluster switches, and word frequencies. Results We found high levels of agreement for word count, with a 93% probability of a newly observed difference being below the minimally important difference. The qualitative features had fair levels of agreement. Word count reached high levels of discrimination between cognitively impaired and unimpaired individuals, regardless of transcription mode. Discussion Our results support the use of automated speech recognition particularly for the assessment of quantitative speech features, even when using data from telephone calls with cognitively impaired individuals in their homes. Highlights High levels of agreement were found between automated and gold‐standard manual transcriptions of telephone chatbot‐based semantic verbal fluency testing, particularly for word count. The qualitative features had fair levels of agreement. Word count reached high levels of discrimination between cognitively impaired and unimpaired individuals, regardless of transcription mode. Automated speech recognition for the assessment of quantitative and qualitative speech features, even when using data from telephone calls with cognitively impaired individuals in their homes, seems feasible and reliable.https://doi.org/10.1002/dad2.70011automated speech recognitionBland–Altman analysisdementiareliabilityremote cognitive testingsemantic verbal fluency
spellingShingle Alexandra König
Stefanie Köhler
Johannes Tröger
Emrah Düzel
Wenzel Glanz
Michaela Butryn
Elisa Mallick
Josef Priller
Slawek Altenstein
Annika Spottke
Okka Kimmich
Björn Falkenburger
Antje Osterrath
Jens Wiltfang
Claudia Bartels
Ingo Kilimann
Christoph Laske
Matthias H. Munk
Sandra Roeske
Ingo Frommann
Daniel C. Hoffmann
Frank Jessen
Michael Wagner
Nicklas Linz
Stefan Teipel
Automated remote speech‐based testing of individuals with cognitive decline: Bayesian agreement of transcription accuracy
Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring
automated speech recognition
Bland–Altman analysis
dementia
reliability
remote cognitive testing
semantic verbal fluency
title Automated remote speech‐based testing of individuals with cognitive decline: Bayesian agreement of transcription accuracy
title_full Automated remote speech‐based testing of individuals with cognitive decline: Bayesian agreement of transcription accuracy
title_fullStr Automated remote speech‐based testing of individuals with cognitive decline: Bayesian agreement of transcription accuracy
title_full_unstemmed Automated remote speech‐based testing of individuals with cognitive decline: Bayesian agreement of transcription accuracy
title_short Automated remote speech‐based testing of individuals with cognitive decline: Bayesian agreement of transcription accuracy
title_sort automated remote speech based testing of individuals with cognitive decline bayesian agreement of transcription accuracy
topic automated speech recognition
Bland–Altman analysis
dementia
reliability
remote cognitive testing
semantic verbal fluency
url https://doi.org/10.1002/dad2.70011
work_keys_str_mv AT alexandrakonig automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT stefaniekohler automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT johannestroger automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT emrahduzel automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT wenzelglanz automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT michaelabutryn automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT elisamallick automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT josefpriller automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT slawekaltenstein automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT annikaspottke automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT okkakimmich automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT bjornfalkenburger automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT antjeosterrath automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT jenswiltfang automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT claudiabartels automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT ingokilimann automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT christophlaske automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT matthiashmunk automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT sandraroeske automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT ingofrommann automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT danielchoffmann automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT frankjessen automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT michaelwagner automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT nicklaslinz automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy
AT stefanteipel automatedremotespeechbasedtestingofindividualswithcognitivedeclinebayesianagreementoftranscriptionaccuracy