No Cover Image

Journal article 257 views 45 downloads

Alzheimer’s Dementia Recognition From Spontaneous Speech Using Disfluency and Interactional Features

Shamila Nasreen, Morteza Rohanian, Julian Hough Orcid Logo, Matthew Purver

Frontiers in Computer Science, Volume: 3

Swansea University Author: Julian Hough Orcid Logo

  • 64927.VOR.pdf

    PDF | Version of Record

    Copyright © 2021 Nasreen, Rohanian, Hough and Purver. Distributed under the terms of a Creative Commons Attribution 4.0 International License (CC BY 4.0).

    Download (1.33MB)

Check full text

DOI (Published version): 10.3389/fcomp.2021.640669

Abstract

Alzheimer’s disease (AD) is a progressive, neurodegenerative disorder mainly characterized by memory loss with deficits in other cognitive domains, including language, visuospatial abilities, and changes in behavior. Detecting diagnostic biomarkers that are noninvasive and cost-effective is of great...

Full description

Published in: Frontiers in Computer Science
ISSN: 2624-9898
Published: Frontiers Media SA 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa64927
first_indexed 2023-11-07T20:51:34Z
last_indexed 2024-11-25T14:15:01Z
id cronfa64927
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2024-07-11T14:13:38.6240535</datestamp><bib-version>v2</bib-version><id>64927</id><entry>2023-11-07</entry><title>Alzheimer&#x2019;s Dementia Recognition From Spontaneous Speech Using Disfluency and Interactional Features</title><swanseaauthors><author><sid>082d773ae261d2bbf49434dd2608ab40</sid><ORCID>0000-0002-4345-6759</ORCID><firstname>Julian</firstname><surname>Hough</surname><name>Julian Hough</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-11-07</date><deptcode>MACS</deptcode><abstract>Alzheimer&#x2019;s disease (AD) is a progressive, neurodegenerative disorder mainly characterized by memory loss with deficits in other cognitive domains, including language, visuospatial abilities, and changes in behavior. Detecting diagnostic biomarkers that are noninvasive and cost-effective is of great value not only for clinical assessments and diagnostics but also for research purposes. Several previous studies have investigated AD diagnosis via the acoustic, lexical, syntactic, and semantic aspects of speech and language. Other studies include approaches from conversation analysis that look at more interactional aspects, showing that disfluencies such as fillers and repairs, and purely nonverbal features such as inter-speaker silence, can be key features of AD conversations. These kinds of features, if useful for diagnosis, may have many advantages: They are simple to extract and relatively language-, topic-, and task-independent. This study aims to quantify the role and contribution of these features of interaction structure in predicting whether a dialogue participant has AD. We used a subset of the Carolinas Conversation Collection dataset of patients with AD at moderate stage within the age range 60&#x2013;89 and similar-aged non-AD patients with other health conditions. Our feature analysis comprised two sets: disfluency features, including indicators such as self-repairs and fillers, and interactional features, including overlaps, turn-taking behavior, and distributions of different types of silence both within patient speech and between patient and interviewer speech. Statistical analysis showed significant differences between AD and non-AD groups for several disfluency features (edit terms, verbatim repeats, and substitutions) and interactional features (lapses, gaps, attributable silences, turn switches per minute, standardized phonation time, and turn length). For the classification of AD patient conversations vs. non-AD patient conversations, we achieved 83% accuracy with disfluency features, 83% accuracy with interactional features, and an overall accuracy of 90% when combining both feature sets using support vector machine classifiers. The discriminative power of these features, perhaps combined with more conventional linguistic features, therefore shows potential for integration into noninvasive clinical assessments for AD at advanced stages.</abstract><type>Journal Article</type><journal>Frontiers in Computer Science</journal><volume>3</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Frontiers Media SA</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2624-9898</issnElectronic><keywords>Alzheimer&#x2019;s disease, spontaneous speech, disfluency, interaction, natural language processing, mental health monitoring</keywords><publishedDay>18</publishedDay><publishedMonth>6</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-06-18</publishedDate><doi>10.3389/fcomp.2021.640669</doi><url>http://dx.doi.org/10.3389/fcomp.2021.640669</url><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>MP was partially supported by the EPSRC under grant EP/S033564/1 and by the European Union&#x2019;s Horizon 2020 programme under grant agreements 769661 (SAAM, Supporting Active Ageing through Multimodal coaching) and 825153 (EMBEDDIA, Cross-Lingual Embeddings for Less-Represented Languages in European News Media).</funders><projectreference/><lastEdited>2024-07-11T14:13:38.6240535</lastEdited><Created>2023-11-07T20:30:39.7026648</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Shamila</firstname><surname>Nasreen</surname><order>1</order></author><author><firstname>Morteza</firstname><surname>Rohanian</surname><order>2</order></author><author><firstname>Julian</firstname><surname>Hough</surname><orcid>0000-0002-4345-6759</orcid><order>3</order></author><author><firstname>Matthew</firstname><surname>Purver</surname><order>4</order></author></authors><documents><document><filename>64927__29338__d0385b6aa6ca46eab99f6f541686ef5d.pdf</filename><originalFilename>64927.VOR.pdf</originalFilename><uploaded>2024-01-02T14:29:47.4566804</uploaded><type>Output</type><contentLength>1398658</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright &#xA9; 2021 Nasreen, Rohanian, Hough and Purver. Distributed under the terms of a Creative Commons Attribution 4.0 International License (CC BY 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2024-07-11T14:13:38.6240535 v2 64927 2023-11-07 Alzheimer’s Dementia Recognition From Spontaneous Speech Using Disfluency and Interactional Features 082d773ae261d2bbf49434dd2608ab40 0000-0002-4345-6759 Julian Hough Julian Hough true false 2023-11-07 MACS Alzheimer’s disease (AD) is a progressive, neurodegenerative disorder mainly characterized by memory loss with deficits in other cognitive domains, including language, visuospatial abilities, and changes in behavior. Detecting diagnostic biomarkers that are noninvasive and cost-effective is of great value not only for clinical assessments and diagnostics but also for research purposes. Several previous studies have investigated AD diagnosis via the acoustic, lexical, syntactic, and semantic aspects of speech and language. Other studies include approaches from conversation analysis that look at more interactional aspects, showing that disfluencies such as fillers and repairs, and purely nonverbal features such as inter-speaker silence, can be key features of AD conversations. These kinds of features, if useful for diagnosis, may have many advantages: They are simple to extract and relatively language-, topic-, and task-independent. This study aims to quantify the role and contribution of these features of interaction structure in predicting whether a dialogue participant has AD. We used a subset of the Carolinas Conversation Collection dataset of patients with AD at moderate stage within the age range 60–89 and similar-aged non-AD patients with other health conditions. Our feature analysis comprised two sets: disfluency features, including indicators such as self-repairs and fillers, and interactional features, including overlaps, turn-taking behavior, and distributions of different types of silence both within patient speech and between patient and interviewer speech. Statistical analysis showed significant differences between AD and non-AD groups for several disfluency features (edit terms, verbatim repeats, and substitutions) and interactional features (lapses, gaps, attributable silences, turn switches per minute, standardized phonation time, and turn length). For the classification of AD patient conversations vs. non-AD patient conversations, we achieved 83% accuracy with disfluency features, 83% accuracy with interactional features, and an overall accuracy of 90% when combining both feature sets using support vector machine classifiers. The discriminative power of these features, perhaps combined with more conventional linguistic features, therefore shows potential for integration into noninvasive clinical assessments for AD at advanced stages. Journal Article Frontiers in Computer Science 3 Frontiers Media SA 2624-9898 Alzheimer’s disease, spontaneous speech, disfluency, interaction, natural language processing, mental health monitoring 18 6 2021 2021-06-18 10.3389/fcomp.2021.640669 http://dx.doi.org/10.3389/fcomp.2021.640669 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University Another institution paid the OA fee MP was partially supported by the EPSRC under grant EP/S033564/1 and by the European Union’s Horizon 2020 programme under grant agreements 769661 (SAAM, Supporting Active Ageing through Multimodal coaching) and 825153 (EMBEDDIA, Cross-Lingual Embeddings for Less-Represented Languages in European News Media). 2024-07-11T14:13:38.6240535 2023-11-07T20:30:39.7026648 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Shamila Nasreen 1 Morteza Rohanian 2 Julian Hough 0000-0002-4345-6759 3 Matthew Purver 4 64927__29338__d0385b6aa6ca46eab99f6f541686ef5d.pdf 64927.VOR.pdf 2024-01-02T14:29:47.4566804 Output 1398658 application/pdf Version of Record true Copyright © 2021 Nasreen, Rohanian, Hough and Purver. Distributed under the terms of a Creative Commons Attribution 4.0 International License (CC BY 4.0). true eng https://creativecommons.org/licenses/by/4.0/
title Alzheimer’s Dementia Recognition From Spontaneous Speech Using Disfluency and Interactional Features
spellingShingle Alzheimer’s Dementia Recognition From Spontaneous Speech Using Disfluency and Interactional Features
Julian Hough
title_short Alzheimer’s Dementia Recognition From Spontaneous Speech Using Disfluency and Interactional Features
title_full Alzheimer’s Dementia Recognition From Spontaneous Speech Using Disfluency and Interactional Features
title_fullStr Alzheimer’s Dementia Recognition From Spontaneous Speech Using Disfluency and Interactional Features
title_full_unstemmed Alzheimer’s Dementia Recognition From Spontaneous Speech Using Disfluency and Interactional Features
title_sort Alzheimer’s Dementia Recognition From Spontaneous Speech Using Disfluency and Interactional Features
author_id_str_mv 082d773ae261d2bbf49434dd2608ab40
author_id_fullname_str_mv 082d773ae261d2bbf49434dd2608ab40_***_Julian Hough
author Julian Hough
author2 Shamila Nasreen
Morteza Rohanian
Julian Hough
Matthew Purver
format Journal article
container_title Frontiers in Computer Science
container_volume 3
publishDate 2021
institution Swansea University
issn 2624-9898
doi_str_mv 10.3389/fcomp.2021.640669
publisher Frontiers Media SA
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://dx.doi.org/10.3389/fcomp.2021.640669
document_store_str 1
active_str 0
description Alzheimer’s disease (AD) is a progressive, neurodegenerative disorder mainly characterized by memory loss with deficits in other cognitive domains, including language, visuospatial abilities, and changes in behavior. Detecting diagnostic biomarkers that are noninvasive and cost-effective is of great value not only for clinical assessments and diagnostics but also for research purposes. Several previous studies have investigated AD diagnosis via the acoustic, lexical, syntactic, and semantic aspects of speech and language. Other studies include approaches from conversation analysis that look at more interactional aspects, showing that disfluencies such as fillers and repairs, and purely nonverbal features such as inter-speaker silence, can be key features of AD conversations. These kinds of features, if useful for diagnosis, may have many advantages: They are simple to extract and relatively language-, topic-, and task-independent. This study aims to quantify the role and contribution of these features of interaction structure in predicting whether a dialogue participant has AD. We used a subset of the Carolinas Conversation Collection dataset of patients with AD at moderate stage within the age range 60–89 and similar-aged non-AD patients with other health conditions. Our feature analysis comprised two sets: disfluency features, including indicators such as self-repairs and fillers, and interactional features, including overlaps, turn-taking behavior, and distributions of different types of silence both within patient speech and between patient and interviewer speech. Statistical analysis showed significant differences between AD and non-AD groups for several disfluency features (edit terms, verbatim repeats, and substitutions) and interactional features (lapses, gaps, attributable silences, turn switches per minute, standardized phonation time, and turn length). For the classification of AD patient conversations vs. non-AD patient conversations, we achieved 83% accuracy with disfluency features, 83% accuracy with interactional features, and an overall accuracy of 90% when combining both feature sets using support vector machine classifiers. The discriminative power of these features, perhaps combined with more conventional linguistic features, therefore shows potential for integration into noninvasive clinical assessments for AD at advanced stages.
published_date 2021-06-18T20:26:20Z
_version_ 1821347970147155968
score 11.04748

Similar Items