Academic Journal
View in EDS

Preclinical Dialogue Simulation: Evaluating Response Accessibility in Conversational Artificial Intelligence for Aphasia Therapy.

Bibliographic Details
Title: Preclinical Dialogue Simulation: Evaluating Response Accessibility in Conversational Artificial Intelligence for Aphasia Therapy.
Authors: Imaezue, Gerald C., Maram, Krishna V., Ajayi, David, Alohali, Isra, Butta, Rajesh K.
Source: Journal of Speech, Language & Hearing Research; Aug2026, Vol. 69 Issue 8, p3781-3796, 16p
Subject Terms: Statistical models, Artificial intelligence, Rehabilitation of aphasic persons, Benchmarking (Management), Readability (Literary style), Research evaluation, Natural language processing, Speech-language pathology, Simulation methods in education, Communicative disorders, Communication devices for people with disabilities, Data analysis software, Speech therapy, Regression analysis, Sensitivity & specificity (Statistics)
Abstract: Purpose: Large language model (LLM)-driven conversational agents are increasingly considered for use in clinical contexts, yet systematic approaches for evaluating their behavior in impairment-rich, speech-based therapeutic interactions remain limited. This study extends the Agent-Based Conversational Dialogue (ABCD) simulation method as a preclinical testbed to evaluate how LLMs generate accessible clinician language when responding to characteristic aphasic speech during Response Elaboration Training. Method: ABCD was used to simulate multi-turn spoken therapeutic dialogues between an LLM-driven clinician and an artificial intelligence (AI)-simulated aphasic patient, enabling controlled manipulation of impairment profiles, prompting strategies, and reasoning modes without human participants. Three LLM families (Claude, GPT, and Gemini) were benchmarked under zero-shot and few-shot prompting and standard versus advanced reasoning. Response accessibility was quantified using established readability metrics (Flesch Reading Ease, Dale-Chall) and a composite score derived from 16 standardized readability measures. Results: Distinct accessibility signatures emerged across model architectures and configurations. Few-shot prompting and advanced reasoning generally yielded more accessible clinician responses, whereas Gemini demonstrated superior accessibility under zero-shot, standard reasoning. Conclusions: LLMs differ systematically in their capacity to adapt clinician language to impaired speech. ABCD provides a scalable, preclinical dialogue simulation framework for benchmarking conversational AI in clinically oriented, impairment-rich dialogue across multidimensional constraints. It offers guidance for model selection and configuration prior to clinical translation in communication rehabilitation. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Speech, Language & Hearing Research is the property of American Speech-Language-Hearing Association and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
FullText Text:
  Availability: 0
Header DbId: edb
DbLabel: Complementary Index
An: 196185582
RelevancyScore: 1162
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1162.42456054688
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Preclinical Dialogue Simulation: Evaluating Response Accessibility in Conversational Artificial Intelligence for Aphasia Therapy.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Imaezue%2C+Gerald+C%2E%22">Imaezue, Gerald C.</searchLink><br /><searchLink fieldCode="AR" term="%22Maram%2C+Krishna+V%2E%22">Maram, Krishna V.</searchLink><br /><searchLink fieldCode="AR" term="%22Ajayi%2C+David%22">Ajayi, David</searchLink><br /><searchLink fieldCode="AR" term="%22Alohali%2C+Isra%22">Alohali, Isra</searchLink><br /><searchLink fieldCode="AR" term="%22Butta%2C+Rajesh+K%2E%22">Butta, Rajesh K.</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Journal of Speech, Language & Hearing Research; Aug2026, Vol. 69 Issue 8, p3781-3796, 16p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Statistical+models%22">Statistical models</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Rehabilitation+of+aphasic+persons%22">Rehabilitation of aphasic persons</searchLink><br /><searchLink fieldCode="DE" term="%22Benchmarking+%28Management%29%22">Benchmarking (Management)</searchLink><br /><searchLink fieldCode="DE" term="%22Readability+%28Literary+style%29%22">Readability (Literary style)</searchLink><br /><searchLink fieldCode="DE" term="%22Research+evaluation%22">Research evaluation</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+language+processing%22">Natural language processing</searchLink><br /><searchLink fieldCode="DE" term="%22Speech-language+pathology%22">Speech-language pathology</searchLink><br /><searchLink fieldCode="DE" term="%22Simulation+methods+in+education%22">Simulation methods in education</searchLink><br /><searchLink fieldCode="DE" term="%22Communicative+disorders%22">Communicative disorders</searchLink><br /><searchLink fieldCode="DE" term="%22Communication+devices+for+people+with+disabilities%22">Communication devices for people with disabilities</searchLink><br /><searchLink fieldCode="DE" term="%22Data+analysis+software%22">Data analysis software</searchLink><br /><searchLink fieldCode="DE" term="%22Speech+therapy%22">Speech therapy</searchLink><br /><searchLink fieldCode="DE" term="%22Regression+analysis%22">Regression analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Sensitivity+%26+specificity+%28Statistics%29%22">Sensitivity & specificity (Statistics)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Purpose: Large language model (LLM)-driven conversational agents are increasingly considered for use in clinical contexts, yet systematic approaches for evaluating their behavior in impairment-rich, speech-based therapeutic interactions remain limited. This study extends the Agent-Based Conversational Dialogue (ABCD) simulation method as a preclinical testbed to evaluate how LLMs generate accessible clinician language when responding to characteristic aphasic speech during Response Elaboration Training. Method: ABCD was used to simulate multi-turn spoken therapeutic dialogues between an LLM-driven clinician and an artificial intelligence (AI)-simulated aphasic patient, enabling controlled manipulation of impairment profiles, prompting strategies, and reasoning modes without human participants. Three LLM families (Claude, GPT, and Gemini) were benchmarked under zero-shot and few-shot prompting and standard versus advanced reasoning. Response accessibility was quantified using established readability metrics (Flesch Reading Ease, Dale-Chall) and a composite score derived from 16 standardized readability measures. Results: Distinct accessibility signatures emerged across model architectures and configurations. Few-shot prompting and advanced reasoning generally yielded more accessible clinician responses, whereas Gemini demonstrated superior accessibility under zero-shot, standard reasoning. Conclusions: LLMs differ systematically in their capacity to adapt clinician language to impaired speech. ABCD provides a scalable, preclinical dialogue simulation framework for benchmarking conversational AI in clinically oriented, impairment-rich dialogue across multidimensional constraints. It offers guidance for model selection and configuration prior to clinical translation in communication rehabilitation. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Speech, Language & Hearing Research is the property of American Speech-Language-Hearing Association and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=196185582
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1044/2026_JSLHR-26-00031
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 16
        StartPage: 3781
    Subjects:
      – SubjectFull: Statistical models
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Rehabilitation of aphasic persons
        Type: general
      – SubjectFull: Benchmarking (Management)
        Type: general
      – SubjectFull: Readability (Literary style)
        Type: general
      – SubjectFull: Research evaluation
        Type: general
      – SubjectFull: Natural language processing
        Type: general
      – SubjectFull: Speech-language pathology
        Type: general
      – SubjectFull: Simulation methods in education
        Type: general
      – SubjectFull: Communicative disorders
        Type: general
      – SubjectFull: Communication devices for people with disabilities
        Type: general
      – SubjectFull: Data analysis software
        Type: general
      – SubjectFull: Speech therapy
        Type: general
      – SubjectFull: Regression analysis
        Type: general
      – SubjectFull: Sensitivity & specificity (Statistics)
        Type: general
    Titles:
      – TitleFull: Preclinical Dialogue Simulation: Evaluating Response Accessibility in Conversational Artificial Intelligence for Aphasia Therapy.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Imaezue, Gerald C.
      – PersonEntity:
          Name:
            NameFull: Maram, Krishna V.
      – PersonEntity:
          Name:
            NameFull: Ajayi, David
      – PersonEntity:
          Name:
            NameFull: Alohali, Isra
      – PersonEntity:
          Name:
            NameFull: Butta, Rajesh K.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 10924388
          Numbering:
            – Type: volume
              Value: 69
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: Journal of Speech, Language & Hearing Research
              Type: main
ResultId 1