Preserving meaning while improving access: community-engaged AI-Assisted aphasia-friendly text adaptation

Purpose Black individuals experience aphasia at disproportionately high rates following stroke, yet culturally responsive reading interventions remain scarce. While artificial intelligence (AI) offers promise for increasing accessibility, its use in adapting culturally and historically significant texts for individuals with aphasia has been largely unexplored. This study examined the feasibility of an AI-supported, community-engaged model for developing aphasia-friendly reading materials that prioritize linguistic accessibility, cultural relevance, and historical accuracy.Methods The study employed a mixed-methods design grounded in a social constructivist framework and guided by Community-Based Participatory Research (CBPR) principles. Black persons with aphasia (PWA), caregivers, and clinicians were engaged as collaborators throughout the project. A curated subset of contributions from the August 18, 2019, issue of The New York Times Magazine, devoted to The 1619 Project, was transformed into an aphasia-friendly reader and evaluated using matched-corpus readability analysis and stakeholder feedback.Results In the matched nine-contribution prose corpus, adaptation reduced word count from 33,460 to 1,887 (94.4%). Flesch Reading Ease increased from 54.2 to 79.6, and Flesch-Kincaid Grade Level decreased from 11.5 to 4.0, indicating a substantial reduction in surface linguistic complexity. These descriptive metrics do not establish aphasia comprehension or treatment efficacy. Qualitative analysis yielded three primary themes: (1) Historical and Cultural Accuracy, emphasizing the necessity of precise terminology and preservation of contextual meaning; (2) Accessibility and Comprehension, highlighting preferences for person-centered design features such as open-ended questions, multimodal supports, and flexible formats; and (3) Ethical and Practical Considerations, demonstrating the need for culturally informed human oversight, equitable access, and safeguards against misrepresentation or commodification of culturally significant content.Conclusions This preliminary community-engaged evaluation demonstrates the feasibility of using AI to support culturally responsive aphasia-friendly text adaptation while showing that lower linguistic complexity does not by itself guarantee historical or cultural fidelity. By centering the voices of Black individuals with aphasia and a caregiver, the study identifies human and community oversight as a necessary design constraint rather than an optional final review step. Further testing is needed to establish comprehension, usability, and clinical effectiveness.

Authors

Institutions

Publication Details

Journal
Aphasiology
Published
2026-11-12
DOI
https://doi.org/10.1080/02687038.2026.2763002
Primary Topic
Text Readability and Simplification
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Preserving meaning while improving access: community-engaged AI-Assisted aphasia-friendly text adaptation

Brittany Myburgh, Brandi L. Newkirk-Turner, Walter Evan Brown
Aphasiology
Text Readability and Simplification
article

Preserving meaning while improving access: community-engaged AI-Assisted aphasia-friendly text adaptation

Brittany Myburgh, Brandi L. Newkirk-Turner, Walter Evan Brown
article en

Abstract

Purpose Black individuals experience aphasia at disproportionately high rates following stroke, yet culturally responsive reading interventions remain scarce. While artificial intelligence (AI) offers promise for increasing accessibility, its use in adapting culturally and historically significant texts for individuals with aphasia has been largely unexplored. This study examined the feasibility of an AI-supported, community-engaged model for developing aphasia-friendly reading materials that prioritize linguistic accessibility, cultural relevance, and historical accuracy.Methods The study employed a mixed-methods design grounded in a social constructivist framework and guided by Community-Based Participatory Research (CBPR) principles. Black persons with aphasia (PWA), caregivers, and clinicians were engaged as collaborators throughout the project. A curated subset of contributions from the August 18, 2019, issue of The New York Times Magazine, devoted to The 1619 Project, was transformed into an aphasia-friendly reader and evaluated using matched-corpus readability analysis and stakeholder feedback.Results In the matched nine-contribution prose corpus, adaptation reduced word count from 33,460 to 1,887 (94.4%). Flesch Reading Ease increased from 54.2 to 79.6, and Flesch-Kincaid Grade Level decreased from 11.5 to 4.0, indicating a substantial reduction in surface linguistic complexity. These descriptive metrics do not establish aphasia comprehension or treatment efficacy. Qualitative analysis yielded three primary themes: (1) Historical and Cultural Accuracy, emphasizing the necessity of precise terminology and preservation of contextual meaning; (2) Accessibility and Comprehension, highlighting preferences for person-centered design features such as open-ended questions, multimodal supports, and flexible formats; and (3) Ethical and Practical Considerations, demonstrating the need for culturally informed human oversight, equitable access, and safeguards against misrepresentation or commodification of culturally significant content.Conclusions This preliminary community-engaged evaluation demonstrates the feasibility of using AI to support culturally responsive aphasia-friendly text adaptation while showing that lower linguistic complexity does not by itself guarantee historical or cultural fidelity. By centering the voices of Black individuals with aphasia and a caregiver, the study identifies human and community oversight as a necessary design constraint rather than an optional final review step. Further testing is needed to establish comprehension, usability, and clinical effectiveness.

Aphasiology
Jackson State University (US)
Text Readability and Simplification
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon