{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T13:54:27Z","timestamp":1791554067907,"version":"4.3.4"},"reference-count":44,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Aphasia, an acquired language disorder that affects the ability to understand and produce language, significantly impairs effective communication. Large language models (LLMs) such as ChatGPT may help by generating fluent and coherent text, offering new ways to support communication for people with aphasia.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to coproduce a communication support system using LLMs and evaluate its usefulness and acceptability among people with mild-to-moderate expressive aphasia.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We used the Double Diamond approach across 3 phases. Phase 1: a stroke-survivor patient and public involvement (PPI) group (n=4) and the research team used MoSCoW prioritization (Must Have, Should Have, Could Have, Will Not Have) to rank ideas and co-design a software solution (Revolutionizing Speech Enhancement in Aphasia Using Knowledgeable-AI [R-SPEAK]) to augment verbal communication. Phase 2: 8 LLMs were evaluated on interpreting aphasic utterances from AphasiaBank transcripts. Outputs were compared, and the best responses, selected by team consensus, formed ground truth. The model producing the highest-quality responses was used in the prototype. Four people with aphasia and one carer (n=5) evaluated the prototype in semistructured interviews, and a health care professional (HCP) focus group (n=6) evaluated the concept and prototype. Topic guides were informed by the technology acceptance model (TAM), and thematic analysis themes were mapped onto its constructs. People with aphasia (n=4) rated prototype usability using the System Usability Scale (SUS). Phase 3: to improve processing speed, 12 lightweight LLMs (0.5-4 billion parameters) were evaluated on interpreting real aphasic speech using an LLM-as-a-judge framework to assess answer relevancy, faithfulness, and completeness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In Phase 1, PPI groups (people living with aphasia, carers, and HCPs) identified essential system features and contextual data requirements across 2 co-ideation sessions using MoSCoW prioritization. In Phase 2, Mixtral 8x7B, the best-performing LLM for interpreting aphasic utterances, was used for the prototype. People living with aphasia rated R-SPEAK as good (SUS score: mean 75, SD 9.19). Themes mapped across three TAM constructs. (1) Attitude toward using it: people living with aphasia had high hopes, while clinicians were more cautious about its benefits. (2) Perceived ease of use: participants found it easy, though potentially harder for those with other poststroke impairments or more severe aphasia, with training possibly needed. (3) Perceived usefulness: R-SPEAK could be useful in many scenarios and improve independence. Recommendations included improved accuracy, speed, and tailored interface modifications. Phase 3 showed Qwen2.5:3B performed strongest overall, with high faithfulness and sub-second latency, while models under 1.5 billion parameters showed pronounced hallucination, indicating a lower bound on model capacity for reliable clinical speech interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our co-designed AI-supported R-SPEAK prototype was considered acceptable to patients. Next steps involve refining and developing a smartphone app for feasibility testing in a larger cohort of people with mild-to-moderate aphasia.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/93518","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T15:05:05Z","timestamp":1784559905000},"page":"e93518-e93518","source":"Crossref","is-referenced-by-count":0,"title":["R-SPEAK, an AI-Based Smartphone App to Enhance Communication in People With Expressive Aphasia: Qualitative Acceptability and Usability Study"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2459-0298","authenticated-orcid":false,"given":"Abdel-Karim","family":"Al-Tamimi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8408-5782","authenticated-orcid":false,"given":"Jacob","family":"Andrews","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8807-3049","authenticated-orcid":false,"given":"Jacqueline","family":"Benfield","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3510-2193","authenticated-orcid":false,"given":"Cath","family":"Sweby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5845-9429","authenticated-orcid":false,"given":"Chris","family":"Gilmartin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5224-8230","authenticated-orcid":false,"given":"Rebecca","family":"Lindley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6995-1192","authenticated-orcid":false,"given":"Diane","family":"Trusson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5952-8372","authenticated-orcid":false,"given":"Molly","family":"Dziunka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8955-2044","authenticated-orcid":false,"given":"Dee","family":"Webster","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6246-3180","authenticated-orcid":false,"given":"Kathryn","family":"Radford","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"issue":"7","key":"R1","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1080\/02687038.2020.1759772","article-title":"Prevalence of aphasia and dysarthria among inpatient stroke survivors: describing the population, therapy provision and outcomes on discharge","volume":"35","author":"Mitchell","journal-title":"Aphasiology"},{"key":"R2","doi-asserted-by":"crossref","unstructured":"Whitworth A Webster J Howard D . A Cognitive Neuropsychological Approach to Assessment and Intervention in Aphasia: A Clinician\u2019s Guide. Psychology Press; 2005. ISBN: 9786610175048","DOI":"10.4324\/9780203493502"},{"issue":"11","key":"R3","doi-asserted-by":"publisher","first-page":"1338","DOI":"10.1080\/02687030902732745","article-title":"A meta-analysis of word-finding treatments for aphasia","volume":"23","author":"Wisenburn","journal-title":"Aphasiology"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1044\/2021_AJSLP-20-00265","article-title":"The subjective experience of word-finding difficulties in people with aphasia: a thematic analysis of interview data","volume":"31","author":"Fama","journal-title":"Am J Speech Lang Pathol"},{"issue":"5","key":"R5","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1159\/000088671","article-title":"Rehabilitation of left brain-damaged ischemic stroke patients: the role of comprehension language deficits. A matched comparison","volume":"20","author":"Paolucci","journal-title":"Cerebrovasc Dis"},{"issue":"6","key":"R6","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1080\/02687038.2016.1218436","article-title":"\u201cStruggling to stay connected\u201d: comparing the social relationships of healthy older people and people with stroke and aphasia","volume":"31","author":"Hilari","journal-title":"Aphasiology"},{"issue":"10","key":"R7","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2017-017944","article-title":"Longer-term needs of stroke survivors with communication difficulties living in the community: a systematic review and thematic synthesis of qualitative studies","volume":"7","author":"Wray","journal-title":"BMJ Open"},{"issue":"2","key":"R8","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1044\/2019_AJSLP-19-00041","article-title":"Revisiting the role of augmentative and alternative communication in aphasia rehabilitation","volume":"29","author":"Dietz","journal-title":"Am J Speech Lang Pathol"},{"issue":"12","key":"R9","doi-asserted-by":"publisher","first-page":"974","DOI":"10.1080\/02699200802394831","article-title":"Co\u2010constructed talk in the conversations of people with dysarthria and aphasia","volume":"22","author":"Bloch","journal-title":"Clin Linguist Phon"},{"key":"R10","doi-asserted-by":"crossref","unstructured":"Brown E Cairns P . A grounded investigation of game immersion extended abstracts on human factors in computing systems. Presented at: CHI EA\u201924 Extended Abstracts of the CHI Conference on Human Factors in Computing Systems; May 11-16, 2024:1297-1300; Honolulu, HI, USA. URL: https:\/\/dl.acm.org\/doi\/proceedings\/10.1145\/3613905 [Accessed 30-09-2026] [doi: 10.1145\/985921.986048]","DOI":"10.1145\/985921.986048"},{"key":"R11","doi-asserted-by":"crossref","unstructured":"Yu D Deng L . Automatic Speech Recognition: A Deep Learning Approach. Springer; 2015. [doi: 10.1007\/978-1-4471-5779-3]","DOI":"10.1007\/978-1-4471-5779-3"},{"key":"R12","doi-asserted-by":"crossref","unstructured":"Sharma S Mhasakar M Mehra A et al. Comuniqa: exploring large language models for improving english speaking skills. Presented at: COMPASS \u201924: Proceedings of the 7th ACM SIGCAS\/SIGCHI Conference on Computing and Sustainable Societies; Jul 8-11, 2024; New Delhi, India. URL: https:\/\/dl.acm.org\/doi\/proceedings\/10.1145\/3674829 [Accessed 15-09-2026] [doi: 10.1145\/3674829.3675082]","DOI":"10.1145\/3674829.3675082"},{"key":"R13","unstructured":"van den Oord A Dieleman S Zen H et al. WaveNet: a generative model for raw audio. arXiv. Preprint posted online on Sep 12, 2016. URL: https:\/\/arxiv.org\/abs\/1609.03499 [Accessed 30-09-2026]"},{"key":"R14","unstructured":"Arik SO Chen J Peng K Wei P Zhou Y . Neural voice cloning with a few samples. Presented at: NIPS\u201918: 32nd International Conference on Neural Information Processing Systems; Dec 3-8, 2018; Montr\u00e9al, Canada. 2018.URL: https:\/\/dl.acm.org\/doi\/10.5555\/3327546.3327667 [Accessed 30-09-2026]"},{"key":"R15","doi-asserted-by":"crossref","unstructured":"Yang Z Ishay A Lee J . Coupling large language models with logic programming for robust and general reasoning from text. Presented at: Findings of the Association for Computational Linguistics; Jul 9-14, 2023; Toronto, Canada. URL: https:\/\/aclanthology.org\/2023.findings-acl [Accessed 30-09-2026] [doi: 10.18653\/v1\/2023.findings-acl.321]","DOI":"10.18653\/v1\/2023.findings-acl.321"},{"key":"R16","unstructured":"Vatsal S Dubey H . A survey of prompt engineering methods in large language models for different NLP tasks. arXiv. Preprint posted online on Jul 17, 2024. URL: https:\/\/arxiv.org\/abs\/2407.12994 [Accessed 17-09-2202doi: 10.48550\/arXiv.2407.12994]"},{"issue":"6","key":"R17","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1111\/1460-6984.12762","article-title":"\u2018I think writing is everything\u2019: an exploration of the writing experiences of people with aphasia","volume":"57","author":"Thiel","journal-title":"Intl J Lang Comm Disor"},{"issue":"11","key":"R18","doi-asserted-by":"publisher","first-page":"4176","DOI":"10.1044\/2024_JSLHR-24-00045","article-title":"Automatic speech recognition of conversational speech in individuals with disordered speech","volume":"67","author":"Tobin","journal-title":"J Speech Lang Hear Res"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-80764-w","article-title":"Enhancing dysarthric speech recognition through SepFormer and hierarchical attention network models with multistage transfer learning","volume":"14","author":"Vinotha","journal-title":"Sci Rep"},{"key":"R20","doi-asserted-by":"crossref","unstructured":"Hrivn\u00e1kov\u00e1 D V\u00e1czlavov\u00e1 E Laco M , editors. Modified double diamond design methodology for innovative interfaces in the medical domain. Presented at: Proceedings of the Future Technologies Conference (FTC) 2025; Nov 6-7, 2025; Munich, Germany. URL: https:\/\/link.springer.com\/chapter\/10.1007\/978-3-032-07989-3_12 [Accessed 30-09-2026] [doi: 10.1007\/978-3-032-07989-3_12]","DOI":"10.1007\/978-3-032-07989-3_12"},{"issue":"6","key":"R21","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1093\/intqhc\/mzm042","article-title":"Consolidated criteria for reporting qualitative research (COREQ): a 32-item checklist for interviews and focus groups","volume":"19","author":"Tong","journal-title":"Int J Qual Health Care"},{"key":"R22","unstructured":"The DSDM Agile project framework. Agile Business Consortium. URL: https:\/\/www.agilebusiness.org\/resource\/the-dsdm-agile-project-framework\/ [Accessed 30-09-2026]"},{"key":"R23","unstructured":"AphasiaBank. TalkBank. 2017. URL: https:\/\/talkbank.org\/aphasia\/ [Accessed 30-09-2026]"},{"issue":"11","key":"R24","doi-asserted-by":"publisher","first-page":"1286","DOI":"10.1080\/02687038.2011.589893","article-title":"AphasiaBank: methods for studying discourse","volume":"25","author":"Macwhinney","journal-title":"Aphasiology"},{"issue":"3","key":"R25","doi-asserted-by":"publisher","first-page":"319","DOI":"10.2307\/249008","article-title":"Perceived usefulness, perceived ease of use, and user acceptance of information technology","volume":"13","author":"Davis","journal-title":"MIS Q"},{"key":"R26","unstructured":"Marikyan D Papagiannidis S . Technology acceptance model: a review. In: Papagiannidis S , editor. TheoryHub Book. Newcastle University; URL: https:\/\/open.ncl.ac.uk\/ [Accessed 30-09-2026]"},{"key":"R27","doi-asserted-by":"crossref","unstructured":"Green J . Thorogood N , editor. Qualitative Methods for Health Research. 4th ed. SAGE Publications Ltd; 2018. [doi: 10.4135\/9781036234386]","DOI":"10.4135\/9781036234386"},{"issue":"7","key":"R28","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1080\/10447318.2018.1455307","article-title":"The System Usability Scale: Past, Present, and Future","volume":"34","author":"Lewis","journal-title":"Int J Hum-Comput Interact"},{"key":"R29","unstructured":"Simmons-Mackie N Kagan A Shumway E . Aphasia Severity Rating. Aphasia Institute. 2018. URL: https:\/\/www.aphasia.ca\/health-care-providers\/resources-and-tools\/rating-scales\/#ASR [Accessed 30-09-2026]"},{"issue":"2","key":"R30","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1191\/1478088706qp063oa","article-title":"Using thematic analysis in psychology","volume":"3","author":"Braun","journal-title":"Qual Res Psychol"},{"issue":"3","key":"R31","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1080\/14780887.2020.1769238","article-title":"One size fits all? What counts as quality practice in (reflexive) thematic analysis?","volume":"18","author":"Braun","journal-title":"Qual Res Psychol"},{"issue":"13","key":"R32","doi-asserted-by":"publisher","first-page":"1753","DOI":"10.1177\/1049732315617444","article-title":"Sample size in qualitative interview studies: guided by information power","volume":"26","author":"Malterud","journal-title":"Qual Health Res"},{"key":"R33","doi-asserted-by":"crossref","unstructured":"Zheng L Chiang WL Sheng Y et al. Judging LLM-as-a-judge with MT-bench and chatbot arena. Presented at: Advances in Neural Information Processing Systems 36; Dec 10-16, 2023:46595-46623; New Orleans, Louisiana, USA. 2023.URL: http:\/\/www.proceedings.com\/75280.html [Accessed 30-09-2026] [doi: 10.52202\/075280-2020]","DOI":"10.52202\/075280-2020"},{"key":"R34","unstructured":"Thomas BK . Quantifying speech pause durations in speakers with nonfluent and fluent aphasia [dissertation]. Brigham Young University; 2021. URL: https:\/\/scholarsarchive.byu.edu\/etd\/8939 [Accessed 15-09-2026]"},{"issue":"9","key":"R35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0239715","article-title":"A randomised trial of social support group intervention for people with aphasia: a novel application of virtual reality","volume":"15","author":"Marshall","journal-title":"PLoS One"},{"key":"R36","doi-asserted-by":"crossref","unstructured":"Mao L Lee JH Faroqi-Shah Y Valencia S . Design probes for AI-driven AAC: addressing complex communication needs in aphasia. Presented at: DIS \u201925: Proceedings of the 2025 ACM Designing Interactive Systems Conference; Jul 5-9, 2025; Madeira, Portugal. URL: https:\/\/dl.acm.org\/doi\/proceedings\/10.1145\/3715336 [Accessed 30-09-2026] [doi: 10.1145\/3715336.3735736]","DOI":"10.1145\/3715336.3735736"},{"key":"R37","unstructured":"Anubhav Misra SG Anwar S . Assistive completion of agrammatic aphasic sentences: a transfer learning approach using a neurolinguistics-based synthetic dataset. arXiv. Preprint posted online on Nov 10, 2022. URL: https:\/\/arxiv.org\/abs\/2211.05557 [Accessed 30-09-2026] [doi: 10.48550\/arXiv.2211.05557]"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3639109","article-title":"Generating completions for fragmented Broca\u2019s aphasic sentences using large language models","volume":"PP","author":"van Vaals","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"R39","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1080\/02687038.2024.2445663","article-title":"Generative AI applied to AAC for aphasia: a pilot study of Aphasia-GPT","volume":"40","author":"Bailey","journal-title":"Aphasiology"},{"issue":"1","key":"R40","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-24725-x","article-title":"Reconstructing impaired language using generative AI for people with aphasia","volume":"15","author":"Adikari","journal-title":"Sci Rep"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI230016","article-title":"Concept and pictogram-based user-interface design of a helper tool for people with aphasia","volume":"302","author":"Patrick Mayer","journal-title":"Stud Health Technol Inform"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2024.1401240","article-title":"AI-assisted assessment and treatment of aphasia: a review","volume":"12","author":"Zhong","journal-title":"Front Public Health"},{"issue":"1","key":"R43","doi-asserted-by":"publisher","first-page":"41","DOI":"10.3233\/ACS-230005","article-title":"Big data and artificial intelligence in post-stroke aphasia: a mapping review","volume":"27","author":"Pottinger","journal-title":"Adv Commun Swallow"},{"key":"R44","unstructured":"Funding projects to deliver better rehabilitation and improved outcomes. Rehab Technologies Network. URL: https:\/\/www.rehabtechnologies.net\/fundedprojects [Accessed 15-09-2026]"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T13:43:38Z","timestamp":1791553418000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e93518"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,8]]},"references-count":44,"URL":"https:\/\/doi.org\/10.2196\/93518","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,8]]},"article-number":"v28i7e93518"}}