ChatGPT in Healthcare: Exploring AI Chatbot for Spontaneous Word Retrieval in Aphasia
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Having a word on the tip of one’s tongue can be frustrating. Individuals with a language disorder like aphasia, however, face this experience regularly, making it both stressful and debilitating. Large language models, such as ChatGPT, have been gaining traction in healthcare recently. They could enable digital voice assistants to help people find what they want to say during a conversation. However, research on the topic is still not mature. Our study aims at providing a first exploration of the potential use of LLMs for aphasia. Specifically, we aim to examine whether ChatGPT can aid in word retrieval in aphasia. In our study, ChatGPT is tested on real-life speech samples of people with aphasia using the AphasiaBank corpus. Additionally, we investigate whether ChatGPT can utilize politeness strategies. We found ChatGPT to be accurate in identifying the intended word 91.67% of the time as well as successful in incorporating politeness strategies.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“In this study, ChatGPT was found to be 91.67% accurate in detecting the target word and successful in combining politeness strategies [19].”
From Is there any room for ChatGPT AI bot in speech-language pathology? (2025) · cites this paper as [19]
The cited source says what the claim attributes to it.
In the citing paper
“In this study, ChatGPT was found to be 91.67% accurate in detecting the target word and successful in combining politeness strategies [19].”
From Is there any room for ChatGPT AI bot in speech-language pathology? (2025) · cites this paper as [19]
The cited source says what the claim attributes to it.
In the citing paper
“more than 90% accuracy was achieved in the responses to examples of people with different types of aphasia [19].”
From Is there any room for ChatGPT AI bot in speech-language pathology? (2025) · cites this paper as [19]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Politeness: Some Universals in Language Usage
Brown, P., Levinson, S. C., & Gumperz, J. J. (1987) · Cambridge University Press eBooks · doi:10.1017/cbo9780511813085 · Cited by 10,438
AphasiaBank: Methods for studying discourse
MacWhinney, B., Fromm, D., Forbes, M., & Holland, A. (2011) · Aphasiology · doi:10.1080/02687038.2011.589893 · Cited by 432 · cited 1×
“This preliminary study employs American English speech samples of PWA who underwent the AphasiaBank protocol from the Aphasi-aBank corpus [17].”
Cummings, L. (2009) · Cambridge University Press eBooks · doi:10.1017/cbo9780511581601 · Cited by 218
Palmer, R., Dimairo, M., Cooper, C., Enderby, P., Brady, M., Bowen, A., Latimer, N., Julious, S., Cross, E., Alshreef, A., et al. (2019) · The Lancet Neurology · doi:10.1016/s1474-4422(19)30192-9 · Cited by 200 · cited 3×
“Computer software such as StepByStep offers individuals with daily word-finding exercises based on their needs and chosen words and therapy software such as Linguagraphica provides a wide range of exercises that may be beneficial for the improvement of trained words [24].”
BackgroundMethodPragmatic aspects of intervention in aphasia
Holland, A. L. (1991) · Journal of Neurolinguistics · doi:10.1016/0911-6044(91)90007-6 · Cited by 158 · cited 1×
“4 Studies have suggested that PWA, just like healthy individuals, are sensitive to politeness breaches as a result of their relatively intact pragmatic skills [12, 29].”
BackgroundDiscourse Characteristics in Aphasia Beyond the Western Aphasia Battery Cutoff
Fromm, D., Forbes, M., Holland, A., Dalton, S. G., Richardson, J., & MacWhinney, B. (2017) · American Journal of Speech-Language Pathology · doi:10.1044/2016_ajslp-16-0071 · Cited by 145 · cited 2×
“The corpus also includes the extent of severity of aphasia that is measured quantitatively by the Western Aphasia Battery-Revised (WAB-R) score [9].”
BackgroundMethodInfluentialThe Western Aphasia Battery: a systematic review of research and clinical applications
Kertesz, A. (2020) · Aphasiology · doi:10.1080/02687038.2020.1852002 · Cited by 111 · cited 1×
“8 on the Aphasia Quotient (AQ) out of 100, with higher scores indicating better language function [14, 25].”
BackgroundNorthcott, S., Simpson, A., Moss, B., Ahmed, N., & Hilari, K. (2016) · International Journal of Language & Communication Disorders · doi:10.1111/1460-6984.12278 · Cited by 92 · cited 1×
“2 Furthermore, PWA are at a higher risk of developing depression [23].”
BackgroundAphasics' comprehension of contextually conveyed meaning
Wilcox, M. J., Davis, G. A., & Leonard, L. B. (1978) · Brain and Language · doi:10.1016/0093-934x(78)90069-x · Cited by 71 · cited 1×
“4 Studies have suggested that PWA, just like healthy individuals, are sensitive to politeness breaches as a result of their relatively intact pragmatic skills [12, 29].”
BackgroundSpeech and Language Therapy for Aphasia After Stroke
Brady, M., Godwin, J., Enderby, P., Kelly, H., & Campbell, P. (2016) · Stroke · doi:10.1161/strokeaha.116.014439 · Cited by 62
Research works printed but not linked: 10
- Som Biswas. 2023. Role of chatGPT in Journalism: According to chatGPT. Avail- able at SSRN 4405396 (2023).
- Leora R Cherney. 2010. Oral reading for language in aphasia (ORLA): Evaluating the efficacy of computer-delivered therapy in chronic nonfluent aphasia. Topics in stroke rehabilitation 17, 6 (2010), 423-431.
- Louise Cummings. 2009. Clinical Pragmatics. Cambridge University Press. https://doi.org/10.1017/CBO9780511581601 · DOI
- G Albyn Davis. 2013. Aphasia and related cognitive-communicative disorders. Pearson Higher Ed.
- Matthew B Hoy. 2018. Alexa, Siri, Cortana, and more: an introduction to voice assistants. Medical reference services quarterly 37, 1 (2018), 81-88.
- Brian MacWhinney. 2000. The CHILDES Project: Tools for analyzing talk. tran- scription format and programs. Vol. 1. Psychology Press.
- Joseph Newbold, Gavin Doherty, Sean Rintel, and Anja Thieme. 2019. Politeness Strategies in the Design of Voice Agents for Mental Health.
- Daniel Street and Joseph Wilck. 2023. 'Let's Have a Chat': Principles for the Effective Application of ChatGPT and Large Language Models in the Practice of Forensic Accounting. Available at SSRN 4351817 (2023).
- W Mieke E van de Sandt-Koenderman. 2011. Aphasia rehabilitation and the role of computer technology: Can we keep up with modern times? International journal of speech-language pathology 13, 1 (2011), 21-27.
- Meredith Wells. 2014. Computer-assisted anomia treatment for persons with chronic aphasia: generalization to untrained words. Journal of Medical Speech- Language Pathology 21, 2 (2014), 149-163.
Cited by
Moulaei, K., Yadegari, A., Baharestani, M., Farzanbakhsh, S., Sabet, B., & Reza Afrash, M. (2024) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105474 · Cited by 244
A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration
Gao, J., Gebreegziabher, S. A., Choo, K. T. W., Li, T. J.-J., Perrault, S. T., & Malone, T. W. (2024) · Extended Abstracts of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613905.3650786 · Cited by 57
User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistants
Mahmood, A., Wang, J., Yao, B., Wang, D., & Huang, C.-M. (2025) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2024.103406 · Cited by 51
Perceptions of Artificial Intelligence and ChatGPT by Speech-Language Pathologists and Students
Austin, J., Benas, K., Caicedo, S., Imiolek, E., Piekutowski, A., & Ghanim, I. (2025) · American Journal of Speech-Language Pathology · doi:10.1044/2024_ajslp-24-00218 · Cited by 31
Clinical efficacy of pre-trained large language models through the lens of aphasia
Cong, Y., LaCroix, A. N., & Lee, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-66576-y · Cited by 25
“Puro-hit et al. 19 explored ChatGPT in a qualitative text analysis, showcasing how prompt engineering can be used for word retrieval in aphasia.”
BackgroundAscleAI: A LLM-based Clinical Note Management System for Enhancing Clinician Productivity
Han, J., Park, J., Huh, J., Oh, U., Do, J., & Kim, D. (2024) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3613905.3650784 · Cited by 41
“The system integrates an Automatic Speech Recognition (ASR) model and a large language model (LLM) to seamlessly combine the strengths of both technologies for facilitating seamless interactions between clinicians, patients, and the system.”
Unlocking Memories with AI: Exploring the Role of AI-Generated Cues in Personal Reminiscing
Jeung, J. L., & Huang, Y. (2024) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3613905.3650979 · Cited by 23
“A study using ChatGPT demonstrated its potential in assisting word retrieval for individuals with language disorders, such as aphasia, which relates to memory retrieval processes [13].”
BackgroundChatGPT Dependency Disorder in Healthcare Practice: An Editorial
Samant, A. C., Tyagi, I., Vybhavi, J., Jha, H., & Patel, J. (2024) · Cureus · doi:10.7759/cureus.66155 · Cited by 16
Is there any room for ChatGPT AI bot in speech-language pathology?
Birol, N. Y., Çiftci, H. B., Yılmaz, A., Çağlayan, A., & Alkan, F. (2025) · European Archives of Oto-Rhino-Laryngology · doi:10.1007/s00405-025-09295-y · Cited by 12
How Can I Signal You To Trust Me: Investigating AI Trust Signalling in Clinical Self-Assessments
Kollerup, N. K., Wester, J., Skov, M. B., & van Berkel, N. (2024) · Designing Interactive Systems Conference · doi:10.1145/3643834.3661612 · Cited by 16
“For example, Purohit et al. showed how ChatGPT can support individuals with language disorders in retrieving words they have on the tip of the tongue [55].”
BackgroundKeppler, S. M., Sinchaisri, W. P., & Snyder, C. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3711026 · Cited by 14
“Experimental studies have shown that in many cases, this collaboration can be productive for singular, predefined tasks [12, 45, 48, 54, 57, 62, 64].”
Transphobia Is in the Eye of the Prompter: Trans-Centered Perspectives on Large Language Models
Scheuerman, M. K., Weathington, K., Petterson, A., Doyle, D. T., Das, D., DeVito, M. A., & Brubaker, J. R. (2025) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3743676 · Cited by 14
SketchGPT: A Sketch-based Multimodal Interface for Application-Agnostic LLM Interaction
Huang, Z., Gao, C., Shan, Y., Hu, H., Li, Q., Deng, X., Ma, C., Lai, Y., Liu, Y., Tian, F., et al. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747598 · Cited by 25
“Large language models (LLMs) are increasingly integrated into various tasks, from recording [11, 47] and reading [30] to health-care [32, 71, 74], voice processing [54], data analysis [87, 88, 97], etc.”
Hanna, M., & Yana, S. (2025) · International Journal of Language & Communication Disorders · doi:10.1111/1460-6984.70088 · Cited by 10
Mo, W., Singh, A., & Holloway, C. (2024) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663548.3675609 · Cited by 10
“For instance, studies suggested that it can support clinical decisions, and patient communication, and create synthetic patient data [42, 60].”
ChatGPT and Large Language Models in Healthcare; a Bibliometrics Analysis and Review
Mosavi, A. H., Imre, F., & Hùng, V. T. (2024) · IEEE International Conference on Computational Cybernetics (ICCC) · doi:10.1109/iccc62278.2024.10582937 · Cited by 11
Kurland, J., Varadharaju, V., Liu, A., Stokes, P., Gupta, A., Hudspeth, M., & O'Connor, B. (2025) · American Journal of Speech-Language Pathology · doi:10.1044/2025_ajslp-24-00400 · Cited by 9
Zhang, H., Zhang, J., Zhou, Y., Louie, R., Kim, T., Guo, Q., Li, S., & Peng, Z. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3711031 · Cited by 17
Harnessing AI for aphasia: a case report on ChatGPT's role in supporting written expression
Allen, A. K., Brennan, C., Riseman, C., Kleiber, H., & Hilger, A. (2025) · Frontiers in Rehabilitation Sciences · doi:10.3389/fresc.2025.1600145 · Cited by 9
Bailey, D. J., Anjum, J., Park, H., Carpenter, E., Mamlekar, C. R., & Kurland, J. (2026) · American Journal of Speech-Language Pathology · doi:10.1044/2025_ajslp-25-00262 · Cited by 7
Mytsyk, H., Kovachov, S., & Suchikova, Y. (2025) · Disability and Rehabilitation: Assistive Technology · doi:10.1080/17483107.2025.2472262 · Cited by 5
Reconstructing impaired language using generative AI for people with aphasia
Adikari, A., Alahakoon, D., Pallewela, N., Pierce, J. E., Hernandez, N. J., & Rose, M. L. (2025) · Scientific Reports · doi:10.1038/s41598-025-24725-x · Cited by 6
“Purohit et al. 19 explored ChatGPT’s ability to identify intended words in circumlocution produced by individuals with aphasia.”
Envisioning Possibilities and Challenges of AI for Personalized Cancer Care
Kong, E. W. S., Huang, K., & Gautam, A. (2024) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/3678884.3681885 · Cited by 6
“Each cancer journey is profoundly individual, and care services need to attend to these personal realities [20, 36, 42].”
Collaboratively Designing and Evaluating Responsible AI Interventions
Deng, W. H., Berman, G., Kaur, H., Schwartz, R., Ibrahim, M. A., Eslami, M., Holstein, K., & Madaio, M. (2024) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/3678884.3687136 · Cited by 5
“…responsible design of a healthcare chatbot may require software engineers to collaborate with user-facing roles to improve understanding of whether and how to design such tools in consideration of the different interaction types and expectations of patients or healthcare providers in context [13].”
Nagai, N., Miyamoto, T., & Katagami, D. (2025) · Applied Sciences · doi:10.3390/app15073897 · Cited by 4
Cheng, W.-H., Lee, Y., Jamieson, J., Wang, W.-H., & Lin, W. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757517 · Cited by 2
Kaur, J., & Singh, P. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757475 · Cited by 2
Customer Service Representative's Perception of the AI Assistant in an Organization's Call Center
Qin, K. K., Du, K., Chen, Y., Liu, Y., Cai, J., Nie, Z., Gao, N., Wei, G., Wang, S., & Yu, C. (2025) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/3715070.3749260 · Cited by 6
When Handwriting Goes Social: Creativity, Anonymity, and Communication in Graphonymous Online Spaces
Purohit, A. K., Upadhyaya, A., Ruiz, N., Roffarello, A. M., & Heuer, H. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790828 · Cited by 1
Self-citationThe role of AI in supporting written communication in aphasia: a qualitative interview study
Robinson, A., & Thiel, L. (2026) · Aphasiology · doi:10.1080/02687038.2026.2663784 · Cited by 1
Re-imagining Mental Health Access: The Role of Human, AI and Design
Iftikhar, Z. (2024) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/3678884.3682056
“Instead, new scalable approaches are emerging to expand access to care, including peer support platforms [11, 20] and recent advancements in AI, also known as large language models (LLMs) [13].”
Li, J., Hu, Y., Fu, S., Wu, Z., Hui, P., Wang, H., & Fan, M. (2024) · International Symposium of Chinese CHI (Chinese CHI) · doi:10.1145/3758871.3758911 · Cited by 2
“For example, chronic disease self-management [42], helping individuals with aphasia in word retrieval [34], developing rehabilitation plans [40], and remote diagnostic capabilities [29].”
Han, L., Wei, M., Chen, Q., Wang, A., Pang, R., & Yip, D. K. M. (2026) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3742413.3789085
“For example, Purohit et al. demonstrated how LLM-based methods can aid word retrieval for individuals with aphasia, suggesting broader applications in reminiscence therapy [65].”
Do-It-Yourself AAC: Co-Designing User-Programmable AI Communication Tools with People with Aphasia
Lee, J. H., & Valencia, S. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790321 · Cited by 1
“Augmentative and Alternative Communication (AAC) solutions can support PWA’s communication ranging from low-tech solutions such as picture boards [11] to sophisticated dictionaries and AI-enhanced technology [5, 28, 39].”
Lee, J., Worthy, P., Deslandes, R., Burton, B., Copland, D. A., Jamieson, P., Barron, K., Shrubsole, K., Togher, L., Hill, A. J., et al. (2026) · BMC Digital Health · doi:10.1186/s44247-026-00289-2
“While artificial intelligence (AI) tools and voice assistants can aid online searching [15, 16], there are mixed perceptions regarding their use amongst people with aphasia.”
ChatGPT Sensemaking and Appropriation in Everyday Life
Ma, R., McGrenere, J., & Lindqvist, J. (2026) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3816911 · Cited by 1
“Its applications also extend to healthcare, where it has been examined for patient monitoring and clinical decision support [15, 23, 106], as well as business contexts, where it can support customer service automation and communication workflows [24, 47].”
Abdelsattar, H. A., & Khan, S. A. (2026) · Aphasiology · doi:10.1080/02687038.2026.2747806
Pragmatica: A VR Tool for Autonomous Practice During Language Therapy
Prasad, K., Schneider, O., & Wallace, J. R. (2026) · Graphics Interface · doi:10.1145/3831423.3831432
“Purohit et al. [46] show how AI chatbots can be used to make NPCs more dynamic and interesting, or even to fully simulate social situations.”
Metadata
- Authors
- Purohit, A. K., Upadhyaya, A., & Holzer, A.
- Affiliations
- Radboud University Nijmegen (NL)
- Justus-Liebig-Universität Gießen (DE)
- University of Neuchâtel (CH)
- Venue
- Computer Supported Cooperative Work and Social Computing
- Publisher
- ACM
- Published
- 2023-10-14
- Pages
- 1-5
- OpenAlex
- W4387606041
- Cited by
- 38
- References
- 18
- Citations by year
- 2026: 9 · 2025: 14 · 2024: 15
- FWCI
- 6.74
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Conference on Computer Supported Cooperative Work (CSCW) (publishedVersion, cc-by)
- Radboud Repository (Radboud University) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- aphasia, ChatGPT, large language models, word retrieval, spontaneous speech, speech recognition, politeness strategies, voice assistants, language disorders
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.