Use of large language model-based chatbots in managing the rehabilitation concerns and education needs of outpatient stroke survivors and caregivers
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Background: The utility of large language model-based (LLM) artificial intelligence (AI) chatbots in many aspects of healthcare is becoming apparent though their ability to address patient concerns remains unknown. We sought to evaluate the performance of two well-known, freely-accessible chatbots, ChatGPT and Google Bard, in responding to common questions about stroke rehabilitation posed by patients and their caregivers. Methods: We collected questions from outpatients and their caregivers through a survey, categorised them by theme, and created representative questions to be posed to both chatbots. We then evaluated the chatbots' responses based on accuracy, safety, relevance, and readability. Interrater agreement was also tracked. Results: Although both chatbots achieved similar overall scores, Google Bard performed slightly better in relevance and safety. Both provided readable responses with some general accuracy, but struggled with hallucinated responses, were often not specific, and lacked awareness of the possibility for emotional situations with the potential to turn dangerous. Additionally, interrater agreement was low, highlighting the variability in physician acceptance of their responses. Conclusions: AI chatbots show potential in patient-facing support roles, but issues remain regarding safety, accuracy, and relevance. Future chatbots should address these problems to ensure that they can reliably and independently manage the concerns and questions of stroke patients and their caregivers.
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.
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
Large Language Models Encode Clinical Knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.13138 · Cited by 4,083
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083 · cited 2×
“A fourth limitation is the use of more outdated LLM frameworks over more recent or speci fi c ones such as GPT-4 and Med-PaLM.”
BackgroundDave, T., Athaluri, S. A., & Singh, S. (2023) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2023.1169595 · Cited by 1,204
Almanac — Retrieval-Augmented Language Models for Clinical Medicine
Zakka, C., Shad, R., Chaurasia, A., Dalal, A. R., Kim, J. L., Moor, M., Fong, R., Phillips, C., Alexander, K., Ashley, E., et al. (2024) · NEJM AI · doi:10.1056/aioa2300068 · Cited by 424
Parviainen, J., & Rantala, J. (2022) · Medicine, Health Care and Philosophy · doi:10.1007/s11019-021-10049-w · Cited by 146
Gianola, S., Bargeri, S., Castellini, G., Cook, C., Palese, A., Pillastrini, P., Salvalaggio, S., Turolla, A., & Rossettini, G. (2024) · Journal of Orthopaedic & Sports Physical Therapy · doi:10.2519/jospt.2024.12151 · Cited by 62
Cited by
Sezgin, E., Jackson, D. I., Kocaballi, A. B., Bibart, M., Zupanec, S., Landier, W., Audino, A., Ranalli, M., & Skeens, M. (2025) · Cancer Medicine · doi:10.1002/cam4.70554 · Cited by 30
Kim, J., Won, J., & Lee, Y. (2025) · Nurse Education in Practice · doi:10.1016/j.nepr.2025.104536 · Cited by 10
Evaluating the role of ChatGPT in rehabilitation medicine: a narrative review
Luo, M., Duan, Z., Gao, J., Sun, Y., Chen, L., & Feng, X. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1618510 · Cited by 5
Metadata
- Authors
- Neo, J. R. E., Ser, J. S., & Tay, S. S.
- Venue
- Frontiers in Digital Health
- Publisher
- Frontiers Media SA
- Published
- 2024-05-09
- Volume
- 6
- Pages
- 1395501-1395501
- ISSN
- 2673-253X (ISSN-L)
- OpenAlex
- W4396775758
- Cited by
- 44
- References
- 6
- FWCI
- 3.53
- Type
- journal article
- Language
- en
- Open access
- gold
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.