Evaluating the Potential of Large Language Models for Vestibular Rehabilitation Education: A Comparison of ChatGPT, Google Gemini, and Clinicians
Open accessPublished version of a preprint
Abstract
Objective: This study aimed to compare the performance of 2 large language models, ChatGPT (Generative Pre-trained Transformer) and Google Gemini, against experienced physical therapists and students in responding to multiple-choice questions related to vestibular rehabilitation. The study further aimed to assess the accuracy of ChatGPT’s responses by board-certified otoneurologists. Methods: This study was conducted among 30 physical therapist professionals experienced with vestibular rehabilitation and 30 physical therapist students. They were asked to complete a vestibular knowledge test (VKT) consisting of 20 multiple-choice questions that were divided into 3 categories: (1) Clinical Knowledge, (2) Basic Clinical Practice, and (3) Clinical Reasoning. ChatGPT and Google Gemini were tasked with answering the same 20 VKT questions. Three board-certified otoneurologists independently evaluated the accuracy of each response using a 4-level scale, ranging from comprehensive to completely incorrect. Results: ChatGPT outperformed Google Gemini with a 70% score on the VKT test, while Gemini scored 60%. Both excelled in Clinical Knowledge scoring 100% but struggled in Clinical Reasoning with ChatGPT scoring 50% and Gemini scoring 25%. According to 3 otoneurologic experts, ChatGPT’s accuracy was considered “comprehensive” in 45% of the 20 questions, while 25% were found to be completely incorrect. ChatGPT provided “comprehensive” responses in 50% of Clinical Knowledge and Basic Clinical Practice questions, but only 25% in Clinical Reasoning. Conclusion: Caution is advised when using ChatGPT and Google Gemini due to their limited accuracy in clinical reasoning. While they provide accurate responses concerning Clinical Knowledge, their reliance on web information may lead to inconsistencies. ChatGPT performed better than Gemini. Health care professionals should carefully formulate questions and be aware of the potential influence of the online prevalence of information on ChatGPT’s and Google Gemini’s responses. Combining clinical expertise and clinical guidelines with ChatGPT and Google Gemini can maximize benefits while mitigating limitations. The results are based on current models of ChatGPT3.5 and Google Gemini. Future iterations of these models are expected to offer improved accuracy as the underlying modeling and algorithms are further refined. Impact: This study highlights the potential utility of large language models like ChatGPT in supplementing clinical knowledge for physical therapists, while underscoring the need for caution in domains requiring complex clinical reasoning. The findings emphasize the importance of integrating technological tools carefully with human expertise to enhance patient care and rehabilitation outcomes.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
AI-assisted learning is not inherently good or bad; its impact on nursing education depends on how, when, and with what pedagogical factors it is applied.
“AI-assisted learning is not a bad or good practice, but the impact of this tool on the nursing education sector heavily relies on the way it is applied, at what time, and what pedagogical factors are taken into consideration [24].”
From HOW AI TOOLS (LIKE CHATGPT/GEMINI) AFFECT CRITICAL THINKING IN NURSING STUDENTS. A SYSTEMATIC REVIEW (2026) · cites this paper as [24]
The Discussion (page unavailable in our copy) says AI tools can aid health care learning in specific uses, while their usefulness depends on careful prompting and the task’s complexity. It also discusses critical thinking and problem-based learning. The paper studies vestibular rehabilitation education, however, and does not establish the claim specifically for nursing education or address when AI-assisted learning should be applied. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
A revision of bloom's taxonomy: an overview
Krathwohl, D. R. (2002) · Theory Into Practice · doi:10.1207/s15430421tip4104_2 · Cited by 8,132 · see citing works
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115 · see citing works
Sallam, M. (2023) · Healthcare · doi:10.3390/healthcare11060887 · Cited by 3,126 · cited 1× · see citing works
“26 Likewise, instead of sifting through every necessary article or available data, ChatGPT and Google Gemini can diminish the workload by retrieving only the most relevant information, providing that the user ensures that the uploaded data is up-to-date and is precise when prompting the AI.”
Gilson, A., Safranek, C. W., Huang, T., Socrates, V., Chi, L., Taylor, R. A., & Chartash, D. (2023) · JMIR Medical Education · doi:10.2196/45312 · Cited by 2,078 · see citing works
Staab, J. P., Eckhardt-Henn, A., Horii, A., Jacob, R., Strupp, M., Brandt, T., & Bronstein, A. (2017) · Journal of Vestibular Research · doi:10.3233/ves-170622 · Cited by 840 · see citing works
Clinical Practice Guideline: Benign Paroxysmal Positional Vertigo (Update)
Bhattacharyya, N., Gubbels, S. P., Schwartz, S., Edlow, J. A., El‐Kashlan, H. K., Fife, T. D., Holmberg, J. M., Mahoney, K., Hollingsworth, D. B., Roberts, R. A., et al. (2017) · Otolaryngology · doi:10.1177/0194599816689667 · Cited by 819 · see citing works
von Brevern, M., Bertholon, P., Brandt, T., Fife, T., Imai, T., Nuti, D., & Newman-Toker, D. (2015) · Journal of Vestibular Research · doi:10.3233/ves-150553 · Cited by 795 · see citing works
Bisdorff, A., Von Brevern, M., Lempert, T., & Newman-Toker, D. E. (2009) · Journal of Vestibular Research · doi:10.3233/ves-2009-0343 · Cited by 742 · see citing works
Yeo, Y. H., Samaan, J. S., Ng, W. H., Ting, P., Trivedi, H. D., Vipani, A., Ayoub, W. S., Yang, J. D., Liran, O., Spiegel, B. M. R., et al. (2023) · Clinical and Molecular Hepatology · doi:10.3350/cmh.2023.0089 · Cited by 655 · see citing works
Introducing artificial intelligence training in medical education
Paranjape, K., Schinkel, M., Nannan Panday, R., Car, J., & Nanayakkara, P. (2019) · JMIR Medical Education · doi:10.2196/16048 · Cited by 634 · see citing works
Evaluating the Performance of ChatGPT in Ophthalmology
Antaki, F., Touma, S., Milad, D., El-Khoury, J., & Duval, R. (2023) · Ophthalmology Science · doi:10.1016/j.xops.2023.100324 · Cited by 563 · see citing works
Samaan, J. S., Yeo, Y. H., Rajeev, N., Hawley, L., Abel, S., Ng, W. H., Srinivasan, N., Park, J., Burch, M., Watson, R., et al. (2023) · Obesity Surgery · doi:10.1007/s11695-023-06603-5 · Cited by 282 · see citing works
Vestibular paroxysmia: Diagnostic criteria
Strupp, M. L., Lopez-Escamez, J. A., Kim, J., Straumann, D., Jen, J. C., Carey, J. P., Bisdorff, A., & Brandt, T. (2017) · Journal of Vestibular Research · doi:10.3233/ves-160589 · Cited by 237 · see citing works
Can ChatGPT pass the life support exams without entering the American heart association course?
Fijačko, N., Gosak, L., Štiglic, G., Picard, C. T., & John Douma, M. (2023) · Resuscitation · doi:10.1016/j.resuscitation.2023.109732 · Cited by 206 · see citing works
Hoch, C. C., Wollenberg, B., Lüers, J.-C., Knoedler, S., Knoedler, L., Frank, K., Cotofana, S., & Alfertshofer, M. (2023) · European Archives of Oto-Rhino-Laryngology · doi:10.1007/s00405-023-08051-4 · Cited by 154 · see citing works
Gemini versus ChatGPT: applications, performance, architecture, capabilities, and implementation
Rane, N., Choudhary, S., & Rane, J. (2024) · Journal of Applied Artificial Intelligence · doi:10.48185/jaai.v5i1.1052 · Cited by 149 · see citing works
Differentiating ChatGPT-Generated and Human-Written Medical Texts: Quantitative Study
Liao, W., Liu, Z., Dai, H., Xu, S., Wu, Z., Zhang, Y., Huang, X., Zhu, D., Cai, H., Li, Q., et al. (2023) · JMIR Medical Education · doi:10.2196/48904 · Cited by 135 · see citing works
Differentiate ChatGPT-generated and Human-written Medical Texts
Liao, W., Liu, Z., Dai, H., Xu, S., Wu, Z., Zhang, Y., Huang, X., Zhu, D., Cai, H., Liu, T., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.11567 · Cited by 119
Moons, P., & Van Bulck, L. (2023) · European Journal of Cardiovascular Nursing · doi:10.1093/eurjcn/zvad022 · Cited by 118 · see citing works
Hall, C. D., Herdman, S. J., Whitney, S. L., Anson, E. R., Carender, W. J., Hoppes, C. W., Cass, S. P., Christy, J. B., Cohen, H. S., Fife, T. D., et al. (2022) · PubMed Central · doi:10.1097/npt.0000000000000382 · Cited by 118 · see citing works
Cawthorne, T. (1946) · Proceedings of the Royal Society of Medicine · doi:10.1177/003591574603900522 · Cited by 107 · see citing works
Carlà, M. M., Gambini, G., Baldascino, A., Giannuzzi, F., Boselli, F., Crincoli, E., D’Onofrio, N. C., & Rizzo, S. (2024) · British Journal of Ophthalmology · doi:10.1136/bjo-2023-325143 · Cited by 97 · see citing works
Vestibular rehabilitation in Europe: a survey of clinical and research practice
Meldrum, D., Burrows, L., Čakrt, O., Kerkeni, H., Christophe Lopez, A., Tjernstrom, F., Vereeck, L., Zur, O., & Jahn, K. (2020) · Journal of Neurology · doi:10.1007/s00415-020-10228-4 · Cited by 75 · see citing works
Evaluating the performance of ChatGPT in medical physiology university examination of phase I MBBS
Mahila, S., Jaleel, I., & Surapaneni, K. M. (2023) · AJP Advances in Physiology Education · doi:10.1152/advan.00036.2023 · Cited by 72 · see citing works
Treatment of Benign Paroxysmal Positional Vertigo
Herdman, S. J. (1990) · Physical Therapy · doi:10.1093/ptj/70.6.381 · Cited by 67 · see citing works
Gemini Versus ChatGPT: Applications, Performance, Architecture, Capabilities, and ImplementationPreprint
Rane, N., Choudhary, S., & Rane, J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4723687 · Cited by 42 · see citing works
Shukla, R., Mishra, A. K., Banerjee, N., & Verma, A. (2024) · Cureus · doi:10.7759/cureus.58232 · Cited by 31 · see citing works
Male, A. J., Ramdharry, G. M., Grant, R., Davies, R. A., & Beith, I. D. (2018) · Physiotherapy · doi:10.1016/j.physio.2018.08.007 · Cited by 21 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Saatçi, G., Korkut, S., & Ünsal, A. (2024) · Nurse Education in Practice · doi:10.1016/j.nepr.2024.104186 · Cited by 31 · see citing works
Gürses, Ö. A., Özüdoğru, A., Tuncay, F., & Karartı, C. (2025) · Journal of Medical Systems · doi:10.1007/s10916-025-02207-x · Cited by 28 · see citing works
Birinci, M., Kılıçtaş, A. U., Gül, O., Yemiş, T., Erdivanlı, B., Çeliker, M., Özgür, A., Erdivanlı, Ö. Ç., & Dursun, E. (2026) · Otolaryngology · doi:10.1002/ohn.70192 · Cited by 6 · see citing works
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 · see citing works
AI-Powered Physiotherapy: Evaluating LLMs Against Students in Clinical Rehabilitation Scenarios
Michou, I., Fouras, A., Chrysanthakopoulou, D., Theodoritsi, M., Stellatou, S., Mariettou, S., & Koutsojannis, C. M. (2026) · Applied Sciences · doi:10.3390/app16031165 · Cited by 6 · see citing works
AI vs AI: clinical reasoning performance of language models in orthopedic rehabilitation
Safran, E., & Yaşasın, Y. (2025) · Journal of Health Sciences and Medicine · doi:10.32322/jhsm.1743257 · Cited by 2 · see citing works
Artificial Intelligence Models for Dysphonia Patient Education
Ho, R., Shah, E., Armas, J. S. D., Yan, K. K.-L., & Kaye, R. J. (2025) · Otolaryngology · doi:10.1002/ohn.70030 · Cited by 2 · see citing works
Bai, T., Jiang, K., Yu, Y., Qie, S., Wang, C., Wang, B., & Zhang, W. (2026) · Future Internet · doi:10.3390/fi18020095 · Cited by 2 · see citing works
Wang, S. Q. G., Mou, K., Wang, J., Mo, C., Shen, X., Wang, J., Zuo, W., & Chen, Y. (2026) · BMC Medical Education · doi:10.1186/s12909-026-09223-6 · Cited by 2 · see citing works
Agharia, S., Soroush, S., Ameen, D., & Zhou, Y. (2026) · Archives of Orthopaedic and Trauma Surgery · doi:10.1007/s00402-026-06400-6 · Cited by 2 · see citing works
Generative AI and Large Language Models in Rehabilitation: A Scoping Review
Cha, S. (2026) · Life · doi:10.3390/life16081310 · Cited by 2 · see citing works
HOW AI TOOLS (LIKE CHATGPT/GEMINI) AFFECT CRITICAL THINKING IN NURSING STUDENTS. A SYSTEMATIC REVIEW
Din, A. L. (2026) · Journal of Medical & Health Sciences Review · doi:10.65035/650ytk03 · Cited by 1 · see citing works
Gürses, Ö. A., Özüdoğru, A., Tuncay, F., & Karartı, C. (2025) · Genel Tıp Dergisi · doi:10.54005/geneltip.1634118 · Cited by 1 · see citing works
Evaluating Evidence With AI: ChatGPT's Performance on the PEDro Scale in Physical Therapy Research
Hao, J., Yao, Z., Remis, A., & Yu, X. (2025) · Journal of Evidence-Based Medicine · doi:10.1111/jebm.70074 · Cited by 1 · see citing works
Kleebayoon, A., & Wiwanitkit, V. (2025) · Physical Therapy · doi:10.1093/ptj/pzaf053
Author Response to Kleebayoon and Wiwanitkit
Gimmon, Y., Arbel, Y., & Shmueli, L. (2025) · Physical Therapy · doi:10.1093/ptj/pzaf054
Self-citationHao, J., & Siu, K. (2026) · Health Science Reports · doi:10.1002/hsr2.72748
Almulla, A. A., Alduais, A. M. S., & Almulla, M. O. (2026) · Journal of Disability Research · doi:10.57197/jdr-2026-0937
Cali, A., Yörükoğlu, M. E., Açar, G., & Safran, E. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1935702
Technology-Based Vestibular Education
Kotwal, S., Omron, R., Edlow, J. A., & Bhandari, A. (2026) · Neurologic Clinics · doi:10.1016/j.ncl.2026.07.019
Generative Artificial Intelligence in Rehabilitation: A Systematic Mapping Review
Coraci, D., Regazzo, G., Santilli, G., & Masiero, S. (2026) · Applied Sciences · doi:10.3390/app16199784
LARGE LANGUAGE MODELS FOR GAIT CLASSIFICATION AND TREATMENT RECOMMENDATION IN CEREBRAL PALSY
Çelik, M., Birsel, S. E., Demirci, E., Doğan, O., & İnan, M. (2026) · Gait & Posture · doi:10.1016/j.gaitpost.2026.110677
- Authors
- Arbel, Y., Gimmon, Y., & Shmueli, L.
- Affiliations
- Bar-Ilan University (IL)
- Sheba Medical Center (IL)
- Corresponding author
- Gimmon, Yoav
- Venue
- Physical Therapy
- Publisher
- Oxford University Press (OUP)
- Published
- 2025-02-11
- Volume
- 105
- Issue
- 4
- ISSN
- 0031-9023 (ISSN-L)
- 1538-6724
- PMC
- PMC11994992
- OpenAlex
- W4407362752
- Cited by
- 21
- References
- 28
- Citations by year
- 2026: 12 · 2025: 8 · 2024: 1
- FWCI
- 4.81
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Physical Therapy (publishedVersion, cc-by)
- medRxiv (acceptedVersion)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Innovations in Medical Education
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Keywords
- large language models, ChatGPT, Google Gemini, vestibular rehabilitation, physiotherapists, physiotherapy students, clinical reasoning, clinical knowledge, AI accuracy evaluation, artificial intelligence in education, ChatGPT-3.5
- MeSH terms
- Large Language Models, Generative Artificial Intelligence, Clinical Competence, Educational Measurement, Female, Humans, Language, Male, Vestibular Diseases, Physical Therapists
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
