{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T05:20:16Z","timestamp":1787721616115,"version":"build-2784847793"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Individualized rehabilitation supports safe return to sport, yet clinical workload may limit personalized program design. This study evaluated ChatGPT-4.1-generated programs for five sports injury scenarios using a structured rubric scored by two independent sports physiotherapy experts and examined inter-rater reliability and clinical applicability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Mixed-methods design combining rubric scoring with deductive qualitative content analysis of expert commentary. Five cases covered muscle (hamstring strain), ligament (anterior cruciate ligament [ACL] reconstruction), tendon (rotator cuff tendinopathy), neural (lumbar disc herniation) and bone (clavicle fracture) injuries. Exactly one 6-week tabular program per case was generated with ChatGPT-4.1 from a standardized prompt in a fresh session with memory, cross-chat history and custom instructions disabled. Two sports physiotherapists (&amp;gt;20\u202fyears\u2019 experience) independently rated accuracy, exercise selection, progression and applicability on 1\u20135 scales, blinded to each other\u2019s ratings, the verbatim prompt (including the imposed six-week horizon), model identity and study aims, while retaining the clinical scenario. ICC[2,1] (two-way random-effects, absolute agreement) with 95% CIs was computed across the 20 case \u00d7 criterion units; exact and within-one-point agreement, weighted\n                      <jats:italic>\u03ba<\/jats:italic>\n                      and Bland\u2013Altman limits were supplementary.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The overall mean of 40 ratings was 3.85\u202f\u00b1\u202f1.21 (95% CI 3.48\u20134.22), reported alongside disaggregated case- and criterion-level values. Case 5 (clavicle fracture) scored highest (5.00\u202f\u00b1\u202f0.00), Case 2 (ACL) lowest (1.88\u202f\u00b1\u202f0.83, 95% CI 1.18\u20132.57); exercise selection scored highest (4.20\u202f\u00b1\u202f1.32, 95% CI 3.26\u20135.14), clinical applicability lowest (3.60\u202f\u00b1\u202f1.26, 95% CI 2.70\u20134.50). Inter-rater reliability was good (ICC[2,1]\u202f=\u202f0.84, 95% CI 0.52\u20130.94;\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.001); exact agreement 65%, within-one-point agreement 95%, weighted\n                      <jats:italic>\u03ba<\/jats:italic>\n                      \u202f=\u202f0.69. Experts praised structural organization and progression logic but noted weakness in multifactorial, postoperative-timing-sensitive cases.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ChatGPT-4.1 generates plausible, structured programs for linear, protocol-based recovery (e.g., post-fracture), but performance declines markedly in complex, postoperative-staging-sensitive cases; it should serve as a clinician-supervised support tool, not an autonomous decision-maker. Because the six-week length was fixed across all scenarios, case complexity and prompt\u2013scenario congruence are confounded. Findings rest on five programs from one prompting strategy and model, requiring confirmation in larger multi-prompt, multi-model studies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1935702","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T04:42:43Z","timestamp":1787719363000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ChatGPT-generated rehabilitation programs in sports physiotherapy: an expert evaluation and a mixed-methods study of clinical applicability"],"prefix":"10.3389","volume":"13","author":[{"given":"Adem","family":"Cali","sequence":"first","affiliation":[{"name":"Faculty of Health Sciences, Department of Occupational Therapy and Rehabilitation, Istanbul Topkapi University","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehmet Erdem","family":"Yorukoglu","sequence":"additional","affiliation":[{"name":"Dr. Savas Kudas Clinic","place":["Ankara, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gorkem","family":"Acar","sequence":"additional","affiliation":[{"name":"Faculty of Sports Sciences, Istanbul Geli\u015fim University","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ertugrul","family":"Safran","sequence":"additional","affiliation":[{"name":"Department of Physical Therapy and Rehabilitation, Faculty of Health Sciences, Istanbul Geli\u015fim University","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e000713","DOI":"10.1136\/bmjsem-2019-000713","article-title":"Clinical reasoning framework for thoracic spine exercise prescription in sport: a systematic review and narrative synthesis","volume":"6","author":"Heneghan","year":"2020","journal-title":"BMJ Open Sport Exerc Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"102693","DOI":"10.1016\/j.artmed.2023.102693","article-title":"Artificial intelligence in physical rehabilitation: a systematic review","volume":"146","author":"Sumner","year":"2023","journal-title":"Artif Intell Med"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"e20736","DOI":"10.1016\/j.heliyon.2023.e20736","article-title":"Barriers and facilitators of integrating physiotherapy into primary health care settings: a systematic scoping review of qualitative research","volume":"9","author":"ShahAli","year":"2023","journal-title":"Heliyon"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"951","DOI":"10.3390\/jpm13060951","article-title":"A review of the role of artificial intelligence in healthcare","volume":"13","author":"Al Kuwaiti","year":"2023","journal-title":"J Pers Med"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1186\/s12909-023-04698-z","article-title":"Revolutionizing healthcare: the role of artificial intelligence in clinical practice","volume":"23","author":"Alowais","year":"2023","journal-title":"BMC Med Educ"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine learning in medicine","volume":"380","author":"Rajkomar","year":"2019","journal-title":"N Engl J Med"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1618510","DOI":"10.3389\/fdgth.2025.1618510","article-title":"Evaluating the role of ChatGPT in rehabilitation medicine: a narrative review","volume":"7","author":"Luo","year":"2025","journal-title":"Front Digital Health"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1186\/s12891-025-08650-8","article-title":"A cross-sectional study on ChatGPT's alignment with clinical practice guidelines in musculoskeletal rehabilitation","volume":"26","author":"Safran","year":"2025","journal-title":"BMC Musculoskelet Disord"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1186\/s13102-025-01409-7","article-title":"Comparative evaluation of ChatGPT versions in training program design: scientific approach, accuracy, and practical applicability","volume":"18","author":"Gen\u00e7","year":"2025","journal-title":"BMC Sports Sci Med Rehabil"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"209","DOI":"10.5114\/biolsport.2024.132987","article-title":"Artificial intelligence in sport: exploring the potential of using ChatGPT in resistance training prescription","volume":"41","author":"Washif","year":"2024","journal-title":"Biol Sport"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"101210","DOI":"10.1016\/j.asmr.2025.101210","article-title":"ChatGPT-generated responses across Orthopaedic sports medicine surgery vary in accuracy, quality, and readability: a systematic review","volume":"7","author":"Kodra","year":"2025","journal-title":"Arthrosc Sports Med Rehabil"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e59309","DOI":"10.2196\/59309","article-title":"Using large language models to enhance exercise recommendations and physical activity in clinical and healthy populations: scoping review","volume":"13","author":"Lai","year":"2025","journal-title":"JMIR Med Inform"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1606088","DOI":"10.3389\/fdgth.2025.1606088","article-title":"Artificial intelligence in personalized rehabilitation: current applications and a SWOT analysis","volume":"7","author":"Attoh-Mensah","year":"2025","journal-title":"Front Digital Health"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1364660","DOI":"10.3389\/fpubh.2024.1364660","article-title":"Large language models in physical therapy: time to adapt and adept","volume":"12","author":"Naqvi","year":"2024","journal-title":"Front Public Health"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1186\/s12909-025-08535-3","article-title":"Physiotherapy students' acceptance of AI-based chatbots (including ChatGPT) in education: a multi-institutional study from Turkey","volume":"26","author":"G\u00fcler","year":"2026","journal-title":"BMC Med Educ"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e70177","DOI":"10.1002\/msc.70177","article-title":"Artificial intelligence in physical therapy education: evaluating clinical reasoning performance in musculoskeletal care using ChatGPT","volume":"23","author":"Hao","year":"2025","journal-title":"Musculoskeletal Care"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1186\/s12911-025-03202-5","article-title":"Can large language models follow guidelines? A comparative study of ChatGPT-4o and DeepSeek AI in clavicle fracture management based on AAOS recommendations","volume":"25","author":"Ke\u00e7eci","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"415","DOI":"10.5152\/j.aott.2025.25428","article-title":"Comparative evaluation of large language model-based chatbots in a septic arthritis scenario: ChatGPT, Claude, and perplexity","volume":"59","author":"Bayrak","year":"2025","journal-title":"Acta Orthop Traumatol Turc"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"33","DOI":"10.3390\/japma116030033","article-title":"Comparison of ChatGPT-5 and DeepSeek V3 for artificial intelligence-assisted patient education in foot and ankle disorders","volume":"116","author":"Karag\u00f6z","year":"2026","journal-title":"J Am Podiatr Med Assoc"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1111\/j.1365-2648.2007.04569.x","article-title":"The qualitative content analysis process","volume":"62","author":"Elo","year":"2008","journal-title":"J Adv Nurs"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1136\/bjsports-2012-091448","article-title":"Terminology and classification of muscle injuries in sport: the Munich consensus statement","volume":"47","author":"Mueller-Wohlfahrt","year":"2013","journal-title":"Br J Sports Med"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1136\/bjsports-2013-093302","article-title":"British athletics muscle injury classification: a new grading system","volume":"48","author":"Pollock","year":"2014","journal-title":"Br J Sports Med"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"CPG1\u2013CPG44","DOI":"10.2519\/jospt.2022.0301","article-title":"Hamstring strain injury in athletes","volume":"52","author":"Martin","year":"2022","journal-title":"J Orthop Sports Phys Ther"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.asmart.2026.05.006","article-title":"APKASS 2024 consensus statement on anterior cruciate ligament reconstruction, part III: return to play after anterior cruciate ligament reconstruction","volume":"45","author":"Liang","year":"2026","journal-title":"Asia Pac J Sports Med Arthrosc Rehabil Technol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"235","DOI":"10.2519\/jospt.2025.13182","article-title":"Rotator cuff tendinopathy diagnosis, nonsurgical medical care, and rehabilitation: a clinical practice guideline","volume":"55","author":"Desmeules","year":"2025","journal-title":"J Orthop Sports Phys Ther"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1531637","DOI":"10.3389\/fmed.2025.1531637","article-title":"Clinical efficacy of exercise therapy for lumbar disc herniation: a systematic review and meta-analysis of randomized controlled trials","volume":"12","author":"Du","year":"2025","journal-title":"Front Med"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/j.xrrt.2024.11.002","article-title":"Return to play following clavicular fracture - a systematic review and meta analysis","volume":"5","author":"Kilkenny","year":"2024","journal-title":"JSES Rev Rep Tech"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A guideline of selecting and reporting Intraclass correlation coefficients for reliability research","volume":"15","author":"Koo","year":"2016","journal-title":"J Chiropr Med"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"39426","DOI":"10.1038\/s41598-025-22940-0","article-title":"Limitations of large language models in clinical problem-solving arising from inflexible reasoning","volume":"15","author":"Kim","year":"2025","journal-title":"Sci Rep"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"13387","DOI":"10.18653\/v1\/2023.findings-acl.847","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Perez","year":"2023"},{"key":"ref31","article-title":"Towards understanding sycophancy in language models. In the twelfth international conference on learning representations (ICLR 2024)","author":"Sharma","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1038\/s43856-025-01021-3","article-title":"Multi-model assurance analysis showing large language models are highly vulnerable to adversarial hallucination attacks during clinical decision support","volume":"5","author":"Omar","year":"2025","journal-title":"Commun Med"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"pzaf010","DOI":"10.1093\/ptj\/pzaf010","article-title":"Evaluating the potential of large language models for vestibular rehabilitation education: a comparison of chatgpt, google gemini, and clinicians","volume":"105","author":"Arbel","year":"2025","journal-title":"Phys Ther"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1016\/j.arthro.2024.08.036","article-title":"ChatGPT Can offer at least satisfactory responses to common patient questions regarding hip arthroscopy","volume":"41","author":"\u00d6zbek","year":"2025","journal-title":"Arthroscopy"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1038\/s41746-026-02428-5","article-title":"Large language models provide unsafe answers to patient-posed medical questions","volume":"9","author":"Draelos","year":"2026","journal-title":"NPJ Digit Med"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"e848","DOI":"10.1016\/S2589-7500(24)00143-2","article-title":"Generative artificial intelligence and ethical considerations in health care: a scoping review and ethics checklist","volume":"6","author":"Ning","year":"2024","journal-title":"Lancet Digit Health"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1518049","DOI":"10.3389\/frai.2025.1518049","article-title":"Benefits, limits, and risks of ChatGPT in medicine","volume":"8","author":"Tangsrivimol","year":"2025","journal-title":"Frontiers in artificial intelligence"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1935702\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T04:42:52Z","timestamp":1787719372000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1935702\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":37,"alternative-id":["10.3389\/fmed.2026.1935702"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1935702","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"article-number":"1935702"}}