{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T19:33:05Z","timestamp":1787081585979,"version":"build-2736575974"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100008004","name":"Kastamonu University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100008004","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Spine J"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aim\/background<\/jats:title>\n                    <jats:p>Large language models (LLMs) are increasingly used by patients to obtain medical information. Adolescent idiopathic scoliosis (AIS), a chronic condition requiring long-term monitoring and treatment decisions, generates substantial demand for reliable and understandable patient education. Although LLMs may function as accessible explanatory tools, their suitability for patient-oriented use remains uncertain. This study aimed to perform an expert-led, patient-centered evaluation of two widely accessible LLMs, Claude Sonnet 4.5 and GPT 5.2, focusing on their ability to deliver accurate, clear, and conceptually adequate responses to common AIS-related patient questions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A cross-sectional comparative design was used with 100 high-frequency patient questions covering ten clinical domains. Responses generated by both models using standardized zero-shot prompts were independently assessed by expert clinicians: factual accuracy by three raters (two orthopedic spine surgeons and one senior pediatric physiotherapist), and clarity and conceptual coverage by two raters (one surgeon and the physiotherapist). A structured evaluation framework examined three dichotomous dimensions relevant to patient education: factual accuracy, clarity and understandability, and conceptual coverage. Model performances were compared using McNemar\u2019s test, and inter-model agreement was assessed with Krippendorff\u2019s alpha.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Both models demonstrated equally high factual accuracy (91%). However, clarity was limited, with only one-third of responses rated as sufficiently understandable. A significant difference was observed in conceptual coverage, with Claude Sonnet 4.5 outperforming GPT 5.2 (46% vs. 29%,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.012), particularly in domains requiring integrative explanations.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Despite strong factual accuracy, current LLMs show deficiencies in clarity and conceptual depth, limiting their reliability as standalone patient education tools for AIS. These findings highlight the necessity of clinician mediation and the importance of patient-centered evaluation criteria before clinical adoption.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Clinical trial registration<\/jats:title>\n                    <jats:p>As this study is not a clinical trial, clinical trial registration is not applicable.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00586-026-10046-8","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T01:25:55Z","timestamp":1781054755000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An expert-led benchmark using common patient questions: evaluating large language models for adolescent idiopathic scoliosis education"],"prefix":"10.1007","author":[{"given":"Cemre","family":"Aydin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asli Beril","family":"Karakas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anil Murat","family":"Ozturk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Figen","family":"Govsa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehmet Asim","family":"Ozer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"10046_CR1","doi-asserted-by":"publisher","first-page":"15030","DOI":"10.1038\/nrdp.2015.30","volume":"1","author":"JC Cheng","year":"2015","unstructured":"Cheng JC, Castelein RM, Chu WC, Danielsson AJ, Dobbs MB, Grivas TB et al (2015) Adolescent idiopathic scoliosis. Nat Rev Dis Prim 1:15030. https:\/\/doi.org\/10.1038\/nrdp.2015.30","journal-title":"Nat Rev Dis Prim"},{"key":"10046_CR2","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1007\/s00381-020-04608-4","volume":"36","author":"D Addai","year":"2020","unstructured":"Addai D, Zarkos J, Bowey AJ (2020) Current concepts in the diagnosis and management of adolescent idiopathic scoliosis. Childs Nerv Syst 36:1111\u20131119. https:\/\/doi.org\/10.1007\/s00381-020-04608-4","journal-title":"Childs Nerv Syst"},{"key":"10046_CR3","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1186\/s12888-019-2128-1","volume":"19","author":"H Wang","year":"2019","unstructured":"Wang H, Li T, Yuan W, Zhang Z, Wei J, Qiu G et al (2019) Mental health of patients with adolescent idiopathic scoliosis and their parents in China: a cross-sectional survey. BMC Psychiatry 19:147. https:\/\/doi.org\/10.1186\/s12888-019-2128-1","journal-title":"BMC Psychiatry"},{"key":"10046_CR4","doi-asserted-by":"publisher","first-page":"2322","DOI":"10.3390\/healthcare12232322","volume":"12","author":"X Lyu","year":"2024","unstructured":"Lyu X, Li J, Li S (2024) Approaches to Reach Trustworthy Patient Education: A Narrative Review. Healthcare 12:2322. https:\/\/doi.org\/10.3390\/healthcare12232322","journal-title":"Healthcare"},{"key":"10046_CR5","doi-asserted-by":"publisher","first-page":"e47479","DOI":"10.2196\/47479","volume":"25","author":"HL Walker","year":"2023","unstructured":"Walker HL, Ghani S, Kuemmerli C, Nebiker CA, M\u00fcller BP, Raptis DA et al (2023) Reliability of Medical Information Provided by ChatGPT: Assessment Against Clinical Guidelines and Patient Information Quality Instrument. J Med Internet Res 25:e47479. https:\/\/doi.org\/10.2196\/47479","journal-title":"J Med Internet Res"},{"key":"10046_CR6","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1001\/jamainternmed.2023.1838","volume":"183","author":"JW Ayers","year":"2023","unstructured":"Ayers JW, Poliak A, Dredze M, Leas EC, Zhu Z, Kelley JB et al (2023) Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum. JAMA Intern Med 183:589. https:\/\/doi.org\/10.1001\/jamainternmed.2023.1838","journal-title":"JAMA Intern Med"},{"key":"10046_CR7","doi-asserted-by":"publisher","first-page":"4135","DOI":"10.1007\/s00586-023-07975-z","volume":"33","author":"A Stroop","year":"2024","unstructured":"Stroop A, Stroop T, Zawy Alsofy S, Nakamura M, M\u00f6llmann F, Greiner C et al (2024) Large language models: Are artificial intelligence-based chatbots a reliable source of patient information for spinal surgery? Eur Spine J 33:4135\u20134143. https:\/\/doi.org\/10.1007\/s00586-023-07975-z","journal-title":"Eur Spine J"},{"key":"10046_CR8","doi-asserted-by":"publisher","DOI":"10.1101\/2023.01.30.23285067","author":"DM Levine","year":"2023","unstructured":"Levine DM, Tuwani R, Kompa B, Varma A, Finlayson SG, Mehrotra A et al (2023) The Diagnostic and Triage Accuracy of the GPT-3 Artificial Intelligence Model. MedRxiv Prepr Serv Heal Sci. https:\/\/doi.org\/10.1101\/2023.01.30.23285067","journal-title":"MedRxiv Prepr Serv Heal Sci"},{"key":"10046_CR9","doi-asserted-by":"publisher","first-page":"222","DOI":"10.5152\/j.aott.2025.25279","volume":"59","author":"S Ya\u015f","year":"2025","unstructured":"Ya\u015f S, Yapar D, Yapar A, \u00d6zel T, Tokg\u00f6z MA, Baymurat AC et al (2025) Assessing the role of large language models in adolescent idiopathic scoliosis care: a comparison between ChatGPT and Google Gemini. Acta Orthop Traumatol Turc 59:222\u20139. https:\/\/doi.org\/10.5152\/j.aott.2025.25279","journal-title":"Acta Orthop Traumatol Turc"},{"key":"10046_CR10","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s43390-024-00955-3","volume":"13","author":"S Lang","year":"2025","unstructured":"Lang S, Vitale J, Galbusera F, Fekete T, Boissiere L, Charles YP et al (2025) Is the information provided by large language models valid in educating patients about adolescent idiopathic scoliosis? An evaluation of content, clarity, and empathy. Spine Deform 13:361\u2013372. https:\/\/doi.org\/10.1007\/s43390-024-00955-3","journal-title":"Spine Deform"},{"key":"10046_CR11","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1177\/18632521251359098","volume":"19","author":"A Suresh","year":"2025","unstructured":"Suresh A, Siahaan J, Marco RA, Klineberg E, Borden T, Vanodia R et al (2025) Comparing the effectiveness of generative AI technology in commonly asked scoliosis questions. J Child Orthop 19:416\u201321. https:\/\/doi.org\/10.1177\/18632521251359098","journal-title":"J Child Orthop"},{"key":"10046_CR12","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1007\/s00586-025-09166-4","volume":"35","author":"F Negrini","year":"2026","unstructured":"Negrini F, Malfitano C, Ferriero G, Morone G, Negrini A, Zaina F et al (2026) Evaluating ChatGPT-4.0\u2019s accuracy and potential in idiopathic scoliosis conservative treatment: a preliminary study on clarity, validity, and expert perceptions. Eur Spine J 35:422\u201330. https:\/\/doi.org\/10.1007\/s00586-025-09166-4","journal-title":"Eur Spine J"},{"key":"10046_CR13","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13144013","volume":"13","author":"A Fabijan","year":"2024","unstructured":"Fabijan A, Zawadzka-Fabijan A, Fabijan R, Zakrzewski K, Nowos\u0142awska E, Polis B (2024) Assessing the accuracy of artificial intelligence models in scoliosis classification and suggested therapeutic approaches. J Clin Med 13:4013. https:\/\/doi.org\/10.3390\/jcm13144013","journal-title":"J Clin Med"},{"key":"10046_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.wneu.2024.11.114","volume":"194","author":"AK Almekkawi","year":"2025","unstructured":"Almekkawi AK, Caruso JP, Anand S, Hawkins AM, Rauf R, Al-Shaikhli M et al (2025) Comparative analysis of large language models and spine surgeons in surgical decision-making and radiological assessment for spine pathologies. World Neurosurg 194:123531. https:\/\/doi.org\/10.1016\/j.wneu.2024.11.114","journal-title":"World Neurosurg"},{"key":"10046_CR15","doi-asserted-by":"publisher","DOI":"10.1177\/21925682251411225","author":"A Kartal","year":"2025","unstructured":"Kartal A, Manalil NF, Cheng CD, Chung LK, Gebhard H, Greenberg M et al (2025) Evaluating Large Language Models for Decision Support in Minimally Invasive Spine Surgery Triage and Procedural Categories. Glob Spine J. https:\/\/doi.org\/10.1177\/21925682251411225","journal-title":"Glob Spine J"},{"key":"10046_CR16","doi-asserted-by":"publisher","first-page":"992","DOI":"10.1177\/1460458215602939","volume":"22","author":"MA Clarke","year":"2016","unstructured":"Clarke MA, Moore JL, Steege LM, Koopman RJ, Belden JL, Canfield SM et al (2016) Health information needs, sources, and barriers of primary care patients to achieve patient-centered care: a literature review. Health Informatics J 22:992\u20131016. https:\/\/doi.org\/10.1177\/1460458215602939","journal-title":"Health Informatics J"},{"key":"10046_CR17","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare7020078","volume":"7","author":"S Wellburn","year":"2019","unstructured":"Wellburn S, van Schaik P, Bettany-Saltikov J (2019) The information needs of adolescent idiopathic scoliosis patients and their parents in the UK: an online survey. Healthcare 7:78. https:\/\/doi.org\/10.3390\/healthcare7020078","journal-title":"Healthcare"},{"key":"10046_CR18","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s11999-014-4071-2","volume":"473","author":"AEM Eltorai","year":"2015","unstructured":"Eltorai AEM, Sharma P, Wang J, Daniels AH (2015) Most American Academy of Orthopaedic Surgeons\u2019 Online Patient Education Material Exceeds Average Patient Reading Level. Clin Orthop Relat Res 473:1181\u20131186. https:\/\/doi.org\/10.1007\/s11999-014-4071-2","journal-title":"Clin Orthop Relat Res"},{"key":"10046_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jposna.2025.100196","volume":"12","author":"X Bryson","year":"2025","unstructured":"Bryson X, Albarran M, Pham N, Salunga A, Johnson T, Hogue GD et al (2025) Artificial intelligence-based large language models can facilitate patient education. J Pediatr Orthop Soc North Am 12:100196. https:\/\/doi.org\/10.1016\/j.jposna.2025.100196","journal-title":"J Pediatr Orthop Soc North Am"},{"issue":"1","key":"10046_CR20","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1186\/s12913-020-05442-9","volume":"20","author":"C Kersting","year":"2020","unstructured":"Kersting C, Kneer M, Barzel A (2020) Patient-relevant outcomes: what are we talking about? A scoping review to improve conceptual clarity. BMC Health Serv Res 20:596. https:\/\/doi.org\/10.1186\/s12913-020-05442-9","journal-title":"BMC Health Serv Res"},{"key":"10046_CR21","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s10900-004-1959-x","volume":"30","author":"N Cotugna","year":"2005","unstructured":"Cotugna N, Vickery CE, Carpenter-Haefele KM (2005) Evaluation of literacy level of patient education pages in health-related journals. J Community Health 30:213\u2013219. https:\/\/doi.org\/10.1007\/s10900-004-1959-x","journal-title":"J Community Health"},{"key":"10046_CR22","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1007\/s43390-025-01087-y","volume":"13","author":"B Lieu","year":"2025","unstructured":"Lieu B, Crawford E, Laubach L, Yeramosu T, Sharps C, Horstmann J et al (2025) Patient education strategies in pediatric orthopaedics: using ChatGPT to answer frequently asked questions on scoliosis. Spine Deform 13:1377\u201389. https:\/\/doi.org\/10.1007\/s43390-025-01087-y","journal-title":"Spine Deform"},{"key":"10046_CR23","doi-asserted-by":"publisher","DOI":"10.1186\/s12891-025-09315-2","volume":"26","author":"E Giray","year":"2025","unstructured":"Giray E, Korkmaz MD, Illeez OG, Capan N, Karadag Saygi E, Aydin AR (2025) Let\u2019s chat (GPT) about adolescent idiopathic scoliosis: accuracy and reliability of chat responses to frequently asked questions. BMC Musculoskelet Disord 26:1075. https:\/\/doi.org\/10.1186\/s12891-025-09315-2","journal-title":"BMC Musculoskelet Disord"},{"key":"10046_CR24","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1227\/neu.0000000000002551","volume":"93","author":"R Ali","year":"2023","unstructured":"Ali R, Tang OY, Connolly ID, Fridley JS, Shin JH, Zadnik Sullivan PL et al (2023) Performance of ChatGPT, GPT-4, and Google Bard on a Neurosurgery Oral Boards preparation question bank. Neurosurgery 93:1090\u20138. https:\/\/doi.org\/10.1227\/neu.0000000000002551","journal-title":"Neurosurgery"},{"key":"10046_CR25","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1097\/BRS.0000000000003641","volume":"45","author":"CYW Chan","year":"2020","unstructured":"Chan CYW, Chong JSL, Lee SY, Ch\u2019ng PY, Chung WH, Chiu CK et al (2020) Parents\u2019\/patients\u2019 perception of the informed consent process and surgeons accountability in corrective surgery for adolescent idiopathic scoliosis. Spine (Phila Pa 1976) 45:1661\u20137. https:\/\/doi.org\/10.1097\/BRS.0000000000003641","journal-title":"Spine (Phila Pa 1976)"},{"issue":"4","key":"10046_CR26","doi-asserted-by":"publisher","DOI":"10.3390\/children9040563","volume":"9","author":"C de Groot","year":"2022","unstructured":"de Groot C, Heemskerk JL, Willigenburg NW, Altena MC, Kempen DHR (2022) Educating parents improves their ability to recognize adolescent idiopathic scoliosis: a diagnostic accuracy study. Children Basel 9. https:\/\/doi.org\/10.3390\/children9040563","journal-title":"Children Basel"},{"key":"10046_CR27","doi-asserted-by":"publisher","first-page":"2260","DOI":"10.1097\/CORR.0000000000002668","volume":"481","author":"GJ Kirchner","year":"2023","unstructured":"Kirchner GJ, Kim RY, Weddle JB, Bible JE (2023) Can Artificial Intelligence Improve the Readability of Patient Education Materials? Clin Orthop Relat Res 481:2260\u20132267. https:\/\/doi.org\/10.1097\/CORR.0000000000002668","journal-title":"Clin Orthop Relat Res"},{"key":"10046_CR28","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","volume":"31","author":"K Singhal","year":"2025","unstructured":"Singhal K, Tu T, Gottweis J, Sayres R, Wulczyn E, Amin M et al (2025) Toward expert-level medical question answering with large language models. Nat Med 31:943\u201350. https:\/\/doi.org\/10.1038\/s41591-024-03423-7","journal-title":"Nat Med"}],"container-title":["European Spine Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00586-026-10046-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00586-026-10046-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00586-026-10046-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T01:25:58Z","timestamp":1781054758000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00586-026-10046-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":28,"alternative-id":["10046"],"URL":"https:\/\/doi.org\/10.1007\/s00586-026-10046-8","relation":{},"ISSN":["0940-6719","1432-0932"],"issn-type":[{"value":"0940-6719","type":"print"},{"value":"1432-0932","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]},"assertion":[{"value":"5 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study involved the expert evaluation of AI-generated responses to standardized, non-identifiable patient questions and did not include human participants, patient data, or clinical interventions. In accordance with institutional policy, ethical approval was obtained from the relevant Institutional Ethics Committee (approval number: 26-6T\/20). All study procedures were designed in compliance with the ethical principles of the Declaration of Helsinki and its subsequent amendments.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable. The study did not involve direct participation of human subjects, patient interaction, or the use of identifiable personal data.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}