{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:52:15Z","timestamp":1781639535205,"version":"3.54.5"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005296","name":"Universit\u00e4tsklinikum Regensburg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005296","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>Introduction\/background<\/jats:title>\n                    <jats:p>Spinal cord injuries (SCI) present complex challenges for patients, who increasingly turn to online resources for supplementary information. Large language models (LLMs) like ChatGPT and Google Gemini have emerged as potential tools for patient education. However, concerns about the accuracy, clarity, and comprehensiveness of their responses remain, particularly in specialized fields such as SCI. This study aimed to evaluate the performance of ChatGPT 4, ChatGPT 3.5, and Google Gemini in addressing common patient questions about SCI.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Material and methods<\/jats:title>\n                    <jats:p>A systematic process was used to identify 10 key patient questions related to SCI from online sources, PubMed, and Google Trends. These questions were submitted to ChatGPT 4, ChatGPT 3.5, and Google Gemini using a standardized prompt and a 150-word response cap to elicit expert-like responses. Eight blinded spine surgeons evaluated the chatbot-generated answers for quality, clarity, empathy, and comprehensiveness using a validated rating system. Responses were categorized as \u201cexcellent,\u201d \u201csatisfactory with minimal clarification,\u201d \u201csatisfactory with moderate clarification,\u201d or \u201cunsatisfactory.\u201d<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Across all three models, the majority of responses were rated as either excellent or requiring only minimal clarification. ChatGPT 4 achieved the highest proportion of high-quality responses, with up to almost 90% rated as \u201cexcellent\u201d or \u201cminimal clarification required.\u201d ChatGPT 3.5 and Google Gemini performed similarly, with slightly lower percentages of high-quality responses. No statistically significant differences were observed between the models in overall performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>In a standardized single turn, 150-word setting, publicly available LLMs produced largely satisfactory answers to common SCI questions with comparable performance across models. LLMs can be recommended as adjuncts for general patient education, while their outputs should be reviewed within clinical care. Further studies should test multi turn interactions, include patient and multidisciplinary evaluators, compare chatbot responses with clinician authored answers and evaluate the performance of domain specific medical LLMs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of evidence<\/jats:title>\n                    <jats:p>II.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00586-026-09763-x","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T04:54:05Z","timestamp":1772168045000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Application and efficacy of artificial intelligence in patient education on spinal cord injuries"],"prefix":"10.1007","author":[{"given":"Jonas","family":"Krueckel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melanie","family":"Ardelt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Schiffelholz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josina","family":"Straub","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Siller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vanessa","family":"Hubertus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sonja","family":"H\u00e4ckel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denis","family":"Bratelj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christof","family":"Wutte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helena","family":"Arias","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franz","family":"Hilber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Volker","family":"Alt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siegmund","family":"Lang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,27]]},"reference":[{"issue":"10","key":"9763_CR1","doi-asserted-by":"publisher","first-page":"1371","DOI":"10.1089\/neu.2004.21.1371","volume":"21","author":"KD Anderson","year":"2004","unstructured":"Anderson KD (2004) Targeting recovery: priorities of the spinal Cord-Injured population. J Neurotrauma Oktober 21(10):1371\u20131383","journal-title":"J Neurotrauma Oktober"},{"key":"9763_CR2","doi-asserted-by":"crossref","unstructured":"Manns PJ, Chad KE (2001) Components of quality of life for persons with a Quadriplegic and Paraplegic Spinal Cord Injury","DOI":"10.1177\/104973201129119541"},{"issue":"3","key":"9763_CR3","first-page":"271","volume":"13","author":"M Tyrrell Burrus","year":"2017","unstructured":"Tyrrell Burrus M, Werner BC, Starman JS, Kurkis GM, Pierre JM, Diduch DR (2017) u. a. Patient perceptions and current trends in internet use by orthopedic outpatients. HSS Journal\u00ae Musculoskelet J Hosp Spec Surg Oktober 13(3):271\u2013275","journal-title":"HSS Journal\u00ae Musculoskelet J Hosp Spec Surg Oktober"},{"key":"9763_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.resuscitation.2023.109729","volume":"185","author":"C Ahn","year":"2023","unstructured":"Ahn C (2023) Exploring chatgpt for information of cardiopulmonary resuscitation. Resuscitation 185:109729","journal-title":"Resuscitation"},{"issue":"9","key":"9763_CR5","doi-asserted-by":"publisher","first-page":"2289","DOI":"10.1016\/j.arth.2024.03.017","volume":"39","author":"SS Bains","year":"2024","unstructured":"Bains SS, Dubin JA, Hameed D, Sax OC, Douglas S, Mont MA (2024) u. a. Use and application of large Language models for patient questions following total knee arthroplasty. J Arthroplasty September 39(9):2289\u20132294","journal-title":"J Arthroplasty September"},{"key":"9763_CR6","doi-asserted-by":"publisher","first-page":"102804","DOI":"10.1016\/j.bas.2024.102804","volume":"4","author":"S Lang","year":"2024","unstructured":"Lang S, Vitale J, Fekete TF, Haschtmann D, Reitmeir R, Ropelato M (2024) u. a. Are large Language models valid tools for patient information on lumbar disc herniation? The spine surgeons\u2019 perspective. Brain Spine 4:102804","journal-title":"Brain Spine"},{"issue":"2","key":"9763_CR7","doi-asserted-by":"publisher","first-page":"633","DOI":"10.14245\/ns.2448098.049","volume":"21","author":"SP Lang","year":"2024","unstructured":"Lang SP, Yoseph ET, Gonzalez-Suarez AD, Kim R, Fatemi P, Wagner K (2024) u. a. Analyzing large Language models\u2019 responses to common lumbar spine fusion surgery questions: A comparison between ChatGPT and bard. Neurospine 30 Juni 21(2):633\u2013641","journal-title":"Neurospine 30 Juni"},{"key":"9763_CR8","doi-asserted-by":"publisher","first-page":"e48568","DOI":"10.2196\/48568","volume":"25","author":"J Liu","year":"2023","unstructured":"Liu J, Wang C, Liu S (2023) Utility of ChatGPT in clinical practice. J Med Internet Res 28 Juni 25:e48568","journal-title":"J Med Internet Res 28 Juni"},{"issue":"2","key":"9763_CR9","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.arthro.2024.07.040","volume":"41","author":"BU Nwachukwu","year":"2025","unstructured":"Nwachukwu BU, Varady NH, Allen AA, Dines JS, Altchek DW, Williams RJ (2025) u. a. Currently available large Language models do not provide musculoskeletal treatment recommendations that are concordant with Evidence-Based clinical practice guidelines. Arthrosc J Arthrosc Relat Surg Februar 41(2):263\u2013275e6","journal-title":"Arthrosc J Arthrosc Relat Surg Februar"},{"key":"9763_CR10","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 (2023) u. a. Reliability of medical information provided by chatgpt: assessment against clinical guidelines and patient information quality instrument. J Med Internet Res 30 Juni 25:e47479","journal-title":"J Med Internet Res 30 Juni"},{"issue":"11","key":"9763_CR11","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1136\/bmjqs-2023-016690","volume":"33","author":"MD Howell","year":"2024","unstructured":"Howell MD (2024) Generative artificial intelligence, patient safety and healthcare quality: a review. BMJ Qual Saf 33(11):748\u201354","journal-title":"BMJ Qual Saf"},{"issue":"4","key":"9763_CR12","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1007\/s10880-022-09844-1","volume":"29","author":"Y Wang","year":"2022","unstructured":"Wang Y, Wu Q, Wang Y, Wang P (2022) The effects of physicians\u2019 communication and empathy ability on Physician\u2013Patient relationship from physicians\u2019 and patients\u2019 perspectives. J Clin Psychol Med Settings Dezember 29(4):849\u2013860","journal-title":"J Clin Psychol Med Settings Dezember"},{"issue":"1","key":"9763_CR13","doi-asserted-by":"publisher","first-page":"e9","DOI":"10.2196\/jmir.5729","volume":"19","author":"SSL Tan","year":"2017","unstructured":"Tan SSL, Goonawardene N (2017) Internet health information seeking and the Patient-Physician relationship: A systematic review. J Med Internet Res 19 Januar 19(1):e9","journal-title":"J Med Internet Res 19 Januar"},{"issue":"4","key":"9763_CR14","first-page":"323","volume":"50","author":"DH Thom","year":"2001","unstructured":"Thom DH, Stanford Trust Study Physicians (2001) Physician behaviors that predict patient trust. J Fam Pract 50(4):323\u20138","journal-title":"J Fam Pract"},{"issue":"19","key":"9763_CR15","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.2106\/JBJS.23.00209","volume":"105","author":"AP Mika","year":"2023","unstructured":"Mika AP, Martin JR, Engstrom SM, Polkowski GG, Wilson JM (2023) Assessing ChatGPT responses to common patient questions regarding total hip arthroplasty. J Bone Jt Surg 4 Oktober 105(19):1519\u20131526","journal-title":"J Bone Jt Surg 4 Oktober"},{"issue":"1","key":"9763_CR16","doi-asserted-by":"publisher","first-page":"e70138","DOI":"10.1002\/jeo2.70138","volume":"12","author":"E Artioli","year":"2025","unstructured":"Artioli E, Veronesi F, Mazzotti A, Brogini S, Zielli SO, Giavaresi G (2025) u. a. Assessing ChatGPT responses to common patient questions regarding total ankle arthroplasty. J Exp Orthop Januar 12(1):e70138","journal-title":"J Exp Orthop Januar"},{"issue":"12","key":"9763_CR17","doi-asserted-by":"publisher","first-page":"1989","DOI":"10.5664\/jcsm.10728","volume":"19","author":"DJ Campbell","year":"2023","unstructured":"Campbell DJ, Estephan LE, Mastrolonardo EV, Amin DR, Huntley CT, Boon MS (2023) Evaluating ChatGPT responses on obstructive sleep apnea for patient education. J Clin Sleep Med Dezember 19(12):1989\u20131995","journal-title":"J Clin Sleep Med Dezember"},{"key":"9763_CR18","doi-asserted-by":"publisher","first-page":"e55939","DOI":"10.2196\/55939","volume":"26","author":"D Gibson","year":"2024","unstructured":"Gibson D, Jackson S, Shanmugasundaram R, Seth I, Siu A, Ahmadi N (2024) u. a. Evaluating the efficacy of ChatGPT as a patient education tool in prostate cancer: multimetric assessment. J Med Internet Res 14 August 26:e55939","journal-title":"J Med Internet Res 14 August"},{"issue":"6","key":"9763_CR19","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 (2023) u. a. Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum. JAMA Intern Med 1 Juni 183(6):589","journal-title":"JAMA Intern Med 1 Juni"},{"issue":"11","key":"9763_CR20","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 (2024) u. a. Large Language models: are artificial intelligence-based chatbots a reliable source of patient information for spinal surgery? Eur Spine J November 33(11):4135\u20134143","journal-title":"Eur Spine J November"},{"key":"9763_CR21","first-page":"e54345","volume":"12","author":"F Aljamaan","year":"2024","unstructured":"Aljamaan F, Temsah MH, Altamimi I, Al-Eyadhy A, Jamal A, Alhasan K (2024) u. a. Reference hallucination score for medical artificial intelligence chatbots: development and usability study. JMIR Med Inf 31 Juli 12:e54345","journal-title":"JMIR Med Inf 31 Juli"},{"issue":"12","key":"9763_CR22","doi-asserted-by":"publisher","first-page":"462","DOI":"10.3390\/fi16120462","volume":"16","author":"P Zhang","year":"2024","unstructured":"Zhang P, Shi J, Kamel Boulos MN (2024) Generative AI in medicine and healthcare: moving beyond the \u2018Peak of inflated expectations\u2019. Future Internet 9 Dezember 16(12):462","journal-title":"Future Internet 9 Dezember"},{"key":"9763_CR23","doi-asserted-by":"publisher","first-page":"e60501","DOI":"10.2196\/60501","volume":"26","author":"J Zaghir","year":"2024","unstructured":"Zaghir J, Naguib M, Bjelogrlic M, N\u00e9v\u00e9ol A, Tannier X, Lovis C (2024) Prompt engineering paradigms for medical applications: scoping review. J Med Internet Res 10 September 26:e60501","journal-title":"J Med Internet Res 10 September"},{"issue":"3","key":"9763_CR24","doi-asserted-by":"publisher","first-page":"198","DOI":"10.3390\/ime2030019","volume":"2","author":"T Heston","year":"2023","unstructured":"Heston T, Khun C (2023) Prompt engineering in medical education. Int Med Educ 31 August 2(3):198\u2013205","journal-title":"Int Med Educ 31 August"},{"issue":"1","key":"9763_CR25","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1038\/s41597-023-02433-3","volume":"10","author":"S Ott","year":"2023","unstructured":"Ott S, Hebenstreit K, Li\u00e9vin V, Hother CE, Moradi M, Mayrhauser M (2023) u. a. ThoughtSource: A central hub for large Language model reasoning data. Sci Data 8 August 10(1):528","journal-title":"Sci Data 8 August"}],"container-title":["European Spine Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00586-026-09763-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00586-026-09763-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00586-026-09763-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T18:58:50Z","timestamp":1781636330000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00586-026-09763-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,27]]},"references-count":25,"alternative-id":["9763"],"URL":"https:\/\/doi.org\/10.1007\/s00586-026-09763-x","relation":{},"ISSN":["0940-6719","1432-0932"],"issn-type":[{"value":"0940-6719","type":"print"},{"value":"1432-0932","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,27]]},"assertion":[{"value":"4 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 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":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}