{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:10Z","timestamp":1785545050743,"version":"3.56.0"},"reference-count":49,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Patients increasingly use large language models (LLMs) to obtain medical information, but the quality of LLM-generated information on complex spinal infections such as spondylodiscitis remains uncertain. Existing evaluations in spine surgery have mainly addressed degenerative conditions or surgical procedures, and disease-specific data for spondylodiscitis are limited.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This preliminary study evaluated spine surgeons\u2019 ratings of single-turn LLM responses to 10 author-curated frequently asked questions (FAQs) about spondylodiscitis and compared answer sets generated from GPT-4, GPT-4o, and Google Gemini web interfaces under the authors\u2019 implemented prompting conditions.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A pool of patient-oriented questions was generated through a chronological workflow including publicly available FAQ sources, PubMed-informed terminology review, Google Trends topic checking, and LLM-generated candidate questions. Duplicate and semantically overlapping questions were removed, the remaining questions were grouped into thematic categories, and 10 final FAQ-style prompts were synthesized. Each prompt was submitted once to the publicly accessible web interfaces of GPT-4, GPT-4o, and Google Gemini. The study was interpreted as an expert evaluation of the resulting answer sets. Seven blinded board-certified spine surgeons rated the responses using a 4-level rating system ranging from excellent to unsatisfactory and additionally assessed comprehensiveness, clarity, empathy, and appropriateness of length. Descriptive statistics and nonparametric comparisons were performed. Interrater reliability was assessed using the intraclass correlation coefficient.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Across all responses, 38.6% (81\/210) were rated as excellent, 39% (82\/210) as satisfactory with minimal clarification needed, 16.7% (35\/210) as satisfactory with moderate clarification needed, and 5.7% (12\/210) as unsatisfactory. The most common reason for necessary clarification was insufficient information (58\/141, 41.1%), followed by language-related issues (21\/141, 14.9%) and overly detailed responses (18\/141, 12.8%). The complication-related question received the highest mean rating (3.4\/5), whereas treatment- and prognosis-related questions received lower ratings (2.7\/5 and 2.9\/5). Median overall ratings did not differ significantly among the 3 evaluated LLMs. Spine surgeons reported a generally positive attitude toward artificial intelligence\u2013supported patient information but expressed remaining uncertainty regarding reliability and direct patient-physician communication.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n In this preliminary expert evaluation, selected publicly accessible LLM web interfaces generated mostly satisfactory responses to author-curated spondylodiscitis FAQs. The findings reflect outputs produced at the time of access under the authors\u2019 implemented prompting conditions. LLMs may support patient education only with clinician oversight. Future research should explore advanced, domain-specific models to further improve the quality of communication between clinicians and patients.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/90364","type":"journal-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T05:11:35Z","timestamp":1784265095000},"page":"e90364-e90364","source":"Crossref","is-referenced-by-count":0,"title":["Publicly Accessible Large Language Model Responses to Frequently Asked Questions About Spondylodiscitis: Preliminary Expert Evaluation"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5050-0316","authenticated-orcid":false,"given":"Melanie","family":"Ardelt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4271-8980","authenticated-orcid":false,"given":"David","family":"Schiffelholz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0459-9092","authenticated-orcid":false,"given":"Siegmund","family":"Lang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9592-4208","authenticated-orcid":false,"given":"Josina","family":"Straub","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9415-6633","authenticated-orcid":false,"given":"Sonja","family":"H\u00e4ckel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1928-5686","authenticated-orcid":false,"given":"Nicolas","family":"von der Hoeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Dreimann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4060-4748","authenticated-orcid":false,"given":"Jonathan","family":"Neuhoff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5236-4397","authenticated-orcid":false,"given":"Sebastian","family":"Siller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2608-0662","authenticated-orcid":false,"given":"Denis","family":"Bratelj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0208-4650","authenticated-orcid":false,"given":"Volker","family":"Alt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3212-4580","authenticated-orcid":false,"given":"Dietmar","family":"Dammerer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3057-2600","authenticated-orcid":false,"given":"Jonas","family":"Krueckel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.1093\/jac\/dkq303","article-title":"Spondylodiscitis: update on diagnosis and management","volume":"65 Suppl 3","author":"Gouliouris","journal-title":"J Antimicrob Chemother"},{"issue":"10","key":"R2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm12103373","article-title":"The epidemiology of spondylodiscitis in Germany: a descriptive report of incidence rates, pathogens, in-hospital mortality, and hospital stays between 2010 and 2020","volume":"12","author":"Lang","journal-title":"J Clin Med"},{"issue":"2","key":"R3","doi-asserted-by":"publisher","first-page":"E102","DOI":"10.1097\/BSD.0000000000000597","article-title":"The epidemiology of vertebral osteomyelitis in the United States from 1998 to 2013","volume":"31","author":"Issa","journal-title":"Clin Spine Surg"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-47341-z","article-title":"Epidemiological trends of pyogenic spondylodiscitis in Germany: an EANS Spine Section Study","volume":"13","author":"Kramer","journal-title":"Sci Rep"},{"key":"R5","doi-asserted-by":"publisher","DOI":"10.3389\/fsurg.2024.1357318","article-title":"Midterm survival and risk factor analysis in patients with pyogenic vertebral osteomyelitis: a retrospective study of 155 cases","volume":"11","author":"Schindler","journal-title":"Front Surg"},{"issue":"7","key":"R6","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.89001","article-title":"Global insights into spondylodiscitis: a bibliometric analysis of four decades of research","volume":"17","author":"Gerstmeyer","journal-title":"Cureus"},{"issue":"10","key":"R7","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1530\/EOR-2025-0041","article-title":"Progress in diagnosis and treatment of primary spondylodiscitis: a systematic literature review","volume":"10","author":"Yu","journal-title":"EFORT Open Rev"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.5729","article-title":"Internet health information seeking and the patient-physician relationship: a systematic review","volume":"19","author":"Tan","journal-title":"J Med Internet Res"},{"issue":"9","key":"R9","doi-asserted-by":"publisher","first-page":"1884","DOI":"10.1007\/s11606-019-05109-0","article-title":"Can patients trust online health information? A meta-narrative systematic review addressing the quality of health information on the internet","volume":"34","author":"Daraz","journal-title":"J Gen Intern Med"},{"issue":"6","key":"R10","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.7579","article-title":"Trust and credibility in web-based health information: a review and agenda for future research","volume":"19","author":"Sbaffi","journal-title":"J Med Internet Res"},{"issue":"3","key":"R11","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/s11420-017-9568-2","article-title":"Patient perceptions and current trends in internet use by orthopedic outpatients","volume":"13","author":"Burrus","journal-title":"HSS J"},{"issue":"13","key":"R12","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","article-title":"Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine","volume":"388","author":"Lee","journal-title":"N Engl J Med"},{"issue":"6","key":"R13","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11060887","article-title":"ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns","volume":"11","author":"Sallam","journal-title":"Healthcare (Basel)"},{"issue":"11","key":"R14","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1136\/bmjqs-2023-016690","article-title":"Generative artificial intelligence, patient safety and healthcare quality: a review","volume":"33","author":"Howell","journal-title":"BMJ Qual Saf"},{"issue":"2","key":"R15","doi-asserted-by":"publisher","first-page":"633","DOI":"10.14245\/ns.2448098.049","article-title":"Analyzing large language models\u2019 responses to common lumbar spine fusion surgery questions: a comparison between ChatGPT and Bard","volume":"21","author":"Lang","journal-title":"Neurospine"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.1016\/j.bas.2024.102804","article-title":"Are large language models valid tools for patient information on lumbar disc herniation? The spine surgeons\u2019 perspective","volume":"4","author":"Lang","journal-title":"Brain Spine"},{"issue":"9","key":"R17","doi-asserted-by":"publisher","first-page":"2289","DOI":"10.1016\/j.arth.2024.03.017","article-title":"Use and application of large language models for patient questions following total knee arthroplasty","volume":"39","author":"Bains","journal-title":"J Arthroplasty"},{"key":"R18","unstructured":"Spondylodiscitis. Advanced Orthopaedics & Sports Medicine. URL: https:\/\/www.advancedosm.com\/spondylodiscitis-orthopaedic-sports-medicine-specialist-cypress-houston-tx\/ [Accessed 14-09-2024]"},{"key":"R19","unstructured":"Spondylodiscitis. Inselspital, Bern University Hospital. URL: https:\/\/neurochirurgie.insel.ch\/en\/diseases-specialities\/spinal-disorders\/spondylodiscitis [Accessed 14-09-2024]"},{"key":"R20","unstructured":"Google Trends. URL: https:\/\/trends.google.com\/trends\/ [Accessed 14-09-2024]"},{"key":"R21","unstructured":"ChatGPT. URL: https:\/\/chat.openai.com [Accessed 14-09-2024]"},{"key":"R22","unstructured":"Gemini. Google. URL: https:\/\/gemini.google.com\/app [Accessed 14-09-2024]"},{"issue":"19","key":"R23","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.2106\/JBJS.23.00209","article-title":"Assessing ChatGPT responses to common patient questions regarding total hip arthroplasty","volume":"105","author":"Mika","journal-title":"J Bone Joint Surg Am"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-025-02170-7","article-title":"Large language models\u2019 responses to spinal cord injury: a comparative study of performance","volume":"49","author":"Li","journal-title":"J Med Syst"},{"issue":"2","key":"R25","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s43390-024-00955-3","article-title":"Is the information provided by large language models valid in educating patients about adolescent idiopathic scoliosis? An evaluation of content, clarity, and empathy: the perspective of the European Spine Study Group","volume":"13","author":"Lang","journal-title":"Spine Deform"},{"issue":"11","key":"R26","doi-asserted-by":"publisher","first-page":"4135","DOI":"10.1007\/s00586-023-07975-z","article-title":"Large language models: are artificial intelligence-based chatbots a reliable source of patient information for spinal surgery?","volume":"33","author":"Stroop","journal-title":"Eur Spine J"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","DOI":"10.1007\/s10143-025-03785-7","article-title":"Current trends and future prospects of language models and processing systems in spine surgery - a scoping review","volume":"48","author":"Sanker","journal-title":"Neurosurg Rev"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","DOI":"10.1186\/s13018-025-05955-1","article-title":"The role of large language models in improving the readability of orthopaedic spine patient educational material","volume":"20","author":"Romoff","journal-title":"J Orthop Surg Res"},{"issue":"3","key":"R29","doi-asserted-by":"publisher","first-page":"385","DOI":"10.3171\/2024.4.SPINE231148","article-title":"An analysis of ChatGPT recommendations for the diagnosis and treatment of cervical radiculopathy","volume":"41","author":"Hoang","journal-title":"J Neurosurg Spine"},{"issue":"9","key":"R30","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.68521","article-title":"Evaluating the adherence of large language models to surgical guidelines: a comparative analysis of chatbot recommendations and North American Spine Society (NASS) coverage criteria","volume":"16","author":"Sarikonda","journal-title":"Cureus"},{"issue":"24","key":"R31","doi-asserted-by":"publisher","first-page":"7864","DOI":"10.3390\/jcm13247864","article-title":"ChatGPT\u2019s performance in spinal metastasis cases-can we discuss our complex cases with ChatGPT?","volume":"13","author":"Heisinger","journal-title":"J Clin Med"},{"issue":"11","key":"R32","doi-asserted-by":"publisher","first-page":"4182","DOI":"10.1007\/s00586-024-08198-6","article-title":"ChatGPT versus NASS clinical guidelines for degenerative spondylolisthesis: a comparative analysis","volume":"33","author":"Ahmed","journal-title":"Eur Spine J"},{"issue":"1","key":"R33","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02740-8","article-title":"Classification of lumbar spine disorders using large language models and MRI segmentation","volume":"24","author":"Dong","journal-title":"BMC Med Inform Decis Mak"},{"issue":"3","key":"R34","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240885","article-title":"Constructing a large language model to generate impressions from findings in radiology reports","volume":"312","author":"Zhang","journal-title":"Radiology"},{"issue":"3","key":"R35","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1016\/j.spinee.2024.10.021","article-title":"MRI spine request form enhancement and auto protocoling using a secure institutional large language model","volume":"25","author":"Hallinan","journal-title":"Spine J"},{"issue":"7","key":"R36","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15070930","article-title":"Information extraction from lumbar spine MRI radiology reports using GPT4: accuracy and benchmarking against research-grade comprehensive scoring","volume":"15","author":"Ziegeler","journal-title":"Diagnostics (Basel)"},{"issue":"19","key":"R37","doi-asserted-by":"publisher","DOI":"10.3390\/cancers17193198","article-title":"Large language model (LLM)-predicted and LLM-assisted calculation of the Spinal Instability Neoplastic Score (SINS) improves clinician accuracy and efficiency","volume":"17","author":"Chan","journal-title":"Cancers (Basel)"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.1016\/j.bas.2024.102765","article-title":"Can AI pass the written European Board Examination in Neurological Surgery? - Ethical and practical issues","volume":"4","author":"Stengel","journal-title":"Brain Spine"},{"issue":"51-52","key":"R39","doi-asserted-by":"publisher","first-page":"875","DOI":"10.3238\/arztebl.2017.0875","article-title":"Spondylodiscitis: diagnosis and treatment options","volume":"114","author":"Herren","journal-title":"Dtsch Arztebl Int"},{"issue":"10","key":"R40","doi-asserted-by":"publisher","first-page":"181","DOI":"10.3238\/arztebl.2008.0181","article-title":"Current diagnosis and treatment of spondylodiscitis","volume":"105","author":"Sobottke","journal-title":"Dtsch Arztebl Int"},{"issue":"1","key":"R41","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/s10143-017-0829-9","article-title":"Primary acquired spondylodiscitis shows a more severe course than spondylodiscitis following spine surgery: a single-center retrospective study of 159 cases","volume":"41","author":"Tschugg","journal-title":"Neurosurg Rev"},{"issue":"3","key":"R42","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11030660","article-title":"The Hamburg Spondylodiscitis Assessment Score (HSAS) for immediate evaluation of mortality risk on hospital admission","volume":"11","author":"Heuer","journal-title":"J Clin Med"},{"issue":"5","key":"R43","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1177\/21925682221145603","article-title":"An assessment of the safety of surgery and hardware placement in de-novo spinal infections. A systematic review and meta-analysis of the literature","volume":"13","author":"Pluemer","journal-title":"Global Spine J"},{"issue":"6","key":"R44","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1177\/21925682211039498","article-title":"Who needs surgical stabilization for pyogenic spondylodiscitis? Retrospective analysis of non-surgically treated patients","volume":"13","author":"Blecher","journal-title":"Global Spine J"},{"key":"R45","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocn.2024.03.021","article-title":"Evaluation of the safety, accuracy, and helpfulness of the GPT-4.0 large language model in neurosurgery","volume":"123","author":"Huang","journal-title":"J Clin Neurosci"},{"issue":"2","key":"R46","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300068","article-title":"Almanac - retrieval-augmented language models for clinical medicine","volume":"1","author":"Zakka","journal-title":"NEJM AI"},{"issue":"6","key":"R47","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1001\/jamainternmed.2023.1838","article-title":"Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum","volume":"183","author":"Ayers","journal-title":"JAMA Intern Med"},{"issue":"1","key":"R48","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"Topol","journal-title":"Nat Med"},{"key":"R49","doi-asserted-by":"publisher","DOI":"10.1016\/j.wneu.2025.124423","article-title":"Prompt engineering and follow-up questioning improves the readability of spine surgery questions in large language models","volume":"203","author":"Daulat","journal-title":"World Neurosurg"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e90364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:24:26Z","timestamp":1785536666000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e90364"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":49,"URL":"https:\/\/doi.org\/10.2196\/90364","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"article-number":"v28i10e90364"}}