{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T15:56:08Z","timestamp":1790610968586,"version":"4.1.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Cedars-Sinai Medical Center","id":[{"id":"https:\/\/ror.org\/02pammg90","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Spine Deform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Most clinical evaluations of large language models assess factual recall rather than the multi-step reasoning behind operative plans. Reasoning-tuned models, post-trained to generate explicit intermediate reasoning before answering, may better approximate surgical decision-making. We compared two such models from different development ecosystems, OpenAI o1 and DeepSeek R1, on complex spine cases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Ten synthetic vignettes spanning deformity, degenerative, urgent, and cervical pathology were analysed; an eleventh was excluded owing to a survey error. Both models received identical prompts. Outputs were anonymised and randomised. Eight fellowship-trained spine surgeons (five consultants, three fellows) scored diagnostic accuracy, reasoning and thoroughness, surgical plan appropriateness, and clarity on 5-point Likert scales, giving 78 paired evaluations. Analysis used linear mixed-effects models with crossed random intercepts for rater and vignette (Bonferroni-adjusted alpha 0.0125); reliability was assessed by intraclass correlation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>o1 scored higher in all four domains, significantly for diagnostic accuracy (4.6 vs. 4.3; mean difference 0.24, 95% CI 0.11\u20130.38) and clarity (4.4 vs. 4.2; 0.26, 0.07\u20130.44); reasoning and thoroughness (0.21, 0.03\u20130.38), and surgical plan appropriateness (0.17, \u2212\u00a00.03 to 0.36) did not meet the adjusted threshold. Inter-rater reliability was poor (ICC 0.03\u20130.07). Clarity correlated strongly with the clinical domains (rho 0.74\u20130.79); adjusting for clarity attenuated the o1 advantage by 55% to over 100%, leaving no detectable clinical-domain difference.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Both models produced plans surgeons usually rated good or excellent. o1 was rated higher, significantly only for diagnostic accuracy and clarity, most of it reflecting presentation rather than clinical content. Surgeon oversight and format-normalised evaluation designs remain essential.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s43390-026-01557-x","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T15:07:17Z","timestamp":1790608037000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating reasoning-tuned large language models for clinical decision-making in spine surgery"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1970-3038","authenticated-orcid":false,"given":"Chuck H.","family":"Lam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Conor T.","family":"Boylan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adit","family":"Ravishankar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Bulloso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"McKay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David L.","family":"Skaggs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Morgan","family":"Jones","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"issue":"1","key":"1557_CR1","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25(1):44\u201356","journal-title":"Nat Med"},{"issue":"1","key":"1557_CR2","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1097\/SLA.0000000000002693","volume":"268","author":"DA Hashimoto","year":"2018","unstructured":"Hashimoto DA, Rosman G, Rus D, Meireles OR (2018) Artificial intelligence in surgery: promises and perils. Ann Surg 268(1):70\u201376","journal-title":"Ann Surg"},{"key":"1557_CR3","unstructured":"Wei J, Wang X, Schuurmans D, Bosma M, Ichter B, Xia F et al (2025) Chain-of-thought prompting elicits reasoning in large language models. Preprint at https:\/\/arxiv.org\/abs\/2201.11903"},{"issue":"8081","key":"1557_CR4","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","volume":"645","author":"D Guo","year":"2025","unstructured":"Guo D, Yang D, Zhang H, Song J, Wang P, Zhu Q et al (2025) DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645(8081):633\u2013638","journal-title":"Nature"},{"key":"1557_CR5","unstructured":"OpenAI, Jaech A, Kalai A, Lerer A, Richardson A, El-Kishky A et al (2024) OpenAI o1 system card. Preprint at https:\/\/arxiv.org\/abs\/2412.16720"},{"issue":"2","key":"1557_CR6","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1097\/CORR.0000000000001086","volume":"478","author":"C Vu","year":"2020","unstructured":"Vu C, Gendelberg D (2020) Classifications in brief: AO thoracolumbar classification system. Clin Orthop Relat Res 478(2):434\u2013440","journal-title":"Clin Orthop Relat Res"},{"issue":"11","key":"1557_CR7","doi-asserted-by":"publisher","first-page":"1778","DOI":"10.1016\/j.spinee.2022.07.095","volume":"22","author":"KW Morse","year":"2022","unstructured":"Morse KW, Steinhaus M, Bovonratwet P, Kazarian G, Gang CH, Vaishnav AS et al (2022) Current treatment and decision-making factors leading to fusion vs decompression for one-level degenerative spondylolisthesis: survey results from members of the Lumbar Spine Research Society and Society of Minimally Invasive Spine Surgery. Spine J 22(11):1778\u20131787","journal-title":"Spine J"},{"issue":"1","key":"1557_CR8","doi-asserted-by":"publisher","DOI":"10.1186\/s13018-023-04467-0","volume":"19","author":"N Jain","year":"2024","unstructured":"Jain N, Gottlich C, Fisher J, Campano D, Winston T (2024) Assessing ChatGPT\u2019s orthopedic in-service training exam performance and applicability in the field. J Orthop Surg Res 19(1):27","journal-title":"J Orthop Surg Res"},{"issue":"1","key":"1557_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/s00701-024-06372-9","volume":"166","author":"A Patil","year":"2024","unstructured":"Patil A, Serrato P, Chisvo N, Arnaout O, See PA, Huang KT (2024) Large language models in neurosurgery: a systematic review and meta-analysis. Acta Neurochir 166(1):475","journal-title":"Acta Neurochir"},{"issue":"6","key":"1557_CR10","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1227\/neu.0000000000002632","volume":"93","author":"R Ali","year":"2023","unstructured":"Ali R, Tang OY, Connolly ID, Zadnik Sullivan PL, Shin JH, Fridley JS et al (2023) Performance of ChatGPT and GPT-4 on neurosurgery written board examinations. Neurosurgery 93(6):1353\u20131365","journal-title":"Neurosurgery"},{"key":"1557_CR11","doi-asserted-by":"publisher","first-page":"e160","DOI":"10.1016\/j.wneu.2023.08.042","volume":"179","author":"GA Guerra","year":"2023","unstructured":"Guerra GA, Hofmann H, Sobhani S, Hofmann G, Gomez D, Soroudi D et al (2023) GPT-4 artificial intelligence model outperforms ChatGPT, medical students, and neurosurgery residents on neurosurgery written board-like questions. World Neurosurg 179:e160\u2013e165","journal-title":"World Neurosurg"},{"issue":"2","key":"1557_CR12","doi-asserted-by":"publisher","DOI":"10.1136\/bmjno-2023-000530","volume":"5","author":"TC Chen","year":"2023","unstructured":"Chen TC, Multala E, Kearns P, Delashaw J, Dumont A, Maraganore D et al (2023) Assessment of ChatGPT\u2019s performance on neurology written board examination questions. BMJ Neurol Open 5(2):e000530","journal-title":"BMJ Neurol Open"},{"issue":"3","key":"1557_CR13","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1177\/21925682231195783","volume":"14","author":"R Rajjoub","year":"2024","unstructured":"Rajjoub R, Arroyave JS, Zaidat B, Ahmed W, Mejia MR, Tang J et al (2024) ChatGPT and its role in the decision-making for the diagnosis and treatment of lumbar spinal stenosis: a comparative analysis and narrative review. Glob Spine J 14(3):998\u20131017","journal-title":"Glob Spine J"},{"key":"1557_CR14","volume":"22","author":"CCJ Lin","year":"2025","unstructured":"Lin CCJ, Krzy\u017c EZ, Tsai SHL, Wang YC, Chang CW, Lin TY et al (2025) A comparative analysis between ChatGPT versus NASS clinical guidelines for adult isthmic spondylolisthesis. N Am Spine Soc J 22:100599","journal-title":"N Am Spine Soc J"},{"issue":"9","key":"1557_CR15","volume":"16","author":"A Sarikonda","year":"2024","unstructured":"Sarikonda A, Isch E, Self M, Sambangi A, Carreras A, Sivaganesan A et al (2024) Evaluating the adherence of large language models to surgical guidelines: a comparative analysis of chatbot recommendations and North American Spine Society (NASS) coverage criteria. Cureus 16(9):e68521","journal-title":"Cureus"},{"issue":"1","key":"1557_CR16","doi-asserted-by":"publisher","first-page":"149","DOI":"10.14245\/ns.2347052.526","volume":"21","author":"MR Mejia","year":"2024","unstructured":"Mejia MR, Arroyave JS, Saturno M, Ndjonko LCM, Zaidat B, Rajjoub R et al (2024) Use of ChatGPT for determining clinical and surgical treatment of lumbar disc herniation with radiculopathy: a North American Spine Society guideline comparison. Neurospine 21(1):149\u2013158","journal-title":"Neurospine"},{"issue":"8","key":"1557_CR17","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1080\/17434440.2024.2384541","volume":"21","author":"J Zeng","year":"2024","unstructured":"Zeng J, Fu Q (2024) A review: artificial intelligence in image-guided spinal surgery. Expert Rev Med Devices 21(8):689\u2013700","journal-title":"Expert Rev Med Devices"},{"issue":"10","key":"1557_CR18","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/s12178-025-09972-9","volume":"18","author":"JS MacLeod","year":"2025","unstructured":"MacLeod JS, Compton T, Bakaes Y, Chopra A, Akwuole F, Christenson C et al (2025) Artificial intelligence in spine surgery: imaging-based applications for diagnosis and surgical techniques. Curr Rev Musculoskelet Med 18(10):398\u2013405","journal-title":"Curr Rev Musculoskelet Med"},{"key":"1557_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.bas.2024.104165","volume":"5","author":"S Motov","year":"2025","unstructured":"Motov S, Butenschoen VM, Krauss PE, Veeravagu A, Yoo KH, Stengel FC et al (2025) Current state and future perspectives of spinal navigation and robotics-an AO spine survey. Brain Spine 5:104165","journal-title":"Brain Spine"},{"issue":"2","key":"1557_CR20","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1177\/21925682241290752","volume":"15","author":"AT Yahanda","year":"2025","unstructured":"Yahanda AT, Joseph K, Bui T, Greenberg JK, Ray WZ, Ogunlade JI et al (2025) Current applications and future implications of artificial intelligence in spine surgery and research: a narrative review and commentary. Glob Spine J 15(2):1445\u20131454","journal-title":"Glob Spine J"},{"issue":"1","key":"1557_CR21","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1097\/MS9.0000000000002782","volume":"87","author":"MM Khan","year":"2025","unstructured":"Khan MM, Chaurasia B (2025) Artificial intelligence and its use in spine surgery and preparation of predictive models: a systematic review. Ann Med Surg 87(1):171\u2013176","journal-title":"Ann Med Surg"},{"issue":"1","key":"1557_CR22","doi-asserted-by":"publisher","first-page":"53","DOI":"10.20517\/ais.2024.45","volume":"5","author":"VS Ambati","year":"2025","unstructured":"Ambati VS, Saggi S, Dada A, Alan N (2025) Has artificial intelligence in spine surgery lived up to the hype? A narrative review of recent approaches, current challenges, and the path forward. Artif Intell Surg 5(1):53\u201364","journal-title":"Artif Intell Surg"},{"issue":"1","key":"1557_CR23","doi-asserted-by":"publisher","DOI":"10.1186\/s13063-020-04951-6","volume":"22","author":"H Ibrahim","year":"2021","unstructured":"Ibrahim H, Liu X, Rivera SC, Moher D, Chan AW, Sydes MR et al (2021) Reporting guidelines for clinical trials of artificial intelligence interventions: the SPIRIT-AI and CONSORT-AI guidelines. Trials 22(1):11","journal-title":"Trials"},{"issue":"9","key":"1557_CR24","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1038\/s41591-020-1037-7","volume":"26","author":"S Cruz Rivera","year":"2020","unstructured":"Cruz Rivera S, Liu X, Chan AW, Denniston AK, Calvert MJ (2020) Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. Nat Med 26(9):1351\u20131363","journal-title":"Nat Med"},{"issue":"5","key":"1557_CR25","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1038\/s41591-022-01772-9","volume":"28","author":"B Vasey","year":"2022","unstructured":"Vasey B, Nagendran M, Campbell B, Clifton DA, Collins GS, Denaxas S et al (2022) Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. Nat Med 28(5):924\u2013933","journal-title":"Nat Med"}],"container-title":["Spine Deformity"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43390-026-01557-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43390-026-01557-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43390-026-01557-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T15:07:18Z","timestamp":1790608038000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s43390-026-01557-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":25,"alternative-id":["1557"],"URL":"https:\/\/doi.org\/10.1007\/s43390-026-01557-x","relation":{},"ISSN":["2212-134X","2212-1358"],"issn-type":[{"value":"2212-134X","type":"print"},{"value":"2212-1358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"assertion":[{"value":"21 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"C.H.L, A.R, C.T.B, A.B, G.M, and M.J declare that they have no competing interests. D.L.S reports research grant support from the Pediatric Spine Study Group and the Safety in Spine Surgery Project. D.L.S is a Consultant for Highridge, Globus Medical, and Orthobullets. D.L.S holds stock options in Orthobullets and has a personal investment in Green Sun Medical. D.L.S receives royalties from Wolters Kluwer Health (textbooks), Medtronic, Highridge, and Globus Medical. D.L.S has patents with Medtronic and Highridge, and holds personal patents.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study evaluated large language model responses using synthetic, non-identifiable spine case vignettes and anonymous ratings from spine surgeons. No real patient data, human tissue, or identifiable personal information were used. In accordance with institutional and national guidance, formal research ethics committee approval was not required.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No additional identifying information related to the authors, their institutions, funders, or approval committees is included that might compromise anonymity.","order":3,"name":"Ethics","label":"Other identifying information","group":{"name":"EthicsHeading","label":"Declarations"}}]}}