{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:11:48Z","timestamp":1779235908990,"version":"3.51.4"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"content-version":"vor","delay-in-days":40,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Anesthesiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Postoperative pain management is a core component of anesthesiology practice, with regional anesthesia playing a key role in multimodal analgesia strategies. Large language model (LLM)\u2013based artificial intelligence (AI) systems are increasingly proposed as clinical decision support tools; however, their ability to integrate critical perioperative context, such as the presence of an existing regional block, remains insufficiently explored.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This prospective, observational, comparative study included 144 adult patients undergoing elective abdominal surgery at a tertiary care center, after exclusion of four patients due to severe preoperative or intraoperative complications that significantly altered the planned postoperative analgesia. Patients were grouped according to the presence or absence of a regional block (70 per group). For each patient, anonymized and standardized clinical scenarios were evaluated independently by three LLM-based AI systems (ChatGPT, Gemini, and Copilot) to generate postoperative analgesia recommendations. AI outputs were assessed by blinded anesthesiology experts for opioid recommendation, multimodal analgesia, consideration of regional anesthesia, and overall clinical appropriateness using a 5-point Likert scale. Multivariable logistic and ordinal logistic regression analyses were performed to determine the independent effect of regional block presence, adjusting for relevant clinical covariates. Agreement between AI recommendations and actual clinical practice was evaluated using Cohen\u2019s kappa.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Regional block presence was not independently associated with opioid recommendations generated by any AI system (all\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&gt;\u20090.05). However, the likelihood of recommending an additional regional block was significantly reduced by ChatGPT (adjusted odds ratio [aOR] 0.02,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001) and Copilot (aOR 0.15,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.019). Gemini demonstrated complete separation, consistently recommending regional blocks only in patients without an existing block. Multimodal analgesia was universally recommended by ChatGPT and Gemini, precluding regression analysis. Expert evaluation scores were significantly higher in scenarios with an existing regional block across all AI systems. Overall agreement between AI-generated recommendations and real-world clinical decisions was limited.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>LLM-based AI systems demonstrate partial contextual awareness of regional anesthesia when generating postoperative analgesia recommendations. However, this awareness does not consistently translate into concordance with real-world clinical practice. These findings support the use of AI as an adjunctive decision support tool rather than a substitute for clinician judgment in postoperative pain management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12871-026-03814-y","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T23:14:49Z","timestamp":1775776489000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The impact of regional block presence on large language model\u2013based postoperative analgesia recommendations in abdominal surgery: a comparative study using real-world patient data"],"prefix":"10.1186","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3052-2604","authenticated-orcid":false,"given":"Bahar","family":"Uslu Bayhan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2336-1848","authenticated-orcid":false,"given":"Tu\u011f\u00e7e","family":"Gazio\u011flu Ki\u015fi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,10]]},"reference":[{"issue":"2","key":"3814_CR1","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1097\/ALN.0000000000002960","volume":"132","author":"DA Hashimoto","year":"2020","unstructured":"Hashimoto DA, Witkowski E, Gao L, Meireles O, Rosman G. Artificial intelligence in anesthesiology: current techniques, clinical applications, and limitations. Anesthesiology Febr. 2020;132(2):379\u201394.","journal-title":"Anesthesiology Febr"},{"issue":"3","key":"3814_CR2","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1093\/jamia\/ocac231","volume":"30","author":"M Zhang","year":"2022","unstructured":"Zhang M, Zhu L, Lin SY, Herr K, Chi CL, Demir I, et al. Using artificial intelligence to improve pain assessment and pain management: a scoping review. J Am Med Inf Assoc (JAMIA) Dec 2. 2022;30(3):570\u201387.","journal-title":"J Am Med Inf Assoc (JAMIA) Dec 2"},{"issue":"1","key":"3814_CR3","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med January. 2019;25(1):44\u201356.","journal-title":"Nat Med January"},{"issue":"1","key":"3814_CR4","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","volume":"25","author":"A Esteva","year":"2019","unstructured":"Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, et al. A guide to deep learning in healthcare. Nat Med January. 2019;25(1):24\u20139.","journal-title":"Nat Med January"},{"issue":"9","key":"3814_CR5","first-page":"729","volume":"88","author":"V Bellini","year":"2022","unstructured":"Bellini V, Valente M, Gaddi AV, Pelosi P, Bignami E. Artificial intelligence and telemedicine in anesthesia: potential and problems. Minerva Anestesiol September. 2022;88(9):729\u201334.","journal-title":"Minerva Anestesiol September"},{"issue":"2","key":"3814_CR6","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s10877-023-01088-0","volume":"38","author":"S Lopes","year":"2024","unstructured":"Lopes S, Rocha G, Guimar\u00e3es-Pereira L. Artificial intelligence and its clinical application in anesthesiology: a systematic review. J Clin Monit Comput. 2024;38(2):247\u201359.","journal-title":"J Clin Monit Comput"},{"issue":"Suppl 1","key":"3814_CR7","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1111\/anae.15256","volume":"76","author":"YYK Chen","year":"2021","unstructured":"Chen YYK, Boden KA, Schreiber KL. The role of regional anaesthesia and multimodal analgesia in the prevention of chronic postoperative pain: a narrative review. Anaesth January. 2021;76(Suppl 1):8\u201317.","journal-title":"Anaesth January"},{"issue":"3","key":"3814_CR8","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.anclin.2022.04.002","volume":"40","author":"A O\u2019Neill","year":"2022","unstructured":"O\u2019Neill A, Lirk P. Multimodal analgesia. Anesthesiol Clin September. 2022;40(3):455\u201368.","journal-title":"Anesthesiol Clin September"},{"issue":"4","key":"3814_CR9","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1097\/ACO.0000000000001385","volume":"37","author":"H Shanthanna","year":"2024","unstructured":"Shanthanna H, Joshi GP. Opioid-free general anesthesia: considerations, techniques, and limitations. Curr Opin Anaesthesiol August 1. 2024;37(4):384\u201390.","journal-title":"Curr Opin Anaesthesiol August 1"},{"issue":"1","key":"3814_CR10","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1097\/ALN.0000000000005790","volume":"144","author":"GP Joshi","year":"2026","unstructured":"Joshi GP, Mariano E, Elkassabany NM, Harbell M, Johnson RL, Li J, et al. 2026 American Society of Anesthesiologists practice guideline on perioperative pain management using local and regional analgesia for cardiothoracic surgeries, mastectomy, and abdominal surgeries. Anesthesiology January 1. 2026;144(1):19\u201343.","journal-title":"Anesthesiology January 1"},{"issue":"12","key":"3814_CR11","doi-asserted-by":"publisher","first-page":"1974","DOI":"10.1515\/cclm-2022-0291","volume":"25","author":"Q Pei","year":"2022","unstructured":"Pei Q, Luo Y, Chen Y, Li J, Xie D, Ye T. Artificial intelligence in clinical applications for lung cancer: diagnosis, treatment and prognosis. Clin Chem Lab Med November. 2022;25(12):1974\u201383.","journal-title":"Clin Chem Lab Med November"},{"issue":"1","key":"3814_CR12","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s44254-023-00043-1","volume":"25","author":"S Kianian","year":"2024","unstructured":"Kianian S, Bansal J, Lee C, Zhang K, Bergese SD. Perioperative multimodal analgesia: a review of efficacy and safety of the treatment options. Anesthesiol Perioper Sci January. 2024;25(1):9.","journal-title":"Anesthesiol Perioper Sci January"},{"issue":"3","key":"3814_CR13","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.jatmed.2025.09.001","volume":"1","author":"X Chen","year":"2025","unstructured":"Chen X, Chu Q, Peng Y, Chen Y, Kaye AD, Liu H, et al. Clinical practice guidelines for postoperative pain management in adults (2024 edition). J Anesth Transl Med. September 2025;1(3):161\u201385.","journal-title":"J Anesth Transl Med"},{"issue":"Suppl 1","key":"3814_CR14","doi-asserted-by":"publisher","first-page":"S40","DOI":"10.4103\/joacp.JOACP_51_18","volume":"35","author":"AD Kaye","year":"2019","unstructured":"Kaye AD, Urman RD, Rappaport Y, Siddaiah H, Cornett EM, Belani K, et al. Multimodal analgesia as an essential part of enhanced recovery protocols in the ambulatory settings. J Anaesthesiol Clin Pharmacol April. 2019;35(Suppl 1):S40\u20135.","journal-title":"J Anaesthesiol Clin Pharmacol April"},{"issue":"5","key":"3814_CR15","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1097\/ACO.0000000000001408","volume":"1","author":"R Sajdeya","year":"2024","unstructured":"Sajdeya R, Narouze S. Harnessing artificial intelligence for predicting and managing postoperative pain: a narrative literature review. Curr Opin Anaesthesiol Oct. 2024;1(5):604\u201315.","journal-title":"Curr Opin Anaesthesiol Oct"},{"issue":"1","key":"3814_CR16","doi-asserted-by":"publisher","first-page":"3","DOI":"10.4103\/joacp.JOACP_362_19","volume":"38","author":"B Ghai","year":"2022","unstructured":"Ghai B, Jafra A, Bhatia N, Chanana N, Bansal D, Mehta V. Opioid sparing strategies for perioperative pain management other than regional anaesthesia: a narrative review. J Anaesthesiol Clin Pharmacol. 2022;38(1):3\u201310.","journal-title":"J Anaesthesiol Clin Pharmacol"},{"key":"3814_CR17","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s12871-024-02882-2","volume":"3","author":"E \u00c7elik","year":"2025","unstructured":"\u00c7elik E, Turgut MA, Aydo\u011fan M, K\u0131l\u0131n\u00e7 M, Tokta\u015f \u0130, Akelma H. Comparison of AI applications and anesthesiologist\u2019s anesthesia method choices. BMC Anesthesiol January. 2025;3:25:2.","journal-title":"BMC Anesthesiol January"},{"issue":"3","key":"3814_CR18","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1016\/j.anclin.2025.05.004","volume":"43","author":"HJS Medeiros","year":"2025","unstructured":"Medeiros HJS, Dabbagh A, Vlassakov K, Sabouri AS. Artificial intelligence in regional anesthesia and pain management. Anesthesiol Clin September. 2025;43(3):491\u2013505.","journal-title":"Anesthesiol Clin September"},{"key":"3814_CR19","doi-asserted-by":"publisher","first-page":"205520762311893","DOI":"10.1177\/20552076231189331","volume":"18","author":"OV Bitkina","year":"2023","unstructured":"Bitkina OV, Park J, Kim HK. Application of artificial intelligence in medical technologies: a systematic review of main trends. Digit Health July. 2023;18:9:20552076231189331.","journal-title":"Digit Health July"},{"key":"3814_CR20","first-page":"e63924","volume":"9","author":"Y Zhang","year":"2025","unstructured":"Zhang Y, Lu X, Luo Y, Zhu Y, Ling W. Performance of artificial intelligence chatbots on ultrasound examinations: cross-sectional comparative analysis. JMIR Med Inf January. 2025;9:13:e63924.","journal-title":"JMIR Med Inf January"},{"key":"3814_CR21","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1186\/s12903-025-05926-2","volume":"15","author":"BE Yilmaz","year":"2025","unstructured":"Yilmaz BE, Gokkurt Yilmaz BN, Ozbey F. Artificial intelligence performance in answering multiple-choice oral pathology questions: a comparative analysis. BMC Oral Health April. 2025;15:25:573.","journal-title":"BMC Oral Health April"},{"issue":"4","key":"3814_CR22","doi-asserted-by":"publisher","first-page":"357","DOI":"10.17085\/apm.25354","volume":"31","author":"Y Jo","year":"2025","unstructured":"Jo Y, Baek S, Baek D, Oh C, Lee D, Hong B. Artificial intelligence in ultrasound-guided regional anesthesia: bridging the gap between potential and practice: a narrative review. Anesth Pain Med. October 2025;31(4):357\u201370.","journal-title":"Anesth Pain Med"},{"issue":"3","key":"3814_CR23","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1213\/ANE.0000000000007473","volume":"141","author":"RD Minehart","year":"2025","unstructured":"Minehart RD, Stefanski SE. Artificial intelligence supporting anesthesiology clinical decision-making. Anesth Analg September. 2025;141(3):536.","journal-title":"Anesth Analg September"},{"issue":"3","key":"3814_CR24","doi-asserted-by":"publisher","first-page":"e4748","DOI":"10.1002\/ejp.4748","volume":"29","author":"R Antel","year":"2025","unstructured":"Antel R, Whitelaw S, Gore G, Ingelmo P. Moving towards the use of artificial intelligence in pain management. Eur J Pain March. 2025;29(3):e4748.","journal-title":"Eur J Pain March"},{"issue":"11","key":"3814_CR25","doi-asserted-by":"publisher","first-page":"3737","DOI":"10.1038\/s41591-025-03942-x","volume":"31","author":"AW Rosen","year":"2025","unstructured":"Rosen AW, Ose I, G\u00f6genur M, Andersen LPK, Bojesen RD, Vogelsang RP, et al. Clinical implementation of an AI-based prediction model for decision support for patients undergoing colorectal cancer surgery. Nat Med November. 2025;31(11):3737\u201348.","journal-title":"Nat Med November"}],"container-title":["BMC Anesthesiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12871-026-03814-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12871-026-03814-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12871-026-03814-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T23:54:18Z","timestamp":1779234858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12871-026-03814-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,10]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["3814"],"URL":"https:\/\/doi.org\/10.1186\/s12871-026-03814-y","relation":{},"ISSN":["1471-2253"],"issn-type":[{"value":"1471-2253","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,10]]},"assertion":[{"value":"1 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the Gaziantep City Hospital Non-Interventional Clinical Research Ethics Committee (approval decision no: 312\/2025). This study was conducted in compliance with the Declaration of Helsinki.Written informed consent was obtained from all participants.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"316"}}