{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T04:00:51Z","timestamp":1763092851641,"version":"build-2065373602"},"reference-count":22,"publisher":"BMJ","issue":"11","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Reg Anesth Pain Med"],"accepted":{"date-parts":[[2023,6,7]]},"published-print":{"date-parts":[[2023,11]]},"abstract":"<jats:p>Interest in natural language processing, specifically large language models, for clinical applications has exploded in a matter of several months since the introduction of ChatGPT. Large language models are powerful and impressive. It is important that we understand the strengths and limitations of this rapidly evolving technology so that we can brainstorm its future potential in perioperative medicine. In this daring discourse, we discuss the issues with these large language models and how we should proactively think about how to leverage these models into practice to improve patient care, rather than worry that it may take over clinical decision-making. We review three potential major areas in which it may be used to benefit perioperative medicine: (1) clinical decision support and surveillance tools, (2) improved aggregation and analysis of research data related to large retrospective studies and application in predictive modeling, and (3) optimized documentation for quality measurement, monitoring and billing compliance. These large language models are here to stay and, as perioperative providers, we can either adapt to this technology or be curtailed by those who learn to use it well.<\/jats:p>","DOI":"10.1136\/rapm-2023-104637","type":"journal-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T10:15:15Z","timestamp":1687169715000},"page":"575-577","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":12,"title":["How large language models can augment perioperative medicine: a daring discourse"],"prefix":"10.1136","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4443-0021","authenticated-orcid":false,"given":"Rodney A","family":"Gabriel","sequence":"first","affiliation":[{"name":"Anesthesiology, University of California San Diego, La Jolla, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2735-248X","authenticated-orcid":false,"given":"Edward R","family":"Mariano","sequence":"additional","affiliation":[{"name":"Anesthesiology and Perioperative Care Service, VA Palo Alto Health Care System, Palo Alto, California, USA"},{"name":"Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"McAuley","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of California San Diego, La Jolla, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4484-0787","authenticated-orcid":false,"given":"Christopher L","family":"Wu","sequence":"additional","affiliation":[{"name":"Anesthesiology, Hospital for Special Surgery, New York City, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2023,6,19]]},"reference":[{"key":"2025101111083915000_48.11.575.1","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1038\/s41591-023-02289-5","article-title":"Will ChatGPT transform healthcare","volume":"29","year":"2023","journal-title":"Nat Med"},{"key":"2025101111083915000_48.11.575.2","doi-asserted-by":"crossref","first-page":"106649","DOI":"10.1016\/j.compbiomed.2023.106649","article-title":"Natural language processing in electronic health records in relation to healthcare decision-making: a systematic review","volume":"155","author":"Hossain","year":"2023","journal-title":"Comput Biol Med"},{"key":"2025101111083915000_48.11.575.3","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.230163","article-title":"Chatgpt and other large language models are double-edged swords","volume":"307","author":"Shen","year":"2023","journal-title":"Radiology"},{"key":"2025101111083915000_48.11.575.4","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-022-00742-2","article-title":"A large language model for electronic health records","volume":"5","author":"Yang","year":"2022","journal-title":"NPJ Digit Med"},{"key":"2025101111083915000_48.11.575.5","unstructured":"Johnson A . Bard vs Chatgpt: the major difference between the AI chat tools, explained. 2023."},{"key":"2025101111083915000_48.11.575.6","doi-asserted-by":"crossref","DOI":"10.2196\/45312","article-title":"How does ChatGPT perform on the United States medical licensing examination? The implications of large language models for medical education and knowledge assessment","volume":"9","author":"Gilson","year":"2023","journal-title":"JMIR Med Educ"},{"key":"2025101111083915000_48.11.575.7","doi-asserted-by":"crossref","DOI":"10.1016\/j.ebiom.2023.104512","article-title":"Attention is not all you need: the complicated case of ethically using large language models in healthcare and medicine","volume":"90","author":"Harrer","year":"2023","journal-title":"EBioMedicine"},{"key":"2025101111083915000_48.11.575.8","doi-asserted-by":"publisher","DOI":"10.7326\/M18-0139"},{"key":"2025101111083915000_48.11.575.9","doi-asserted-by":"publisher","DOI":"10.1136\/rapm-2021-102669"},{"key":"2025101111083915000_48.11.575.10","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1111\/j.1526-4637.2012.01477.x","article-title":"Use of machine-learning classifiers to predict requests for preoperative acute pain service consultation","volume":"13","author":"Tighe","year":"2012","journal-title":"Pain Med"},{"key":"2025101111083915000_48.11.575.11","unstructured":"Gabriel RA , Park BH , Simpson S . Utilizing natural language processing and machine learning to identify persistent opioid use from postoperative surgical documents. abstract. American Society of Regional Anesthesia and Pain Medicine Annual Conference; 2023"},{"key":"2025101111083915000_48.11.575.12","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1213\/ANE.0000000000006152","article-title":"Identification of preanesthetic history elements by a natural language processing engine","volume":"135","author":"Suh","year":"2022","journal-title":"Anesth Analg"},{"key":"2025101111083915000_48.11.575.13","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1001\/jamasurg.2018.0647","article-title":"Tips for analyzing large data SETS from the JAMA surgery statistical editors","volume":"153","author":"Kaji","year":"2018","journal-title":"JAMA Surg"},{"key":"2025101111083915000_48.11.575.14","doi-asserted-by":"publisher","DOI":"10.1136\/rapm-2021-103299"},{"key":"2025101111083915000_48.11.575.15","doi-asserted-by":"crossref","unstructured":"Giladi AM , Shipp MM , Sanghavi KK , et al . Patient-reported data augment health record data for prediction models of persistent opioid use after elective upper extremity surgery. Plast Reconstr Surg 2023;Publish Ahead of Print. doi:10.1097\/PRS.0000000000010297","DOI":"10.1097\/PRS.0000000000010297"},{"key":"2025101111083915000_48.11.575.16","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1016\/j.spinee.2022.02.009","article-title":"A machine learning algorithm for predicting prolonged postoperative opioid prescription after lumbar disc Herniation surgery. An external validation study using 1,316 patients from a Taiwanese cohort","volume":"22","author":"Yen","year":"2022","journal-title":"Spine J"},{"key":"2025101111083915000_48.11.575.17","doi-asserted-by":"crossref","unstructured":"Debbi EM , Krell EC , Sapountzis N , et al . Predicting postdischarge opioid consumption after total hip and knee arthroplasty in the opioid Na\u00efve patient. J Arthroplasty 2022;37. doi:10.1016\/j.arth.2022.07.025","DOI":"10.1016\/j.arth.2022.07.025"},{"key":"2025101111083915000_48.11.575.18","doi-asserted-by":"crossref","DOI":"10.2196\/23230","article-title":"Automatic ICD-10 coding and training system: deep neural network based on supervised learning","volume":"9","author":"Chen","year":"2021","journal-title":"JMIR Med Inform"},{"key":"2025101111083915000_48.11.575.19","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-023-00768-0","article-title":"Automating the overburdened clinical coding system: challenges and next steps","volume":"6","author":"Venkatesh","year":"2023","journal-title":"NPJ Digit Med"},{"key":"2025101111083915000_48.11.575.20","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph19137898","article-title":"Machine learning-based regression framework to predict health insurance premiums","volume":"19","author":"Kaushik","year":"2022","journal-title":"Int J Environ Res Public Health"},{"key":"2025101111083915000_48.11.575.21","unstructured":"Rosenthal E . Denials of health insurance claims are rising\u2014and getting weirder. 2023. Available: url: https:\/\/www.fiercehealthcare.com\/payers\/denials-health-insurance-claims-are-rising-and-getting-weirder [Accessed 30 May 2023]."},{"key":"2025101111083915000_48.11.575.22","unstructured":"Rucker P , Miller MD . How Cigna saves millions by having its doctors reject claims without reading them. 2023. Available: url: https:\/\/www.propublica.org\/article\/cigna-pxdx-medical-health-insurance-rejection-claims [Accessed 30 May 2023]."}],"container-title":["Regional Anesthesia &amp; Pain Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/rapm-2023-104637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:08:52Z","timestamp":1760206132000},"score":1,"resource":{"primary":{"URL":"https:\/\/rapm.bmj.com\/lookup\/doi\/10.1136\/rapm-2023-104637"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,19]]},"references-count":22,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2023,9,21]]},"published-print":{"date-parts":[[2023,11]]}},"alternative-id":["10.1136\/rapm-2023-104637"],"URL":"https:\/\/doi.org\/10.1136\/rapm-2023-104637","relation":{},"ISSN":["1098-7339","1532-8651"],"issn-type":[{"type":"print","value":"1098-7339"},{"type":"electronic","value":"1532-8651"}],"subject":[],"published":{"date-parts":[[2023,6,19]]}}}