{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T07:29:32Z","timestamp":1784359772185,"version":"3.55.0"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Managing postoperative complications is an essential part of surgical care and largely depends on the medical team\u2019s experience. Large Language Models (LLMs) have demonstrated immense potential in supporting medical professionals. To evaluate the potential of LLMs in surgical patient care, we compared the performance of three state-of-the-art LLMs in managing postoperative complications to that of a panel of medical professionals based on six postsurgical patient cases. Six realistic postoperative patient cases were queried using GPT-3, GPT-4, and Gemini-Advanced and presented to human surgical caregivers. Humans and LLMs provided a triage assessment, an initial suspected diagnosis, and an acute management plan, including initial diagnostic and therapeutic measures. Responses were compared based on medical contextual correctness, coherence, and completeness. In comparison to human caregivers, GPT-3 and GPT-4 possess considerable competencies in correctly identifying postoperative complications (humans: 76.3% vs. GPT-3: 75.0% vs. GPT-4: 96.7%, p\u2009=\u20090.47) as well as triaging patients accordingly (humans: 84.8% vs. GPT-3: 50% vs. GPT-4: 38.3%, p\u2009=\u20090.19). With regard to diagnostic and therapeutic management of postoperative complications, GPT-3 and GPT-4 provided comprehensive management plans. Gemini-Advanced often provided no diagnostic or therapeutic recommendations and censored its outputs. In summary, LLMs can accurately interpret postoperative care scenarios and provide comprehensive management recommendations. These results showcase the improvements in LLMs performance with regard to postoperative surgical use cases and provide evidence for their potential value to support and augment surgical routine care.<\/jats:p>","DOI":"10.1371\/journal.pdig.0000933","type":"journal-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T17:53:36Z","timestamp":1754070816000},"page":"e0000933","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Postoperative complication management: How do large language models measure up to human expertise?"],"prefix":"10.1371","volume":"4","author":[{"given":"Sophie-Caroline","family":"Schwarzkopf","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean-Paul","family":"Bereuter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark Enrik","family":"Geissler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Weitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marius","family":"Distler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2265-4809","authenticated-orcid":true,"given":"Fiona R.","family":"Kolbinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,8,1]]},"reference":[{"issue":"1","key":"pdig.0000933.ref001","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.jss.2013.01.032","article-title":"Postoperative complications and implications on patient-centered outcomes","volume":"181","author":"SE Tevis","year":"2013","journal-title":"J Surg Res"},{"issue":"10","key":"pdig.0000933.ref002","doi-asserted-by":"crossref","DOI":"10.4244\/EIJ-D-23-00461","article-title":"Towards AI-assisted cardiology: a reflection on the performance and limitations of using large language models in clinical decision-making","volume":"19","author":"A Salihu","year":"2023","journal-title":"EuroIntervention"},{"issue":"9","key":"pdig.0000933.ref003","doi-asserted-by":"crossref","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","article-title":"Evaluation and mitigation of the limitations of large language models in clinical decision-making","volume":"30","author":"P Hager","year":"2024","journal-title":"Nat Med"},{"issue":"2","key":"pdig.0000933.ref004","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/j.surg.2024.04.003","article-title":"AI Versus MD: Evaluating the surgical decision-making accuracy of ChatGPT-4","volume":"176","author":"DL Palenzuela","year":"2024","journal-title":"Surgery"},{"key":"pdig.0000933.ref005","article-title":"Language Models are Few-Shot Learners","author":"TB Brown","year":"2020","journal-title":"Arxiv"},{"key":"pdig.0000933.ref006","article-title":"Gemini: A family of highly capable multimodal models","author":"R Anil","year":"2023","journal-title":"Arxiv"},{"issue":"1","key":"pdig.0000933.ref007","doi-asserted-by":"crossref","DOI":"10.1007\/s44163-023-00055-7","article-title":"Does GPT-3 qualify as a co-author of a scientific paper publishable in peer-review journals according to the ICMJE criteria? A case study","volume":"3","author":"A Osmanovic-Thunstr\u00f6m","year":"2023","journal-title":"Discov Artif Intell"},{"issue":"4","key":"pdig.0000933.ref008","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","article-title":"GPT-3: Its Nature, Scope, Limits, and Consequences","volume":"30","author":"L Floridi","year":"2020","journal-title":"Minds & Machines"},{"key":"pdig.0000933.ref009","article-title":"GPT-4 Technical Report","author":"J Achiam","year":"2023","journal-title":"Arxiv"},{"issue":"6","key":"pdig.0000933.ref010","first-page":"1018","article-title":"Beyond ChatGPT: What does GPT-4 add to healthcare? The dawn of a new era","volume":"30","author":"S W\u00f3jcik","year":"2023","journal-title":"Cardiol J"},{"key":"pdig.0000933.ref011","doi-asserted-by":"crossref","DOI":"10.1016\/j.wneu.2023.08.042","article-title":"GPT-4 Artificial Intelligence Model Outperforms ChatGPT, Medical Students, and Neurosurgery Residents on Neurosurgery Written Board-Like Questions","volume":"179","author":"GA Guerra","year":"2023","journal-title":"World Neurosurg"},{"issue":"2","key":"pdig.0000933.ref012","article-title":"Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models","volume":"2","author":"TH Kung","year":"2023","journal-title":"PLOS Digit Health"},{"issue":"4","key":"pdig.0000933.ref013","doi-asserted-by":"crossref","first-page":"936","DOI":"10.1016\/j.surg.2023.12.014","article-title":"Evaluating capabilities of large language models: Performance of GPT-4 on surgical knowledge assessments","volume":"175","author":"BR Beaulieu-Jones","year":"2024","journal-title":"Surgery"},{"key":"pdig.0000933.ref014","article-title":"Utility of ChatGPT in Clinical Practice","volume":"25","author":"J Liu","year":"2023","journal-title":"J Med Internet Res"},{"issue":"2","key":"pdig.0000933.ref015","doi-asserted-by":"crossref","DOI":"10.1093\/jamiaopen\/ooae043","article-title":"Using large language models for safety-related table summarization in clinical study reports","volume":"7","author":"R Landman","year":"2024","journal-title":"JAMIA Open"},{"key":"pdig.0000933.ref016","doi-asserted-by":"crossref","first-page":"108051","DOI":"10.1016\/j.cmpb.2024.108051","article-title":"Improving preliminary clinical diagnosis accuracy through knowledge filtering techniques in consultation dialogues","volume":"246","author":"A Abdul","year":"2024","journal-title":"Comput Methods Programs Biomed"},{"issue":"3","key":"pdig.0000933.ref017","article-title":"Diagnostic and Management Applications of ChatGPT in Structured Otolaryngology Clinical Scenarios","volume":"7","author":"RW Qu","year":"2023","journal-title":"OTO Open"},{"key":"pdig.0000933.ref018","article-title":"Assessing the Utility of ChatGPT Throughout the Entire Clinical Workflow: Development and Usability Study","volume":"25","author":"A Rao","year":"2023","journal-title":"J Med Internet Res"},{"issue":"5","key":"pdig.0000933.ref019","doi-asserted-by":"crossref","first-page":"1257","DOI":"10.1038\/s41591-024-02970-3","article-title":"Artificial intelligence in surgery","volume":"30","author":"C Varghese","year":"2024","journal-title":"Nat Med"},{"issue":"5","key":"pdig.0000933.ref020","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1097\/JS9.0000000000000388","article-title":"The potential impact of ChatGPT\/GPT-4 on surgery: will it topple the profession of surgeons?","volume":"109","author":"K Cheng","year":"2023","journal-title":"Int J Surg"},{"issue":"11","key":"pdig.0000933.ref021","doi-asserted-by":"crossref","first-page":"3041","DOI":"10.3390\/jcm13113041","article-title":"Clinical and Surgical Applications of Large Language Models: A Systematic Review","volume":"13","author":"SM Pressman","year":"2024","journal-title":"J Clin Med"},{"key":"pdig.0000933.ref022","article-title":"Enhancing medical task performance in GPT-4V: A comprehensive study on prompt engineering strategies","author":"P Chen","year":"2023","journal-title":"Arxiv"},{"key":"pdig.0000933.ref023","article-title":"Case-Based Serious Gaming for Complication Management in Colorectal and Pancreatic Surgery: Prospective Observational Study","volume":"11","author":"S-C Schwarzkopf","year":"2023","journal-title":"JMIR Serious Games"},{"issue":"5","key":"pdig.0000933.ref024","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1016\/j.surg.2007.05.005","article-title":"Delayed gastric emptying (DGE) after pancreatic surgery: a suggested definition by the International Study Group of Pancreatic Surgery (ISGPS)","volume":"142","author":"MN Wente","year":"2007","journal-title":"Surgery"},{"issue":"3","key":"pdig.0000933.ref025","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1016\/j.surg.2016.11.014","article-title":"The 2016 update of the International Study Group (ISGPS) definition and grading of postoperative pancreatic fistula: 11 Years After","volume":"161","author":"C Bassi","year":"2017","journal-title":"Surgery"},{"issue":"6","key":"pdig.0000933.ref026","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1016\/j.surg.2013.02.007","article-title":"Validation of the International Study Group of Rectal Cancer definition and severity grading of anastomotic leakage","volume":"153","author":"Y Kulu","year":"2013","journal-title":"Surgery"},{"issue":"6","key":"pdig.0000933.ref027","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1007\/s00423-011-0811-x","article-title":"Critical appraisal of the International Study Group of Pancreatic Surgery (ISGPS) consensus definition of postoperative hemorrhage after pancreatoduodenectomy","volume":"396","author":"T Welsch","year":"2011","journal-title":"Langenbecks Arch Surg"},{"issue":"3","key":"pdig.0000933.ref028","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1071\/AH10922","article-title":"What is a health emergency? The difference in definition and understanding between patients and health professionals","volume":"35","author":"A Morgans","year":"2011","journal-title":"Aust Health Rev"},{"issue":"4","key":"pdig.0000933.ref029","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1097\/JS9.0000000000001066","article-title":"Evaluation of large language models in breast cancer clinical scenarios: a comparative analysis based on ChatGPT-3.5, ChatGPT-4.0, and Claude2","volume":"110","author":"L Deng","year":"2024","journal-title":"Int J Surg"},{"issue":"8","key":"pdig.0000933.ref030","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1093\/asj\/sjae025","article-title":"Utility and Comparative Performance of Current Artificial Intelligence Large Language Models as Postoperative Medical Support Chatbots in Aesthetic Surgery","volume":"44","author":"J Abi-Rafeh","year":"2024","journal-title":"Aesthet Surg J"},{"issue":"7","key":"pdig.0000933.ref031","article-title":"Large Language Models Take on Cardiothoracic Surgery: A Comparative Analysis of the Performance of Four Models on American Board of Thoracic Surgery Exam Questions in 2023","volume":"16","author":"Z Khalpey","year":"2024","journal-title":"Cureus"},{"key":"pdig.0000933.ref032","doi-asserted-by":"crossref","DOI":"10.2196\/52784","article-title":"Influence of Model Evolution and System Roles on ChatGPT\u2019s Performance in Chinese Medical Licensing Exams: Comparative Study","volume":"10","author":"S Ming","year":"2024","journal-title":"JMIR Med Educ"},{"issue":"1","key":"pdig.0000933.ref033","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/s43856-023-00370-1","article-title":"The future landscape of large language models in medicine","volume":"3","author":"J Clusmann","year":"2023","journal-title":"Commun Med (Lond)"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T17:53:41Z","timestamp":1754070821000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000933"}},"subtitle":[],"editor":[{"given":"Philipp","family":"Berens","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,8,1]]},"references-count":33,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0000933","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,1]]}}}