{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:06:55Z","timestamp":1784308015279,"version":"3.55.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,17]]},"DOI":"10.7759\/cureus.112868","type":"journal-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:29:49Z","timestamp":1784305789000},"source":"Crossref","is-referenced-by-count":0,"title":["Comparative Performance of Large Language Models in the Polish State Specialization Examination in Anesthesiology and Intensive Care Medicine"],"prefix":"10.7759","author":[{"given":"Jakub","family":"Wojtas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Glieb","family":"Pak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wojciech J","family":"G\u00f3rski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu AJ","year":"2023","unstructured":"Thirunavukarasu AJ, Ting DS, Elangovan K, Gutierrez L, Tan TF, Ting DS. Large language models in medicine. Nat Med. 2023, 29:1930-40. 10.1038\/s41591-023-02448-8","journal-title":"Nat Med"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","author":"Singhal K","year":"2025","unstructured":"Singhal K, Tu T, Gottweis J, et al.. Toward expert-level medical question answering with large language models. Nat Med. 2025, 31:943-50. 10.1038\/s41591-024-03423-7","journal-title":"Nat Med"},{"key":"ref3","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 M","year":"2023","unstructured":"Sallam M. ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. Healthcare (Basel). 2023, 11:887. 10.3390\/healthcare11060887","journal-title":"Healthcare (Basel)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.17641","article-title":"Performance of large language models on medical oncology examination questions","volume":"7","author":"Longwell JB","year":"2024","unstructured":"Longwell JB, Hirsch I, Binder F, et al.. Performance of large language models on medical oncology examination questions. JAMA Netw Open. 2024, 7:e2417641. 10.1001\/jamanetworkopen.2024.17641","journal-title":"JAMA Netw Open"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00458-8","article-title":"Large pre-trained language models contain human-like biases of what is right and wrong to do","volume":"4","author":"Schramowski P","year":"2022","unstructured":"Schramowski P, Turan C, Andersen N, Rothkopf CA, Kersting K. Large pre-trained language models contain human-like biases of what is right and wrong to do. Nat Mach Intell. 2022, 4:258-68. 10.1038\/s42256-022-00458-8","journal-title":"Nat Mach Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-023-00370-1","article-title":"The future landscape of large language models in medicine","volume":"3","author":"Clusmann J","year":"2023","unstructured":"Clusmann J, Kolbinger FR, Muti HS, et al.. The future landscape of large language models in medicine. Commun Med (Lond). 2023, 3:141. 10.1038\/s43856-023-00370-1","journal-title":"Commun Med (Lond)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2196\/45312","article-title":"How does ChatGPT perform on the United States Medical Licensing Examination (USMLE)? The implications of large language models for medical education and knowledge assessment","volume":"9","author":"Gilson A","year":"2023","unstructured":"Gilson A, Safranek CW, Huang T, Socrates V, Chi L, Taylor RA, Chartash D. How does ChatGPT perform on the United States Medical Licensing Examination (USMLE)? The implications of large language models for medical education and knowledge assessment. JMIR Med Educ. 2023, 9:e45312. 10.2196\/45312","journal-title":"JMIR Med Educ"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra2302038","article-title":"Artificial intelligence and machine learning in clinical medicine, 2023","volume":"388","author":"Haug CJ","year":"2023","unstructured":"Haug CJ, Drazen JM. Artificial intelligence and machine learning in clinical medicine, 2023. N Engl J Med. 2023, 388:1201-8. 10.1056\/NEJMra2302038","journal-title":"N Engl J Med"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-63997-7","article-title":"In-depth analysis of ChatGPT's performance based on specific signaling words and phrases in the question stem of 2377 USMLE step 1 style questions","volume":"14","author":"Knoedler L","year":"2024","unstructured":"Knoedler L, Knoedler S, Hoch CC, et al.. In-depth analysis of ChatGPT's performance based on specific signaling words and phrases in the question stem of 2377 USMLE step 1 style questions. Sci Rep. 2024, 14:13553. 10.1038\/s41598-024-63997-7","journal-title":"Sci Rep"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMsr2214184","article-title":"Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine","volume":"388","author":"Lee P","year":"2023","unstructured":"Lee P, Bubeck S, Petro J. Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine. N Engl J Med. 2023, 388:1233-9. 10.1056\/NEJMsr2214184","journal-title":"N Engl J Med"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1097\/ALN.0000000000002960","article-title":"Artificial intelligence in anesthesiology: current techniques, clinical applications, and limitations","volume":"132","author":"Hashimoto DA","year":"2020","unstructured":"Hashimoto DA, Witkowski E, Gao L, Meireles O, Rosman G. Artificial intelligence in anesthesiology: current techniques, clinical applications, and limitations. Anesthesiology. 2020, 132:379-94. 10.1097\/ALN.0000000000002960","journal-title":"Anesthesiology"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5","article-title":"The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care","volume":"24","author":"Komorowski M","year":"2018","unstructured":"Komorowski M, Celi LA, Badawi O, Gordon AC, Faisal AA. The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care. Nat Med. 2018, 24:1716-20. 10.1038\/s41591-018-0213-5","journal-title":"Nat Med"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1093\/ced\/llad255","article-title":"ChatGPT-3.5 and ChatGPT-4 dermatological knowledge level based on the Specialty Certificate Examination in Dermatology","volume":"49","author":"Lewandowski M","year":"2024","unstructured":"Lewandowski M, \u0141ukowicz P, \u015awietlik D, Bara\u0144ska-Rybak W. ChatGPT-3.5 and ChatGPT-4 dermatological knowledge level based on the Specialty Certificate Examination in Dermatology. Clin Exp Dermatol. 2024, 49:686-91. 10.1093\/ced\/llad255","journal-title":"Clin Exp Dermatol"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare12161637","article-title":"Assessment study of ChatGPT-3.5\u2019s performance on the final Polish Medical Examination: accuracy in answering 980 questions","volume":"12","author":"Siebielec J","year":"2024","unstructured":"Siebielec J, Ordak M, Oskroba A, Dworakowska A, Bujalska-Zadrozny M. Assessment study of ChatGPT-3.5\u2019s performance on the final Polish Medical Examination: accuracy in answering 980 questions. Healthcare (Basel). 2024, 12:1637. 10.3390\/healthcare12161637","journal-title":"Healthcare (Basel)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2196\/69485","article-title":"Performance of large language models in the non-English context: qualitative study of models trained on different languages in Chinese medical examinations","volume":"13","author":"Yao Z","year":"2025","unstructured":"Yao Z, Duan L, Xu S, Chi L, Sheng D. Performance of large language models in the non-English context: qualitative study of models trained on different languages in Chinese medical examinations. JMIR Med Inform. 2025, 13:e69485. 10.2196\/69485","journal-title":"JMIR Med Inform"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-08424-1","article-title":"Comparative analysis of ChatGPT 3.5 and ChatGPT 4 obstetric and gynecological knowledge","volume":"15","author":"\u0141ugowski F","year":"2025","unstructured":"\u0141ugowski F, Babi\u0144ska J, Ludwin A, Stanirowski PJ. Comparative analysis of ChatGPT 3.5 and ChatGPT 4 obstetric and gynecological knowledge. Sci Rep. 2025, 15:21133. 10.1038\/s41598-025-08424-1","journal-title":"Sci Rep"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-46995-z","article-title":"Evaluation of the performance of GPT-3.5 and GPT-4 on the Polish Medical Final Examination","volume":"13","author":"Roso\u0142 M","year":"2023","unstructured":"Roso\u0142 M, G\u0105sior JS, \u0141aba J, Korzeniewski K, M\u0142y\u0144czak M. Evaluation of the performance of GPT-3.5 and GPT-4 on the Polish Medical Final Examination. Sci Rep. 2023, 13:20512. 10.1038\/s41598-023-46995-z","journal-title":"Sci Rep"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.83552","article-title":"Performance of ChatGPT-3.5 and ChatGPT-4 in solving questions based on core concepts in cardiovascular physiology","volume":"17","author":"Banerjee A","year":"2025","unstructured":"Banerjee A, Chatterjee M, Goyal K, Sarangi PK. Performance of ChatGPT-3.5 and ChatGPT-4 in solving questions based on core concepts in cardiovascular physiology. Cureus. 2025, 17:e83552. 10.7759\/cureus.83552","journal-title":"Cureus"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.93022","article-title":"Comparison of GPT-4o with human performance in the Polish vascular surgery specialty examination","volume":"17","author":"Loson-Kawalec M","year":"2025","unstructured":"Loson-Kawalec M, Kowalczyk A, Tabor A, et al.. Comparison of GPT-4o with human performance in the Polish vascular surgery specialty examination. Cureus. 2025, 17:e93022. 10.7759\/cureus.93022","journal-title":"Cureus"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2196\/47737","article-title":"Performance of ChatGPT on UK standardized admission tests: insights from the BMAT, TMUA, LNAT, and TSA examinations","volume":"9","author":"Giannos P","year":"2023","unstructured":"Giannos P, Delardas O. Performance of ChatGPT on UK standardized admission tests: insights from the BMAT, TMUA, LNAT, and TSA examinations. JMIR Med Educ. 2023, 9:e47737. 10.2196\/47737","journal-title":"JMIR Med Educ"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/1471-0528.17641","article-title":"Performance of ChatGPT in medical examinations: a systematic review and a meta-analysis","volume":"131","author":"Levin G","year":"2024","unstructured":"Levin G, Horesh N, Brezinov Y, Meyer R. Performance of ChatGPT in medical examinations: a systematic review and a meta-analysis. BJOG. 2024, 131:378-80. 10.1111\/1471-0528.17641","journal-title":"BJOG"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-025-02213-z","article-title":"Performance of DeepSeek-R1 and ChatGPT-4o on the Chinese National Medical Licensing Examination: a comparative study","volume":"49","author":"Wu J","year":"2025","unstructured":"Wu J, Wang Z, Qin Y. Performance of DeepSeek-R1 and ChatGPT-4o on the Chinese National Medical Licensing Examination: a comparative study. J Med Syst. 2025, 49:74. 10.1007\/s10916-025-02213-z","journal-title":"J Med Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2196\/50965","article-title":"Comparison of the performance of GPT-3.5 and GPT-4 with that of medical students on the written German Medical Licensing Examination: observational study","volume":"10","author":"Meyer A","year":"2024","unstructured":"Meyer A, Riese J, Streichert T. Comparison of the performance of GPT-3.5 and GPT-4 with that of medical students on the written German Medical Licensing Examination: observational study. JMIR Med Educ. 2024, 10:e50965. 10.2196\/50965","journal-title":"JMIR Med Educ"}],"container-title":["Cureus"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cureus.com\/articles\/515187-comparative-performance-of-large-language-models-in-the-polish-state-specialization-examination-in-anesthesiology-and-intensive-care-medicine","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:29:50Z","timestamp":1784305790000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cureus.com\/articles\/515187-comparative-performance-of-large-language-models-in-the-polish-state-specialization-examination-in-anesthesiology-and-intensive-care-medicine"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"references-count":23,"URL":"https:\/\/doi.org\/10.7759\/cureus.112868","relation":{},"ISSN":["2168-8184"],"issn-type":[{"value":"2168-8184","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7,17]]}}}