{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T18:11:21Z","timestamp":1793211081433,"version":"4.5.0"},"reference-count":15,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Surgical Oncology"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The management of rectal adenocarcinoma requires navigation of complex, branching guideline pathways encompassing neoadjuvant sequencing, surgical approach, organ preservation, and surveillance, yet real\u2010world guideline adherence remains as low as 60\u201370%. The ability of current\u2010generation large language models (LLMs) to accurately navigate these decision points has not been fully characterized.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this cross\u2010sectional, vignette\u2010based study, 135 clinical questions were constructed from 45 pages of NCCN Rectal Cancer Guidelines (Version 4.2024). ChatGPT\u20104o was queried using standardized prompts with up to 3 clarifying questions permitted per query. Responses were independently evaluated by two physician raters on a 5\u2010point Likert scale, with potential discrepancies adjudicated by a board\u2010certified surgical oncologist. Primary outcomes were the proportion of responses rated Correct (score \u2265\u20093) and Accurate (score \u2265\u20094). Inter\u2010rater reliability was assessed using Cohen's kappa, and subgroup analysis was performed across clinical domains using the Kruskal\u2010Wallis test.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Of 135 questions, 127 (94.1%; 95% CI, 88.7\u201397.0%) were Correct and 121 (89.6%; 95% CI, 83.3\u201393.7%) were Accurate. One hundred two responses (75.6%) were completely correct without additional prompting. Performance was consistent across clinical domains (Kruskal\u2010Wallis H\u2009=\u20090.530,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.767). Inter\u2010rater agreement was perfect (\u03ba\u2009=\u20091.0). Eight responses (5.9%) contained partially or wholly incorrect information, with errors concentrated in multi\u2010step conditional treatment decision points.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ChatGPT\u20104o demonstrates high concordance with NCCN rectal cancer guidelines across all evaluated clinical domains with notable improvement over prior ChatGPT iterations evaluated by our group. The concentration of errors in complex conditional treatment algorithms suggests that LLMs excel at discrete factual recall but may struggle with multi\u2010step reasoning under clinical uncertainty. Prospective validation using real\u2010world clinical data and comparison with multidisciplinary tumor board recommendations remain necessary prior to clinical integration.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/jso.70314","type":"journal-article","created":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T16:51:31Z","timestamp":1783270291000},"page":"525-530","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Evaluating the Accuracy of ChatGPT\u20104o in Addressing Complex Clinical Questions Based on NCCN Guidelines for Rectal Adenocarcinoma"],"prefix":"10.1002","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5847-9577","authenticated-orcid":false,"given":"Ryan","family":"Meyer","sequence":"first","affiliation":[{"name":"Department of Surgery Los Robles Regional Medical Center Thousand Oaks California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8397-9186","authenticated-orcid":false,"given":"Tamir E.","family":"Bresler","sequence":"additional","affiliation":[{"name":"Department of Surgery Los Robles Regional Medical Center Thousand Oaks California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8353-7598","authenticated-orcid":false,"given":"Kevin M.","family":"Palmer","sequence":"additional","affiliation":[{"name":"Department of Surgery Los Robles Regional Medical Center Thousand Oaks California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7992-3328","authenticated-orcid":false,"given":"Tyler","family":"Wilson","sequence":"additional","affiliation":[{"name":"Department of Surgery Los Robles Regional Medical Center Thousand Oaks California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shivam","family":"Pandya","sequence":"additional","affiliation":[{"name":"Department of Surgery Los Robles Regional Medical Center Thousand Oaks California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manabu","family":"Fujita","sequence":"additional","affiliation":[{"name":"Department of Surgery Los Robles Regional Medical Center Thousand Oaks California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"issue":"1","key":"e_1_2_11_2_1","first-page":"65","article-title":"Rectal Cancer, Version 1.2024. Nccn Clinical Practice Guidelines in Oncology","volume":"22","author":"Benson A. B.","year":"2024","journal-title":"Journal of the National Comprehensive Cancer Network: JNCCN"},{"key":"e_1_2_11_3_1","unstructured":"NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines\u00ae) for Rectal Cancer V.4. \u00a9 National Comprehensive Cancer Network Inc 2024 All rights reserved; 2024 accessed 3 August 2024."},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1097\/DCR.0000000000002341"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1097\/DCR.0000000000003586"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40593-024-00452-8"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/oto2.70075"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12094-025-03905-1"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1097\/DCR.0000000000003504"},{"key":"e_1_2_11_10_1","unstructured":"OpenAI. GPT\u20104o System Card 2024 accessed June 3 2025 https:\/\/openai.com\/index\/gpt-4o-system-card\/."},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/jso.70005"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1177\/00031348241248801"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1177\/00031348241269430"},{"issue":"1","key":"e_1_2_11_14_1","article-title":"Evaluating the Performance of ChatGPT\u20104o Oncology Expert in Comparison to Standard Medical Oncology Knowledge: A Focus on Treatment\u2010Related Clinical Questions","volume":"17","author":"Kinikoglu O.","year":"2025","journal-title":"Cureus"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejso.2025.110096"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01670-7"}],"container-title":["Journal of Surgical Oncology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jso.70314","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jso.70314","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jso.70314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T06:53:30Z","timestamp":1789455210000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jso.70314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":15,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1002\/jso.70314"],"URL":"https:\/\/doi.org\/10.1002\/jso.70314","archive":["Portico"],"relation":{},"ISSN":["0022-4790","1096-9098"],"issn-type":[{"value":"0022-4790","type":"print"},{"value":"1096-9098","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-02-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}