{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:06:12Z","timestamp":1782846372781,"version":"3.54.5"},"reference-count":38,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Perioper Med"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Artificial intelligence (AI) models are being increasingly integrated into clinical care. Moreover, the availability of publicly accessible AI resources makes them attractive to patients seeking clinical information. Little is known regarding the use of large language models as patient resources for navigating major cancer diagnoses.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to evaluate the content, readability, and safety of ChatGPT (OpenAI; GPT-4o)-generated responses to common perioperative queries about hepatic, pancreatic, and colon cancers.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A 28-question survey was developed based on frequently asked surgical questions for select malignancies. Surgical oncologists rated ChatGPT-4o-generated responses on a 5-point Likert scale for accuracy, quality, and tangibility. Readability was assessed using the Flesch-Kincaid Reading Grade Level (FKRGL) and Flesch Reading Ease (FRE). Respondents provided free-text comments and reported their comfort with patients using ChatGPT. Survey completion implied consent.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n A total of 7 attending surgical oncologists with a median of 7 (IQR 4-13) years in practice completed the survey. Responses received mean scores of 3.5\/5 (SD 0.28) for quality, 3.6\/5 (SD 0.34) for accuracy, and 3.6\/5 (SD 0.29) for tangibility. The responses had a median FKRGL score of 14.6 (IQR 13.3-15.6) and FRE score of 29.4 (IQR 20.5-36.3). On a post hoc analysis for select questions, the median FKRGL was 15.6 (IQR 14.4-16.7), decreasing to 7.1 (IQR 6.1-8.3) and 14.5 (IQR 13.2-15.4) with prompting and rephrasing, and the median FRE was 18.1 (IQR 14.6-24.7), increasing to 73.8 (IQR 66.6-79.3) and 32.0 (IQR 27.0-37.7) with prompting and rephrasing. Numerous inaccuracies and content gaps were reported, and approximately 43% (3\/7) of providers did not report feeling \u201ccomfortable\u201d in having patients consult publicly available AI for medical information.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study provides cautionary, yet optimistic, findings regarding the value of publicly accessible ChatGPT as a patient resource for abdominal malignancies. Providers should be prepared to effectively counsel patients to identify their educational attainment level when using ChatGPT to mitigate readability challenges.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/81374","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T22:40:09Z","timestamp":1773355209000},"page":"e81374-e81374","source":"Crossref","is-referenced-by-count":0,"title":["Physician Perspectives on ChatGPT-4o as a Patient Resource for Abdominal Cancer Surgeries: Cross-Sectional Survey"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6421-0996","authenticated-orcid":false,"given":"Christina V","family":"Lindsay","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7543-5414","authenticated-orcid":false,"given":"Devika A","family":"Shenoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9216-0647","authenticated-orcid":false,"given":"Allison N","family":"Martin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6566-3548","authenticated-orcid":false,"given":"Christie L","family":"Clipper","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8466-4001","authenticated-orcid":false,"given":"Kevin N","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0500-2016","authenticated-orcid":false,"given":"Michael E","family":"Lidsky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3070-6605","authenticated-orcid":false,"given":"Daniel P","family":"Nussbaum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5252-5036","authenticated-orcid":false,"given":"Ralph","family":"Snyderman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,5,4]]},"reference":[{"key":"R1","unstructured":"ChatGPT. URL: https:\/\/chatgpt.com [Accessed 09-03-2025]"},{"key":"R2","unstructured":"Guinness H . How does ChatGPT work? Zapier. URL: https:\/\/zapier.com\/blog\/how-does-chatgpt-work\/ [Accessed 15-04-2025]"},{"key":"R3","unstructured":"Bubeck S Chandrasekaran V Eldan R Gehrke J Horvitz E Kamar E et al. Sparks of artificial general intelligence: early experiments with GPT-4. arXiv. Preprint posted online on Mar 22, 2023. [doi: 10.48550\/arXiv.2303.12712]"},{"issue":"2","key":"R4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198","article-title":"Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models","volume":"2","author":"Kung","journal-title":"PLOS Digit Health"},{"key":"R5","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","journal-title":"JMIR Med Educ"},{"issue":"12","key":"R6","doi-asserted-by":"publisher","first-page":"NP1078","DOI":"10.1093\/asj\/sjad128","article-title":"Performance of ChatGPT on the plastic surgery inservice training examination","volume":"43","author":"Gupta","journal-title":"Aesthet Surg J"},{"issue":"9","key":"R7","doi-asserted-by":"publisher","first-page":"4271","DOI":"10.1007\/s00405-023-08051-4","article-title":"ChatGPT\u2019s quiz skills in different otolaryngology subspecialties: an analysis of 2576 single-choice and multiple-choice board certification preparation questions","volume":"280","author":"Hoch","journal-title":"Eur Arch Otorhinolaryngol"},{"issue":"8","key":"R8","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1001\/jamaophthalmol.2023.2754","article-title":"Performance of an upgraded artificial intelligence chatbot for ophthalmic knowledge assessment","volume":"141","author":"Mihalache","journal-title":"JAMA Ophthalmol"},{"issue":"5","key":"R9","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1001\/jamainternmed.2024.0295","article-title":"Clinical reasoning of a generative artificial intelligence model compared with physicians","volume":"184","author":"Cabral","journal-title":"JAMA Intern Med"},{"issue":"6","key":"R10","doi-asserted-by":"publisher","first-page":"3701","DOI":"10.1097\/JS9.0000000000001312","article-title":"ChatGPT in medicine: prospects and challenges: a review article","volume":"110","author":"Tan","journal-title":"Int J Surg"},{"issue":"4","key":"R11","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1007\/s00266-023-03713-4","article-title":"Consulting the digital doctor: Google versus ChatGPT as sources of information on breast implant-associated anaplastic large cell lymphoma and breast implant illness","volume":"48","author":"Liu","journal-title":"Aesthetic Plast Surg"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.2196\/40466","article-title":"Internet use for obtaining medicine information: cross-sectional survey","volume":"7","author":"Bergmo","journal-title":"JMIR Form Res"},{"issue":"3","key":"R13","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1111\/ans.18289","article-title":"Dr Google - assessing the reliability and readability of information on general surgical procedures found via search engines","volume":"93","author":"Ramli","journal-title":"ANZ J Surg"},{"issue":"4","key":"R14","doi-asserted-by":"publisher","first-page":"210","DOI":"10.5694\/mja2.52598","article-title":"Use of ChatGPT to obtain health information in Australia, 2024: insights from a nationally representative survey","volume":"222","author":"Ayre","journal-title":"Med J Aust"},{"issue":"6","key":"R15","doi-asserted-by":"publisher","first-page":"3219","DOI":"10.1007\/s00405-024-08524-0","article-title":"ChatGPT vs. web search for patient questions: what does ChatGPT do better?","volume":"281","author":"Shen","journal-title":"Eur Arch Otorhinolaryngol"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","DOI":"10.1002\/jeo2.70138","article-title":"Assessing ChatGPT responses to common patient questions regarding total ankle arthroplasty","volume":"12","author":"Artioli","journal-title":"J Exp Orthop"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1227\/neu.0000000000002856","article-title":"Usefulness and accuracy of artificial intelligence chatbot responses to patient questions for neurosurgical procedures","volume":"95","author":"Gajjar","journal-title":"Neurosurgery"},{"issue":"6","key":"R18","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.1007\/s11695-023-06603-5","article-title":"Assessing the accuracy of responses by the language model ChatGPT to questions regarding bariatric surgery","volume":"33","author":"Samaan","journal-title":"Obes Surg"},{"issue":"3","key":"R19","doi-asserted-by":"publisher","first-page":"721","DOI":"10.3350\/cmh.2023.0089","article-title":"Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma","volume":"29","author":"Yeo","journal-title":"Clin Mol Hepatol"},{"issue":"5","key":"R20","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300151","article-title":"Comparative evaluation of LLMs in clinical oncology","volume":"1","author":"Rydzewski","journal-title":"NEJM AI"},{"issue":"2","key":"R21","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1053\/j.gastro.2023.04.033","article-title":"ChatGPT answers common patient questions about colonoscopy","volume":"165","author":"Lee","journal-title":"Gastroenterology"},{"issue":"6","key":"R22","doi-asserted-by":"publisher","first-page":"E278","DOI":"10.1097\/BSD.0000000000001600","article-title":"Chat generative pretraining transformer answers patient-focused questions in cervical spine surgery","volume":"37","author":"Subramanian","journal-title":"Clin Spine Surg"},{"issue":"12","key":"R23","doi-asserted-by":"publisher","first-page":"1590","DOI":"10.1016\/j.sapharm.2023.08.012","article-title":"Assessing the accuracy and consistency of ChatGPT in clinical pharmacy management: a preliminary analysis with clinical pharmacy experts worldwide","volume":"19","author":"Al-Dujaili","journal-title":"Res Social Adm Pharm"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1053\/j.gastro.2020.02.068","article-title":"Global burden of 5 major types of gastrointestinal cancer","volume":"159","author":"Arnold","journal-title":"Gastroenterology"},{"key":"R25","unstructured":"Pancreatic cancer questions to ask the healthcare team. Pancreatic Cancer Action Network. 2025. URL: https:\/\/pancan.org\/facing-pancreatic-cancer\/diagnosis\/choosing-your-healthcare-team\/questions-to-ask-your-healthcare-team [Accessed 15-01-2025]"},{"key":"R26","unstructured":"Colon cancer FAQs. Moffitt Cancer Center. 2025. URL: https:\/\/www.moffitt.org\/cancers\/colon-cancer\/faqs [Accessed 15-01-2025]"},{"key":"R27","unstructured":"Frequently asked questions. Mount Sinai Tisch Cancer Center. 2025. URL: https:\/\/www.mountsinai.org\/care\/cancer\/services\/colon\/faqs [Accessed 15-01-2025]"},{"key":"R28","unstructured":"Liver cancer \u2013 frequently asked questions. Pelican Cancer Foundation. 2025. URL: https:\/\/www.pelicancancer.org\/patient-resources\/liver-cancer\/frequently-asked-questions [Accessed 15-01-2025]"},{"key":"R29","unstructured":"Questions to ask about pancreatic cancer. American Cancer Society. 2024. URL: https:\/\/www.cancer.org\/cancer\/types\/pancreatic-cancer\/detection-diagnosis-staging\/talking-with-doctor.html [Accessed 15-01-2025]"},{"key":"R30","unstructured":"Questions to ask about liver cancer. American Cancer Society. 2025. URL: https:\/\/www.cancer.org\/cancer\/types\/liver-cancer\/detection-diagnosis-staging\/talking-with-doctor.html [Accessed 15-01-2025]"},{"key":"R31","unstructured":"Frequently asked questions. Hirshberg Foundation for Pancreatic Cancer Research. 2025. URL: https:\/\/pancreatic.org\/pancreatic-cancer\/faqs [Accessed 15-01-2025]"},{"issue":"4","key":"R32","doi-asserted-by":"publisher","first-page":"1174","DOI":"10.1016\/j.jtcvs.2024.09.030","article-title":"Evaluating ChatGPT as a patient resource for frequently asked questions about lung cancer surgery-a pilot study","volume":"169","author":"Ferrari-Light","journal-title":"J Thorac Cardiovasc Surg"},{"key":"R33","unstructured":"ChatGPT \u2014 release notes. OpenAI. 2026. URL: https:\/\/help.openai.com\/en\/articles\/6825453-chatgpt-release-notes?utm_source=chatgpt.com [Accessed 01-03-2026]"},{"issue":"1","key":"R34","doi-asserted-by":"publisher","first-page":"84","DOI":"10.4103\/1357-6283.210517","article-title":"Assessing reading levels of health information: uses and limitations of flesch formula","volume":"30","author":"Jindal","journal-title":"Educ Health (Abingdon)"},{"issue":"1","key":"R35","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.gassur.2023.11.019","article-title":"Online artificial intelligence platforms and their applicability to gastrointestinal surgical operations","volume":"28","author":"Munir","journal-title":"J Gastrointest Surg"},{"key":"R36","unstructured":"AHRQ health literacy universal precautions toolkit. Agency for Healthcare Research and Quality (AHRQ); 2024. URL: https:\/\/www.ahrq.gov\/sites\/default\/files\/wysiwyg\/health-literacy\/3rd-edition-toolkit\/health-literacy-toolkit-third-edition.pdf [Accessed 20-04-2025]"},{"issue":"9","key":"R37","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1007\/s11606-012-2046-0","article-title":"Readability of patient education materials available at the point of care","volume":"27","author":"Stossel","journal-title":"J Gen Intern Med"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.2196\/51421","article-title":"Exploring the possible use of AI chatbots in public health education: feasibility study","volume":"9","author":"Baglivo","journal-title":"JMIR Med Educ"}],"container-title":["JMIR Perioperative Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/periop.jmir.org\/2026\/1\/e81374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:15:08Z","timestamp":1782843308000},"score":1,"resource":{"primary":{"URL":"https:\/\/periop.jmir.org\/2026\/1\/e81374"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,4]]},"references-count":38,"URL":"https:\/\/doi.org\/10.2196\/81374","relation":{},"ISSN":["2561-9128"],"issn-type":[{"value":"2561-9128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,4]]},"article-number":"v9i2e81374"}}